The aim of this study was to explore and develop a preoperative and noninvasive model for predicting spread through air spaces (STAS) status in lung adenocarcinoma (LUAD) with diameter ≤ 3 cm.

This multicenter retrospective study included 640 LUAD patients. Center I included 525 patients (368 in the training cohort and 157 in the validation cohort); center II included 115 patients (the test cohort). We extracted radiomics features from the intratumor, extended tumor and peritumor regions. Multivariate logistic regression and boruta algorithm were used to select clinical independent risk factors and radiomics features, respectively. We developed a clinical model and four radiomics models (the intratumor model, extended tumor model, peritumor model and fusion model). A nomogram based on prediction probability value of the optimal radiomics model and clinical independent risk factors was developed to predict STAS status.

Maximum diameter and nodule type were clinical independent risk factors. The extended tumor model achieved satisfactory STAS status discrimination performance with the AUC of 0.74, 0.71 and 0.80 in the three cohorts, respectively, performed better than other radiomics models. The integrated discrimination improvement value revealed that the nomogram outperformed compared to the clinical model with the value of 12 %. Patients with high nomogram score (≥ 77.31) will be identified as STAS-positive.

Peritumoral information is significant to predict STAS status. The nomogram based on the extended tumor model and clinical independent risk factors provided good preoperative prediction of STAS status in LUAD with diameter ≤ 3 cm, aiding surgical decision-making.

BackgroundSpread through air spaces (STAS) in lung adenocarcinoma means different treatment and worse prognosis.PurposeTo construct a radiomics model based on CT scans to predict the presence of STAS in stage IA lung adenocarcinoma, compared with the traditional clinical model.Material and MethodsThe study included 317 patients (median age = 57.21 years; age range = 45.84-68.61 years) with pathologically confirmed stage IA lung adenocarcinoma. In total, 122 (38.5%) patients were diagnosed with STAS by pathology after the operation. Two experienced radiologists independently segmented the lesions using MITK software and extracted 1791 radiomics features using Python. Single-factor t-test or Mann-Whitney U-test and LASSO were used to screen for radiomics signatures related to STAS. This study constructed a radiomics model, a clinical model, and a combined model, combining radiomics and clinical features. Model performance was evaluated using the area under the curve (AUC).ResultsBy single-factor analysis, four clinical features and 13 radiomics features were significantly associated with STAS. The three models (the clinical, radiomics, and combine models) achieved predictive efficacy, with an AUC of 0.849, 0.867, and 0.939, respectively, in the training set and 0.808, 0.848, and 0.876, respectively, in the testing set.ConclusionThe combined model based on the radiomics and clinical features of preoperative chest CT could be used to preoperatively diagnose the presence of STAS in stage IA lung adenocarcinoma and has an excellent diagnostic performance.

To develop and validate an individualized nomogram for distinguishing between benign and malignant subpleural pulmonary lesions (SPLs) using B-mode ultrasound imaging and clinical data.

A total of 425 patients with SPLs were enrolled and classified into two groups: 220 patients were diagnosed with malignant lesions, and 205 with benign lesions. Patients were randomly assigned to a development cohort (DC, n = 297) and a validation cohort (VC, n = 128) in a 7:3 ratio. Statistical analyses included rank-sum tests and chi-square tests. Boruta analysis was used to identify key features associated with malignant SPLs. The multivariable logistic regression model based on independent malignant SPL factors was developed and represented as a nomogram. The model's performance was assessed in terms of discrimination, calibration and clinical utility.

Six variables were selected to construct the nomogram: age, pack-year of smoking, air bronchogram, the angle between the lesion border and the thoracic wall, posterior echo of the lesion and visceral pleural invasion. The area under the receiver operating characteristic curve for the model was 0.859 (95% CI: 0.816-0.901) in the DC and 0.862 (95% CI: 0.800-0.923) in the VC. Calibration curve analysis demonstrated that the nomogram closely aligned with the ideal curve, reflecting its good calibration. Furthermore, decision curve analysis, clinical impact curve (CIC) and net reduction curve (NRC) further confirmed the model's favorable clinical utility.

We have developed a nomogram that serves as an effective tool for assessing malignant SPLs. This model holds significant promise as a complementary diagnostic aid, particularly in primary healthcare settings and bedside examination.

The rising incidence of multiple lung cancers (MLCs), encompassing multiple primary lung cancers (MPLCs) and intrapulmonary metastasis (IPM), poses two significant clinical challenges. First, distinguishing between MPLC and IPM remains difficult due to insufficiently accurate criteria and ambiguous integration of genetic testing. Second, standardized therapeutic protocols are still lacking. To address these issues, the Lung Cancer Expert Committee of China Anti-Cancer Association (CACA) assembled a multidisciplinary expert panel spanning thoracic surgery, pulmonary medicine, oncology, radiology, and pathology. Following a comprehensive literature review ending on October 23, 2024, the panel engaged in iterative discussions and conducted two rounds of expert voting, culminating in 25 evidence-based recommendations across five key domains: epidemiology, pre-treatment evaluation, definitive diagnostics, surgical treatment, and non-surgical treatment. This consensus provides clinicians with practical guidance to enhance diagnostic precision and therapeutic decision-making in MLC management while highlighting unmet needs to inform future guideline development.

Cytological examination serves as a crucial diagnostic tool for pleural effusion, with its diagnostic efficacy influenced by variations in specimen processing and staining techniques. Cellular morphological analysis of pleural effusions was performed using Wright-Giemsa staining to assess its diagnostic accuracy and clinical utility in differentiating the various etiologies of exudative pleural effusion. A routine examination was conducted on 2305 cases of unexplained pleural effusion, followed by cellular classification and morphological analysis in 1376 cases identified as exudative effusion. Among the 479 patients with malignant tumors, cytomorphological examination identified malignant cells in 295 patients, resulting in a clinical diagnosis coincidence rate of 98.6%. Abnormal cells, including malignant and heterogeneous nuclear cells, were observed in 364 cases, yielding a detection rate of 76.0%. The proportion of positive malignant cells in the newly diagnosed patient group was significantly higher than that in the previously diagnosed group (P < 0.01). Cytological analysis revealed the presence of bacteria, fungi, and phagocytes in 51 out of 1376 cases. The positivity rate for multiple bacterial infections detected through cytology was significantly greater than that identified by culture (P < 0.01). Additionally, various special morphologies and pathogens, which are rare in clinical practice, were detected, including mixed metastasis of small cell lung carcinoma and adenocarcinoma cells, as well as concurrent infections with Talaromyces marneffei and Pneumocystis jirovecii. This method enables the rapid and comprehensive differentiation between malignant tumors, tuberculosis, pneumonia, and rare exudative pleural effusions resulting from specific clinical conditions.

Doege-Potter syndrome (DPS) is a rare condition that causes hypoinsulinaemic hypoglycaemia due to solitary fibrous tumours (SFTs). This case report details the treatment of a man in middle adulthood (ages 40-65) diagnosed with DPS after experiencing syncope and vasovagal episodes, which led to the discovery of a large mass in the pleura. Following various diagnostic tests confirming the SFT, the patient required anticonvulsant therapy and glucose infusions due to recurrent seizures and severe hypoglycaemia prior to surgery. After the surgical removal of the tumour, both hypoglycaemia and the need for anticonvulsants were resolved. This case highlights the importance of considering DPS in patients with unexplained hypoglycaemia and intrathoracic masses. It concludes that surgical resection is the preferred treatment for SFTs associated with DPS, offering a favourable prognosis, and emphasises the need for regular follow-up to monitor for potential recurrence.

Transforming growth factor-β (TGF-β) plays a complex role in lung cancer pathophysiology, initially acting as a tumor suppressor by inhibiting early-stage tumor growth. However, its role evolves in the advanced stages of the disease, where it contributes to tumor progression not by directly promoting cell proliferation but by enhancing epithelial-mesenchymal transition (EMT) and creating a conducive tumor microenvironment. While EMT is typically associated with enhanced migratory and invasive capabilities rather than proliferation per se, TGF-β's influence on this process facilitates the complex dynamics of tumor metastasis. Additionally, TGF-β impacts the tumor microenvironment by interacting with immune cells, a process influenced by genetic and epigenetic changes within tumor cells. This interaction highlights its role in immune evasion and chemoresistance, further complicating lung cancer therapy. This review provides a critical overview of recent findings on TGF-β's involvement in lung cancer, its contribution to chemoresistance, and its modulation of the immune response. Despite the considerable challenges encountered in clinical trials and the development of new treatments targeting the TGF-β pathway, this review highlights the necessity for continued, in-depth investigation into the roles of TGF-β. A deeper comprehension of these roles may lead to novel, targeted therapies for lung cancer. Despite the intricate behavior of TGF-β signaling in tumors and previous challenges, further research could yield innovative treatment strategies.

Spread through air spaces (STAS) represents a relatively novel concept in the pathology of lung cancer, and it specifically refers to the dissemination of tumour cells into the parenchymal air spaces adjacent to the primary tumour. In 2015, the World Health Organization (WHO) classified STAS as a new invasive form of lung adenocarcinoma (LUAD). Many studies investigated the role of STAS and revealed its association with the prognosis of LUAD and its influence on the outcomes of other malignant pulmonary neoplasms. Additionally, the underlying mechanisms and predictive models of STAS have received considerable attention in recent years. This paper provides a comprehensive overview of the research advancements and prospects of STAS by examining it from multiple perspectives.

In Jordan, lung cancer ranks as the second most common tumor, and there is an urgent need to explore the genetic landscape of lung cancer. This study aimed to identify the actionable mutations in lung cancer samples in Jordanians by targeted next-generation sequencing (NGS) and to investigate the correlations with clinical and pathological parameters.

Totally, 121samples were prepared for NGS by DNA extractions from formalin-fixed paraffin-embedded (FFPE) blocks, followed by library preparation using the AmpliSeq Colon and Lung panel, which covers mutational hot spot regions for 22 cancer genes.

Amongst 121 patients, 88% of those treated for non-small lung carcinoma were successfully analyzed; 35 (29%) carried one mutation or more in actionable genes (KRAS, EGFR, ALK, BRAF, and MET). There are no significant differences between actionable mutation carriers and non-carriers concerning histological tumor type, tumor stage, metastasis, smoking habits, and gender. However, the analysis of survival probabilities revealed lower survival times for females compared to males, as well as for those patients who had metastasis events, smoking, or relapse after treatment.

The type and rates of mutations detected for lung tumors in Jordan are relatively similar to those found in other populations previously studied, although some differences exist. However, lung tumors in Jordan require new customized treatment prescriptions based on prior genetic studies, as part of the hoped-for trend toward precision medicine.

There is still a debate regarding the prognostic implication of lymphovascular invasion (LVI) in stage I lung adenocarcinoma. Ground-glass opacity (GGO) on CT is known to correlate with a less invasive or lepidic component in adenocarcinoma, which may influence the strength of prognostic factors. This study aimed to explore the prognostic value of LVI in stage I lung adenocarcinoma based on the presence of GGO.

Stage I lung adenocarcinoma patients receiving lobectomy between 2010 and 2019 were retrospectively categorized as GGO-positive or GGO-negative (solid adenocarcinoma) on CT. Multivariable Cox regression analyses were performed for disease-free survival (DFS) and overall survival (OS) to evaluate the prognostic significance of pathologic LVI based on the presence of GGO.

Of 924 patients included (mean age, 62.5 ± 9.2 years; 505 women), 525 (56.8%) exhibited GGO-positive adenocarcinoma and 116 (12.6%) were diagnosed with LVI. LVI was significantly more frequent in solid than GGO-positive adenocarcinoma (20.1% vs. 6.9%, p < 0.001). Multivariable analysis identified LVI and visceral pleural invasion (VPI) as significant prognostic factors for shorter DFS among solid adenocarcinoma patients (LVI, hazard ratio (HR): 1.89, p = 0.004; VPI, HR: 1.65, p = 0.003) but not GGO-positive patients (p = 0.76 and p = 0.87). In contrast, LVI was not a significant prognostic factor for OS in either group (p > 0.05).

In stage I lung adenocarcinoma, pathologic LVI was associated with DFS only in patients with solid lung adenocarcinoma.

Lymphovascular invasion (LVI) significantly affects disease-free survival in solid-stage I lung adenocarcinoma patients, but not those with ground-glass opacity (GGO) adenocarcinoma. Risk stratification considering both GGO on CT and LVI may identify patients benefiting from increased surveillance.

The presence of ground-glass opacity portends different prognoses for lung adenocarcinoma. In stage I lung adenocarcinoma, lymphovascular invasion (LVI) was significantly more frequent in solid adenocarcinomas than in ground-glass opacity (GGO)-positive adenocarcinomas. LVI was not associated with overall survival in patients with either solid adenocarcinomas or GGO adenocarcinomas.

Multi-omic studies have identified three molecular separated pulmonary carcinoid (PC) subgroups (A1, A2, B) with distinctive mRNA expression profiles (e.g., orthopedia homeobox protein [OTP], achaete-scute homolog [ASCL1], and hepatocyte nuclear factor 1 homeobox A [HNF1A]). We aimed to establish an immunohistochemical (IHC) biomarker panel that enables subgroup identification, and assessment of its potential clinical relevance.

All patients with resected pulmonary carcinoids (2003-2012) were identified from the Dutch Cancer/Pathology Registry, and tumors were revised. The IHC expression of OTP, ASCL1, and HNF1A was scored in a blinded fashion in a mRNA-profiled (n = 5 per subgroup) and national carcinoid cohort (N = 478). The expression of potential therapeutic targets (somatostatin receptor type 2a [SSTR2A] and delta-like canonical Notch ligand 3 [DLL3]) was assessed. Immunohistochemistry was assessed using H-scoring.

OTP, ASCL1, and HNF1A reported similar IHC and mRNA expression patterns in the matched primary samples. In the national cohort, IHC separated PCs into subgroups A1 (n = 224 [53%], OTPhigh-ASCL1high-HNF1Alow), A2 (n = 161 [38%], OTPhigh-ASCL1low-HNF1Ahigh), and B (n = 37 [9%], OTPlow-ASCL1low-HNF1Ahigh). In 12% of PCs, no distinct classification could be provided. Patients with A1 were enriched for older age (83% > 50 y), female individuals (83%), and peripheral location (55%) with low SSTR2A (median = 10) and high DLL3 (median = 52) expression. A2 included younger patients (34% < 40 y) and endobronchial/central (87%) tumors with high SSTR2A (median = 160), but low DLL3 (median 0) expression. Group B included more male individuals (59%) and recurrence was more frequent (19%) than in groups A1 (8%) and A2 (6%). Neuroendocrine cell hyperplasia was enriched in A1 (25%) compared with A2 (3%) and B (0%).

An OTP, ASCL1, and HNF1A IHC panel enables the identification of molecular-defined pulmonary carcinoid subgroups with distinct clinical phenotypes and diverging therapeutic vulnerabilities that require further prospective evaluation.

Despite significant therapeutic advances, lung cancer remains the biggest killer among cancers. In France, there is no national screening program against lung cancer. Thus, in this perspective, the Foch Hospital decided to implement a pilot and clinical low-dose CT screening program to evaluate the efficiency of such screening. The purpose of this study was to describe the prevalent findings of this low-dose CT screening program. Participants were recruited in the screening program through general practitioners (GPs), pharmacists, and specialists from June 2023 to June 2024. The inclusion criteria included male or female participants aged 50 to 80 years, current smokers or former smokers who had quit less than 15 years prior, with a smoking history of over 20 pack-years. Chest CT scans were conducted at Foch Hospital using a low-dose CT protocol based on volume mode with a multi-slice scanner (≥60 slices) without contrast injection. In total, 477 participants were recruited in the CT scan screening, 235 (49%) were males with a median age of 60 years [56-67] and 35 smoke pack-years [29-44] and 242 females (51%) with a median age of 60 years [55-60] and 30 smoke pack-years [25-40]. Eight participants showed positive nodules on CT scan, as a 1.7% rate. 66.7% of diagnosed cancers were in early stages (0-I). It is feasible to implement structured lung cancer screening using low-dose CT in a real-world setting among the general population. This approach successfully identifies most early-stage cancers that could be treated curatively.

NCCN guidelines recommend surgical resection for well differentiated pulmonary neuroendocrine tumors (NETs), also known as carcinoid tumors, when they present in the lungs. Fortunately, most pulmonary NETs will not require extensive surgical resection beyond a lobectomy. We report two cases in which large pulmonary NETs would have required more extensive surgical resection, including a carinal pneumonectomy and a left lower lobe sleeve resection. However, after taking patient's preferences into account, neoadjuvant photodynamic therapy was able to decrease the overall tumor burden helping to facilitate airway and parenchymal sparing surgical lobectomies.

Interventional pulmonology (IP) and Cardiothoracic surgery (CTS) discussed options extensively with each patient and formulated a plan to perform neoadjuvant bronchoscopic followed by surgical resection if there were any remaining NET on follow up bronchoscopy. Both patients received infusions of porfimer sodium (Photofrin ®, Pinnacle Biologics) at 2mg/kg. Per standard protocol, they each underwent a series of bronchoscopies 48 h after infusion, in which endobronchial NET was illuminated with a fiberoptic catheter delivering up to 200J/cm per treatment. After the initial illumination bronchoscopy, a cryo probe was used to debulk necrotic tumor and allow for repeat illumination of residual tumor. Both patients received extensive education on avoiding phototoxicity.

Both patients underwent follow up restaging bronchoscopies revealing cleared central airways and only residual NET at the subsegmental level. As such, both underwent lobectomies, avoiding more extensive surgical resection. Both are free of disease at four years and 18 months follow up, respectively. Both patients were satisfied with their outcomes and the autonomy they were given in formulating their treatment plan.

While photodynamic therapy has been shown to be an effective stand alone, neoadjuvant, and adjuvant therapy for pulmonary NETs, surgical resection is still required in select patients. We present two cases of in which desired patient outcomes led to the use of neoadjuvant PDT to help facilitate airway and parenchymal sparing lobectomies, thus avoiding more extensive surgical resection and possible long-term morbidity.

Bronchopulmonary carcinoids (BPCs) are classified into typical carcinoids (TC) and atypical carcinoids (AC), based on the mitotic count and absence/presence of necrosis on pathology specimens. There are limitations to accurate measurement of these criteria. It important to study other markers like Ki-67, to enhance the diagnostic accuracy of lung carcinoids.

Retrospective analysis of BPCs treated with surgery between 2012-2022, to examine the accuracy of Ki-67 on the diagnostic specimen, concordance of diagnostic and resection specimens, diagnostic accuracy of Positron Emission Tomography (PET) and concordance of clinical and pathological staging.

205 patients were included in the analysis (final diagnosis TC 180, AC 25). Mean age 60.5 years and 68 % female. Ki-67 (<5% vs. 5-30 %) on diagnostic biopsy, available in 64 % (n = 131) of the cohort, had specificity (diagnose TC correctly) of 89.4 % (95 %CI 80.4 %-94.7 %) and sensitivity (diagnose AC correctly) of 77.8 % (40.2 %-96.1 %). This compared to 97.5 % (90.3 %-99.6 %) and 36.4 % (12.4 %-68.4 %) for mitotic count (<2mitoses/2mm2 vs. 2-10mitoses/2mm2) and 100 % (94.4 %-100 %) and 21.4 % (5.7 %-51.2 %) for necrosis (absence vs. presence). A pre-resection diagnosis of TC (including surgical biopsy) shows better concordance with final diagnosis on resection specimen (94.9 %, 95 %CI 88.7 %-97.9 %, n = 117) as compared to the diagnosis of AC 83.3 % (95 %CI 50.9 %-97.1 %, n = 12). Concordance for AC appears higher with image guided lung biopsy 80 % (95 % CI, 29.9 %-98.9 %) than bronchoscopy 50 % (9.5 %-90.5 %). SUVmax on 18FDG-PET was a modest predictor of BPC sub-type with an AUC of 0.684 (95 % CI: 0.545,0.823). The clinical and pathological staging were concordant in 46 % (85/184) cases. However, 27 % (50/184) were upstaged and 13 % (23/172) found to have occult nodal metastases on pathology review of the surgical specimens.

The diagnosis and sub-typing of BPCs on diagnostic specimens is challenging. Our data suggest Ki-67 could increase diagnostic accuracy, but further research is needed to confirm this.

Pulmonary carcinosarcoma is a rare tumor composed of non-small-cell carcinomas and sarcomatous elements, which is poorly differentiated in most cases. We present a case of carcinosarcoma with a well-differentiated carcinomatous component that required a differential diagnosis from tumors derived from teratomas, such as teratocarcinosarcoma. We present a case of a 68-year-old man who visited our hospital for an examination of a 22-mm lung tumor. The patient underwent left S1+2 segmentectomy, and his postoperative course was uneventful. No recurrence was observed in the 21-month postoperative follow-up period. The segmentectomy specimen revealed a yellow-white, well-circumscribed mass. The tumor consisted of well-differentiated squamous and glandular epithelia, and sarcomatous components of immature spindle cells, chondrosarcoma, and rhabdomyosarcoma. The patient was diagnosed with carcinosarcoma. This case included well-differentiated carcinomatous components, and it was necessary to differentiate it from teratocarcinosarcomas. There was no neural component, and without SMARCA4 loss, which is observed in teratocarcinosarcoma, and ruled out teratocarcinosarcoma. Carcinosarcomas are characterized by a biphasic histopathological pattern, making it difficult to accurately diagnose them on biopsy, which only captures a portion of the tumor. The possibility of carcinosarcoma should be considered even when the tumors derived from teratomas are suspected on preoperative biopsy.

Electronic nose (eNose) analysis of exhaled breath shows potential for accurate and timely lung cancer diagnosis, yet prospective external validation studies are lacking. Our study primarily aimed to prospectively and externally validate a published eNose model for lung cancer detection in COPD patients and assess its diagnostic performance alongside a new eNose model, specifically tailored to the target population, in a more general outpatient population.

This multi-center prospective external validation study included adults with clinical and/or radiological suspicion of lung cancer who were recruited from thoracic oncology outpatient clinics of two sites in The Netherlands. Breath profiles were collected using a cloud-connected eNose (SpiroNose®). The diagnostic performance of the original and new eNose model was assessed in various population subsets based on ROC-AUC, specificity, positive predictive value (PPV), and negative predictive value (NPV), targeting 95% sensitivity. For the new eNose model, a training and validation cohort were used.

Between March 2019 and November 2023, 364 participants were included. The original eNose model detected lung cancer with a ROC-AUC of 0.92 (95% CI: 0.85-0.99) in COPD patients (n=98/116; 84%) and 0.80 (95% CI: 0.75-0.85) in all participants (n=216/364; 59%). At 95% sensitivity, the specificity, PPV, and NPV, were 72% and 51%, 95% and 74%, and 72% and 88%, respectively. In the validation cohort, the new eNose model identified lung cancer across all participants (n=72/121; 60%) with a ROC-AUC of 0.83 (95% CI: 0.75-0.91), 94% sensitivity, 63% specificity, PPV of 79%, and NPV of 89%. Notably, accurate detection was consistent across tumour characteristics, disease stage, diagnostic centers, and clinical characteristics.

This multi-center prospective external validation study confirms that eNose analysis of exhaled breath enables accurate lung cancer detection at thoracic oncology outpatient clinics, irrespective of tumour characteristics, disease stage, diagnostic center, and clinical characteristics.

Large cell neuroendocrine carcinoma (LCNEC) is a rare, aggressive cancer primarily found in the lungs but can also occur in other organs. It is characterized by rapid progression and high metastatic potential. We present a case of advanced-stage LCNEC lung in a patient with a poor performance status (PS), requiring oxygen support. Imaging revealed a large right upper lobe mass, lymphadenopathy, with bronchial encasement and invasion into the superior vena cava, leading to SVC syndrome and pleural effusion. Biopsy and immunohistochemistry confirmed LCNEC. Due to the patient's poor PS, treatment began with low-dose single-agent chemotherapy (carboplatin), followed by etoposide and cisplatin after improvement. Local radiation was also administered, and the treatment plan was adjusted to include atezolizumab. After 10 cycles, the patient achieved complete remission, sustained for 6 years. This case highlights the complexities of managing advanced LCNEC in a geriatric patient and the effectiveness of a multidisciplinary approach and immunotherapy.

The International Association for the Study of Lung Cancer (IASLC) grading system for invasive non-mucinous adenocarcinoma (ADC) incorporates high-grade patterns (HGP) and predominant subtypes (PS). Following the system, this study aimed to explore the feasibility of predicting HGP and PS for IASLC grading.

A total of 529 ADCs from patients who underwent radical surgical resection were randomly divided into training and validation datasets in a 7:3 ratio. A two-step model consisting of two submodels was developed for IASLC grading. One submodel assessed whether the HGP exceeded 20% for ADCs, whereas the other distinguished between lepidic and acinar/papillary PS. The predictions from both submodels determined the final IASLC grades. Two variants of this model using either radiomic or clinical-semantic features were created. Additionally, one-step models that directly assessed IASLC grades using clinical-semantic or radiomic features were developed for comparison. The area under the curve (AUC) was used for model evaluation.

The two-step radiomic model achieved the highest AUC values of 0.95, 0.85, 0.96 for grades 1, 2, 3 among models. The two-step models outperformed the one-step models in predicting grades 2 and 3, with AUCs of 0.89 and 0.96 vs. 0.53 and 0.81 for radiomics, and 0.68 and 0.77 vs. 0.44 and 0.63 for clinical-semantics (p < 0.001). Radiomics models showed better AUCs than clinical-semantic models for grade 3 regardless of model steps.

Predicting HGP and PS using radiomics can achieve accurate IASLC grading in ADCs. Such a two-step radiomics model may provide precise preoperative diagnosis, thereby supporting treatment planning.

Cancer remains a major threat to human health, with chemotherapy serving as one of the main treatment strategies to alleviate patient suffering. However, prolonged chemotherapy often leads to the development of drug resistance, complicating treatment outcomes. Cisplatin, a commonly utilized chemotherapeutic agent, demonstrates efficacy against a range of cancers but frequently encounters resistance, posing a significant challenge in tumor management and prognosis. Drug resistance not only facilitates tumor progression but also reduces survival rates, highlighting the urgent need for innovative strategies to overcome this issue. In recent years, non-coding RNAs, particularly circular RNAs (circRNAs), have gained attention in cancer therapy due to their stability and specificity. Moreover, an increasing number of studies have reported that circRNAs are involved in cisplatin resistance across various types of cancer. This paper primarily reviews the mechanisms and roles of circRNA in mediating cisplatin resistance over the past 3 years. These findings highlight circRNAs as promising therapeutic targets for overcoming cancer drug resistance.

Choroidal metastasis is the most common intraocular malignancy in adults, commonly presenting in later stages of the disease and associated with poor prognosis. This is the first case to describe choroidal involvement as the sole initial metastasis of the rare biphasic pulmonary tumor.

A 42-year-old white male patient presented to the emergency department with 3 weeks of progressive temporal visual field loss in the left eye (oculus sinister) with slight discomfort to palpation. At the emergency department, he underwent computed tomography and computed tomography angiography of the brain to rule out a central nervous system etiology of his vision loss. The imaging demonstrated lentiform dependent hyperdense material with layering hypodensity within the medial aspect of the left globe, consistent with choroidal detachment. His prior medical history was significant for biphasic pulmonary blastoma cT2N2M0 stage IIIA involving the right lung, with extension into the superior vena cava, diagnosed 3 years prior to the current presentation. He was treated with chemoradiation and excision with complete response to therapy.

As the survival rates for cancer patients are increasing owing to better quality and more available treatments, choroidal metastasis may become more common. Early diagnosis and effective treatment of these lesions is crucial for better patient outcomes.

Precision medicine based on biomarkers, such as genetic abnormalities and PD-L1 expression, has been established for the treatment of nonsmall cell lung cancer. Recently, liquid biopsy has emerged as a valuable and minimally invasive alternative. This method analyzes blood and other bodily fluids to detect cancer-related genetic abnormalities and molecular residual disease (MRD). Liquid biopsy, which includes testing for circulating tumor cells, circulating tumor DNA (ctDNA), and microRNA (miRNA), offers several advantages over conventional methods. It is minimally invasive, can be performed repeatedly, and provides crucial information for early cancer diagnosis, genotyping, and treatment monitoring. Elevated ctDNA levels and miRNA markers show promise for early diagnosis. Liquid biopsy complements traditional tissue biopsy during genotyping, particularly when tumor samples are insufficient. Tests such as Cobas® EGFR Mutation Test v2 and Guardant360® CDx have been shown to be effective in detecting genetic mutations and guiding treatment decisions. Although the accuracy of liquid biopsy is still lower than that of tissue biopsy, its clinical utility continues to improve. For cancer prediction recurrence and treatment monitoring, ctDNA analysis can detect MRD earlier than conventional imaging, offering potential benefits for treatment adjustment and early relapse detection. The continuous development and validation of liquid biopsy methods are essential for improving personalized lung cancer treatment strategies.

Achyrocline satureioides have good therapeutic effects on nonsmall cell lung cancer (NSCLC). Nevertheless, it is still challenging to elucidate the active ingredients and mechanism of action due to their complex chemical composition. To address this, we innovatively combined network pharmacology with spatial metabolomics to comprehensively investigate the active components and the action mechanism in the present study. First, metabolomics of cells treated with the methanol extract of A. satureioides (ASM) utilizing high-resolution ultrahigh-performance liquid chromatography tandem mass spectrometry (HR-UHPLC-MS/MS) revealed 32 changed metabolites and 7 enriched metabolic pathways, confirming the anti-NSCLC effect of ASM and its impact on endogenous metabolites at the cellular level. Then, 69 chemical components in the ASM were identified using HR-UHPLC-MS/MS, followed by the screening of 6 core components and 10 core targets of anti-NSCLC with the help of network pharmacology and molecular docking. Lastly, quercetin, the most abundant compound among the six core active ingredients, was chosen for evaluating its anti-NSCLC effect and the potential mechanism using matrix-assisted laser desorption/ionization mass spectrometry imaging (MALDI-MSI). 51 altered endogenous metabolites were screened, and pathway enrichment analysis results were consistent with cell metabolomics, corroborating our network pharmacology predictions. In addition, we also observed the accumulation of three metabolites of quercetin in the tumor tissues. Network pharmacology combined with MSI elucidated the metabolic mechanisms by which A. satureioides treats NSCLC, offering new insights into herbal cancer therapies.

This study aimed to develop an effective radiomics-clinical model to preoperatively discriminate the spread through air spaces (STAS) in lung adenocarcinoma (ADC).

Data from 192 ADC patients were enrolled, with 2/3 (n = 128) allocated as the training cohort and the remaining 1/3 (n = 64) designated as the validation cohort. A total of 2212 radiomics features were extracted from PET/computed tomography (PET/CT) images. The least absolute shrinkage and selection operator regression method was applied to select features. Logistic regression was used to construct radiomics and clinical models. Finally, a radiomics-clinical model that combined clinical with radiomics features was developed. The models were evaluated by receiver operating characteristic (ROC) curve and decision curve analysis.

The area under the ROC curve (AUC) of the radiomics-clinical model was 0.924 (95% confidence interval, 0.878-0.969) in the training cohort and 0.919 (0.833-1.000) in the validation cohort. The AUC of the radiomics model was 0.885 (0.825-0.945) in the training cohort and 0.877 (0.766-0.988) in the validation cohort. The AUC of the clinical model was 0.883 (0.814-0.951) in the training cohort and 0.896 (0.7706-1.000) in the validation cohort. The decision curve analysis indicated its clinical usefulness.

The PET/CT-based radiomics-clinical model achieved satisfactory performance in discriminating the STAS in ADC preoperatively.

Anaplastic lymphoma kinase tyrosine kinase inhibitors (ALK-TKIs) have become first-line therapies for advanced non-small cell lung cancer (NSCLC) with ALK rearrangements. This study investigates ALK-TKI-associated adverse events (AEs), focusing on identifying hepatotoxicity signals and previously undocumented safety concerns. Using disproportionality analysis of 56,864 reports from the FDA Adverse Event Reporting System (FAERS) database, we systematically classified AEs via the Medical Dictionary for Regulatory Activities (MedDRA). At the System Organ Class (SOC) level, crizotinib exhibited a significantly stronger signal for eye disorders, ceritinib was uniquely linked to gastrointestinal disorders, and loratinib was predominantly associated with metabolism and nutrition disorders. Several AEs previously undocumented in drug labels were identified, including pericardial effusion, elevated C-reactive protein, hemolytic anemia, hemoptysis, and decreased hemoglobin. Furthermore, crizotinib, ceritinib, and alectinib were significantly associated with hepatotoxicity, marked by elevated alanine aminotransferase, aspartate aminotransferase, and hepatic enzyme levels. These findings highlight the need for vigilant monitoring of unlabeled AEs and potential label updates, particularly for hepatotoxicity risks associated with crizotinib, ceritinib, and alectinib.

Lung cancer (LC) represents the leading cause of cancer-related death and the third in incidence in Argentina. Survival rates are low.

To analyze the spatial distribution of LC incidence in Córdoba-Argentina (2004-2014), explore trends in histological types, and estimate the probability of survival.

A longitudinal ecological study was conducted using data from the Provincial Cancer Registry. Age-specific and standardized incidence rates for LC (ICD-10: C33-34) were calculated, truncated (35-84 years), and stratified by sex, year (2004-2014), and histology (small cell carcinoma and non-small cell: adenocarcinoma, squamous cells, large cells, and other carcinomas). Temporal analysis employed Joinpoint regression models, estimating annual percentage changes (APC). Median times estimated survival curves and semiparametric Cox regression models were employed for survival. Statistical significance: log-rank tests and proportional hazards tests. Software: Joinpoint-Regression-Program and Stata17.

From 2004-2014, 8246 LC cases were diagnosed in individuals aged 35-84. The highest incidence occurred in males aged 75-79 and females aged 80-84. The Age-standardized incidence rates for males and females were 57.9 and 23.6 cases per 100,000 person-years, respectively. In both sexes, the temporal incidence trend was decreasing (APC -3.21 %; p = 0.001), more pronounced in males (APC -3.99 %, p = 0.011), with negative APCs in all histological subtypes. The probability of survival decreased to 32 % (95 %CI: 31 %-34 %) within just 12 months (38 % in females, 30 % in males). The risk of death increased proportionally with age (males HR: 1.007, (95 %CI: 1.004-1.01, p = 0.000); females HR: 1.005, (95 %CI: 1.00-1.01, p = 0.031)) and across all histological types, with lower proportional risks in females and disparities based on histology: in males, the highest risk was in large cells (p = 0.008) and SMCC, while in females, it was SCLC (p = 0.055).

Despite estimating a favorable trend in LC incidence since 2004, the survival prognosis remains unfavorable one-year post-diagnosis, dependent on sex, age, and histological type.

Pathologic features involving LVI (lympho-vascular invasion), PNI (perineural invasion), STAS (spread through air spaces), and Grade 3 pattern (from the International Association for the Study of Lung Cancer grading system) are related to having an aggressive phenotype and linked to poor prognosis. However, few studies have conducted in-depth analyses of these features simultaneously with genomic profiling.

A total of 1559 sequencing of adenocarcinoma samples were included in the common driver mutations analysis, 1306 samples were brought into genomic mapping analysis. OncoSG's East Asian ancestry dataset was implemented for Tumor-Node-Metastasis-Biomarker (TNMB) classification and prognostic assessment.

EGFR was more significantly prevalent in LVI negativity (P = 0.021), STAS negativity (P = 0.002), and moderate grade (P < 0.001). ALK was significantly interrelated with LVI (P = 0.028), STAS (P < 0.001), and poor grade (P < 0.001); ROS1 and STAS positivity (P = 0.031), poor grade (P = 0.016) were significantly related. KRAS (P = 0.003) and BRAF-V600E (P = 0.002) were only significantly intertwined with poor grade. Apart from common driver mutations, TP53, CHEK2, KEAP1, PTEN, RB1, NF1 were significantly enriched in LVI samples (P < 0.05). TP53, PTEN, CTNNB1, HGF, NF1 were more prominent in STAS (P < 0.01). TP53, LRP1B, NF1 were significantly more prevalent in Grade 3 pattern (P < 0.001). The mixture of STK11, PTEN, and TOP2A generated by exclusive mutations may be a potential predictor of TNMB categorization towards survival. The HR of stage II compared I of TNMB was 2.28 (95 % CI 1.36-3.86, P < 0.001), while stage III compared II was 1.95 (95 % CI 1.04-3.21, P = 0.031).

This analysis demonstrated the correlation of pathologic features with common driver mutations, key mutations and canonical oncogenic signaling pathways. The data highlighted the similarities and differences among these features horizontally, and provide new insights in TNMB classification and prognostic assessment.

Nuclear protein of the testis (NUT) carcinoma (NC) is a rare but highly aggressive disease, characterized by drug resistance and poor prognosis. This report describes the case of a 32-year-old male patient diagnosed to have pulmonary NC; the tumor exhibited positive immunohistochemical staining of NUT and showed rearrangement of BRD4::NUT midline carcinoma family member 1 (NUTM1). After two treatment cycles of chemotherapy (etoposide plus carboplatin) combined with the PD-1 inhibitor sintilimab, the thoracic lesion of the patient disappeared, resulting in a partial response. When the patient's disease progressed even after the targeted therapy with a bromodomain and extra-terminal motif (BET) inhibitor, sintilimab was readministered in combination with platinum-based chemotherapy. However, the disease rapidly progressed after only one treatment cycle. Notably, the disease showed de novo drug resistance to the combination of chemotherapy with the histone deacetylase inhibitor. Although the patient's NC initially responded well to the combination of the PD-1 inhibitor and chemotherapy, the response was transient. These findings suggest that pulmonary NC is a highly malignant thoracic carcinoma, with no durable response and survival benefits from treatment with chemotherapeutics or immune checkpoint inhibitors.

In 2020, the International Association for the Study of Lung Cancer (IASLC) introduced a new grading system for invasive pulmonary adenocarcinoma (IPA). This meta-analysis aimed to validate the prognostic utility of this grading system and identify relevant clinicopathological features. The PubMed, Embase, Web of Science, and Cochrane Library databases were searched for relevant studies published between January 1, 2020 and March 5, 2024. Hazard ratios (HRs) with corresponding 95 % confidence intervals (CIs) were pooled to evaluate the effect of IASLC grading on prognosis. Odds ratios with corresponding 95 % CIs were pooled to assess relevant clinicopathological features. Twenty-two studies comprising 12,515 patients with IPA were included. Regarding overall survival, grade 3 adenocarcinomas had a worse prognosis compared with grades 1-2 (HR: 2.26, 95 % CI: 1.79-2.85, P<0.001), grade 1 (HR: 4.75, 95 % CI: 2.61-8.66, P<0.001), or grade 2 (HR: 1.71, 95 % CI: 1.28-2.29, P<0.001). Considering recurrence-free survival, grade 3 tumors had a higher recurrence risk than grades 1-2 (HR: 1.92, 95 % CI: 1.53-2.41, P<0.001), grade 1 (HR: 4.43, 95 % CI: 2.91-6.73, P<0.001), or grade 2 (HR: 1.67, 95 % CI: 1.33-2.10, P<0.001). In the subgroup analysis of stage I patients, grade 3 tumors exhibited a similarly poor prognosis. In addition, grade 3 adenocarcinomas were associated with aggressive clinicopathological features. This study demonstrated that the IASLC grading system is a robust predictor of prognostic stratification in patients with IPA, and warrants further promotion and worldwide implementation.

The morphology of ground-glass nodule (GGN) under high-resolution computed tomography (HRCT) has been suggested to indicate different histological subtypes of lung adenocarcinoma (LUAD); however, existing studies only include the limited number of GGN characteristics, which lacks a systematic model for predicting invasive LUAD. This study aimed to construct a predictive model based on GGN features under HRCT for LUAD. A total of 1,189 surgical LUAD patients were enrolled, and their GGN-related features were assessed by 2 individual radiologists. The pathological diagnosis of the invasive LUAD was established by pathologic examination following surgery (including 1,073 invasive and 526 non-invasive LUAD). After adjustment by multivariate logistic regression, GGN diameter (OR = 1.382, 95% CI: 1.300-1.469), mean CT attenuation (OR = 1.007, 95% CI: 1.006-1.009), heterogeneous uniformity of density (OR = 2.151, 95% CI: 1.587-2.915), not defined nodule-lung interface (OR = 1.915, 95% CI: 1.384-2.651), GGN with spiculation (OR = 2.097, 95% CI: 1.519-2.896), type I (OR = 1.678, 95% CI: 1.216-2.371), and type II (OR = 3.577, 95% CI: 1.153-11.097) vessel changes were independent risk factors for invasive LUAD. In addition, a predictive model integrating these six independent GGN features was established (named as invasion of lung adenocarcinoma by GGN features (ILAG)), and receiver-operating characteristic curve illustrated that the ILAG model presented good predictive value for invasive LUAD (AUC: 0.905, 95% CI: 0.890-0.919). In conclusion, The ILAG predictive model, which integrates imaging features of GGN via HRCT, including diameter, mean CT attenuation, heterogeneous uniformity of density, not defined nodule-lung interface, GGN with spiculation, type I, and type II vessel changes, shows great potential for early estimation of LUAD invasiveness.

The efficacy of neoantigen-reactive T cells (NRT) therapy in solid tumors, encompassing aspects such as infiltration, recognition, cytotoxicity, and enduring persistence, is notably influenced by the immunological microenvironment. This study endeavors to investigate whether the co-administration of pemetrexed and cisplatin augments the therapeutic efficacy of NRT therapy in lung cancer. Neoantigens were predicted using a comprehensive analysis of mutation data from Lewis lung carcinoma cells and mouse tail tissues. The immunogenicity of NRT cells was assessed through flow cytometry and IFN-γ ELISpot assays. A mouse model of NSCLC was used to investigate the anti-tumor effects of NRT combined with chemotherapy. The combination of NRT cells and chemotherapy significantly inhibited tumor growth in a mouse model, increased CD3+/CD137+ T cells to promote IFN-γ secretion from NRT cells, and up-regulated the levels of inflammatory cytokine proteins including IFN-γ, TNF, IL-6 and IL-10. Immunofluorescence analysis confirmed increased T-cell infiltration in tumor tissues without adverse effects on vital organs. In addition, transcriptome analyses indicated that the tumor microenvironment was altered to favor M1-like macrophages with an increased M1/M2 ratio, creating a pro-inflammatory environment. The integration of NRT with frontline chemotherapy for lung cancer could yield profoundly ideal therapeutic outcomes.

This study aimed to investigate the relationship between imaging features of pure ground-glass opacities (pGGOs) and the pathological subtypes of minimally invasive adenocarcinoma (MIA) and precursor lesions. A retrospective analysis was conducted on data from 1521 patients diagnosed with GGOs as lung adenocarcinoma or precursor lesions between January 2015 and March 2021. The pGGOs were categorized into atypical adenomatous hyperplasia (AAH) / adenocarcinoma in situ (AIS) and MIA groups. Clinical information and CT imaging features were collected. Statistical analysis, logistic regression, and receiver operating characteristic (ROC) curve analysis were performed. A total of 127 patients with 139 pGGOs were included. Maximum radiodensity, minimum radiodensity, mean radiodensity, variance, and skewness showed significant differences between the two groups. Maximum radiodensity and maximum cross-sectional area were identified as risk factors for pathology. The logistic regression model yielded an area under the curve (AUC) of 0.747 (95% CI, 0.666-0.816) for predicting pathological subtypes. The intensity features of pGGOs were found to be significantly different between AAH/AIS and MIA groups. Maximum radiodensity and skewness were independent risk factors for pathology. However, these features did not exhibit satisfactory diagnostic efficiency.

Pulmonary pleomorphic carcinoma is a relatively rare and aggressive subtype of non-small cell lung cancer (NSCLC), with a poor prognosis and early recurrence, and is resistant to conventional therapies. This study investigated the efficacy of immune checkpoint inhibitors (ICIs) in improving the survival outcomes of patients with pulmonary pleomorphic carcinoma with postoperative recurrence.

We conducted a retrospective analysis of 71 patients with pulmonary pleomorphic carcinoma who underwent pulmonary resection at Tokyo Medical University Hospital between 2008 and 2022. Clinicopathological data, programmed cell death ligand 1 (PD-L1) expression, and postoperative recurrence treatment outcomes were reviewed.

Among the 71 patients with pulmonary pleomorphic carcinoma, the 5-year overall survival (OS) rate was 48.6 %, and high PD-L1 expression (28-8 clone) was observed in 87 %. The median recurrence-free survival (RFS) was 19.4 months, and postoperative recurrence occurred in 38 patients (54 %). Treatment after recurrence was administered to 24 patients (63 %), and immunotherapy was administered to 10 patients (26 %). In patients treated with ICI, the overall response rate (ORR) was significantly higher (50 %) compared to those treated without ICI (7 %). The median survival time after relapse was notably longer in the ICI-treated group (83.9 months), compared to the non-ICI group (10.1 months).

ICIs significantly improve survival outcomes in patients with recurrent pulmonary pleomorphic carcinoma, particularly in those with high PD-L1 expression. Early postoperative recurrence and rapid progression have been observed, making therapeutic intervention challenging. Close follow-up is crucial, and ICIs become a pivotal treatment option for managing this highly aggressive cancer.

Both lung cancer and cardiovascular disease (CVD) are prevalent diseases that contribute to global mortality rates. Although individuals with CVD may face an elevated risk of cancer based on the presence of shared risk factors (such as tobacco smoking and excessive body weight), the roles of somatic mutations and heavy metal distributions remain unknown. The present study aimed to explore the differences in somatic mutations and heavy metal distributions between hypertensive patients and non-hypertensive patients in a cohort of patients with non-small cell lung cancer (NSCLC). Tumor tissue samples from 64 patients were analyzed using a next-generation sequencing panel consisting of 82 tumor-related genes through hybrid capture. Serum samples were also analyzed to determine the levels of 18 heavy metals using inductively-coupled plasma mass spectrometry. Among the 16 hypertensive patients, all patients (16/16; 100.00%) harbored 47 somatic mutations in 14 mutant genes, whereas 45 patients without hypertension (45/48; 93.75%) harbored 113 somatic mutations across 26 mutant genes (no mutations were detected in the remaining 3 patients). Among the 32 identified mutant genes in these two groups, FBXW7, CBR3, CDKN2A, HRAS, SMO and UGT1A1 were exclusively observed in patients with hypertension, while 18 mutant genes were only observed in patients without hypertension. No significant mutually exclusive interactions were found in hypertensive patients, but mutually exclusive interactions were observed between EGFR and STK11 (P=0.0240) and between STK11 and KRAS (P=0.0169) in non-hypertensive patients. 'Non-small cell lung cancer' was the top Kyoto Encyclopedia of Genes and Genomes pathway in hypertensive patients, whereas 'central carbon metabolism in cancer' was the top pathway in patients without hypertension. Moreover, the proportions of altered key signaling pathways and biological function categories shared between these two groups were 54.37% (56/103) and 21.62% (8/37), respectively. Furthermore, the levels of chromium (Cr) in the serum of hypertensive patients were notably elevated compared with those in patients without hypertension. In addition, significant negative correlations were observed between Cr and CEA, between CYFRA21-1 and Zn, and between NSE and As in hypertensive patients but not in non-hypertensive patients, indicating differing interactive profiles among the traditional serum biomarkers and heavy metals between these two patient groups. In summary, there were differences in genomic alterations, somatic interactions and the serum levels of Cr between patients with NSCLC with hypertension and patients with NSCLC without hypertension. Furthermore, patients with hypertension exhibited significant negative correlations between Cr and CEA, between CYFRA21-1 and Zn, and between NSE and As, suggesting that heavy metals may contribute to the occurrence of NSCLC with different hypertensive status.

This study aimed to develop and validate 2-Dimensional (2D) and 3-Dimensional (3D) radiomics signatures based on contrast-enhanced computed tomography (CECT) images for preoperative prediction of the thymic epithelial tumors (TETs) risk and compare the predictive performance with conventional CT features.

149 TET patients were retrospectively enrolled from January 2016 to December 2018, and divided into high-risk group (B2/B3/TCs, n = 103) and low-risk group (A/AB/B1, n = 46). All patients were randomly assigned into the training (n = 104) and testing (n = 45) set. 14 conventional CT features were collected, and 396 radiomic features were extracted from 2D and 3D CECT images, respectively. Three models including conventional, 2D radiomics and 3D radiomics model were established using multivariate logistic regression analysis. The discriminative performances of the models were demonstrated by receiver operating characteristic (ROC) curves.

In the conventional model, area under the curves (AUCs) in the training and validation sets were 0.863 and 0.853, sensitivity was 78% and 55%, and specificity was 88% and 100%, respectively. The 2D model yielded AUCs of 0.854 and 0.834, sensitivity of 86% and 77%, and specificity of 72% and 86% in the training and validation sets. The 3D model revealed AUC of 0.902 and 0.906, sensitivity of 75% and 68%, and specificity of 94% and 100% in the training and validation sets.

Radiomics signatures based on 3D images could distinguish high-risk from low-risk TETs and provide complementary diagnostic information.

In patients with metastatic non-small cell lung cancer (NSCLC) with high programmed death-ligand 1 (PD-L1) expression, there is still a lack of biomarkers to identify patients with maximum benefit from first-line treatment with checkpoint inhibitor therapy (CIT) alone. This work examines the impact of different ABO blood groups (BG) on the response to CIT monotherapy.

Retrospective analysis of patients with stage IV NSCLC and high PD-L1 expression (tumor proportional score/TPS ≥ 50%), receiving first-line therapy with pembrolizumab alone or in combination with chemotherapy at the West German Cancer Center from 2017 to 2022. Study endpoints were overall survival (OS) and progression-free survival (PFS).

Eighty-two patients were included in the analysis. Twenty-two patients (27%) received first-line therapy with pembrolizumab alone (monoimmunotherapy cohort/MIC), of which seven patients (32%) had BGO. Sixty patients (73%) were treated with pembrolizumab combined with platinum-based chemotherapy (chemoimmunotherapy cohort/CIC), of which 38 (63%) had BGO. In MIC, younger age and BGO were independent predictors of favorable OS (BGO vs. other ABO-BG: HR 0.22, 95% CI: 0.1-0.9; p = 0.037; median OS 62 versus 19 months) and PFS (BGO vs. other ABO-BG: HR 0.21, 95% CI: 0.1-0.8; p = 0.024; median PFS 39 vs. 4 months). There was no significant impact of ABO-BG in patients treated with CIC. In support, a historical control group treated with chemotherapy alone also showed no prognostic impact of the ABO-BG.

BGO associates with favorable survival in patients with NSCLC receiving pembrolizumab monotherapy, but not in patients with chemo-immunotherapy or chemotherapy. Further validation of this promising strategy for personalized decision-making is warranted.

To comprehensively analyze the association between preoperative maximum standardized uptake value (SUVmax) on 18F-fluorodeoxyglucose positron emission tomography-computed tomography and postoperative recurrence in resected non-small cell lung cancer (NSCLC) using machine learning (ML) and statistical approaches.

This retrospective study included 643 patients who had undergone NSCLC resection. ML models (random forest, gradient boosting, extreme gradient boosting, and AdaBoost) and a random survival forest model were developed to predict postoperative recurrence. Model performance was evaluated using the receiver operating characteristic (ROC) AUC and concordance index (C-index). Shapley additive explanations (SHAP) and partial dependence plots (PDPs) were used to interpret model predictions and quantify feature importance. The relationship between SUVmax and recurrence risk was evaluated by using a multivariable Cox proportional hazards model.

The random forest model showed the highest predictive performance (ROC AUC, 0.90; 95% CI, 0.86 to 0.97). The SHAP analysis identified SUVmax as an important predictor. The PDP analysis showed a nonlinear relationship between SUVmax and recurrence risk, with a sharp increase at SUVmax 2-5. The random survival forest model achieved a C-index of 0.82. A permutation importance analysis identified SUVmax as the most important feature. In the Cox model, increased SUVmax was associated with a higher risk of recurrence (adjusted hazard ratio, 1.03 [95% CI, 1.00 to 1.06]).

Preoperative SUVmax showed significant predictive value for postoperative recurrence after NSCLC resection. The nonlinear relationship between SUVmax and recurrence risk, with a sharp increase at relatively low SUVmax values, suggests its potential as a sensitive biomarker for early identification of high-risk patients. This may contribute to more precise assessments of the risk of recurrence and personalized treatment strategies for NSCLC.

Individualized prediction of cancer drug sensitivity is of vital importance in precision medicine. While numerous predictive methodologies for cancer drug response have been proposed, the precise prediction of an individual patient's response to drug and a thorough understanding of differences in drug responses among individuals continue to pose significant challenges. This study introduced a deep learning model PASO, which integrated transformer encoder, multi-scale convolutional networks and attention mechanisms to predict the sensitivity of cell lines to anticancer drugs, based on the omics data of cell lines and the SMILES representations of drug molecules. First, we use statistical methods to compute the differences in gene expression, gene mutation, and gene copy number variations between within and outside biological pathways, and utilized these pathway difference values as cell line features, combined with the drugs' SMILES chemical structure information as inputs to the model. Then the model integrates various deep learning technologies multi-scale convolutional networks and transformer encoder to extract the properties of drug molecules from different perspectives, while an attention network is devoted to learning complex interactions between the omics features of cell lines and the aforementioned properties of drug molecules. Finally, a multilayer perceptron (MLP) outputs the final predictions of drug response. Our model exhibits higher accuracy in predicting the sensitivity to anticancer drugs comparing with other methods proposed recently. It is found that PARP inhibitors, and Topoisomerase I inhibitors were particularly sensitive to SCLC when analyzing the drug response predictions for lung cancer cell lines. Additionally, the model is capable of highlighting biological pathways related to cancer and accurately capturing critical parts of the drug's chemical structure. We also validated the model's clinical utility using clinical data from The Cancer Genome Atlas. In summary, the PASO model suggests potential as a robust support in individualized cancer treatment. Our methods are implemented in Python and are freely available from GitHub (https://github.com/queryang/PASO).