Timely identification of comorbidities is critical in sleep medicine, where large language models (LLMs) like ChatGPT are currently emerging as transformative tools. Here, we investigate whether the novel LLM ChatGPT o1 preview can identify individual health risks or potentially existing comorbidities from the medical data of fictitious sleep medicine patients.

We conducted a simulation-based study using 30 fictitious patients, designed to represent realistic variations in demographic and clinical parameters commonly seen in sleep medicine. Each profile included personal data (eg, body mass index, smoking status, drinking habits), blood pressure, and routine blood test results, along with a predefined sleep medicine diagnosis. Each patient profile was evaluated independently by the LLM and a sleep medicine specialist (SMS) for identification of potential comorbidities or individual health risks. Their recommendations were compared for concordance across lifestyle changes and further medical measures.

The LLM achieved high concordance with the SMS for lifestyle modification recommendations, including 100% concordance on smoking cessation (κ = 1; p < 0.001), 97% on alcohol reduction (κ = 0.92; p < 0.001) and endocrinological examination (κ = 0.92; p < 0.001) or 93% on weight loss (κ = 0.86; p < 0.001). However, it exhibited a tendency to over-recommend further medical measures (particularly 57% concordance for cardiological examination (κ = 0.08; p = 0.28) and 33% for gastrointestinal examination (κ = 0.1; p = 0.22)) compared to the SMS.

Despite the obvious limitation of using fictitious data, the findings suggest that LLMs like ChatGPT have the potential to complement clinical workflows in sleep medicine by identifying individual health risks and comorbidities. As LLMs continue to evolve, their integration into healthcare could redefine the approach to patient evaluation and risk stratification. Future research should contextualize the findings within broader clinical applications ideally testing locally run LLMs meeting data protection requirements.

The gold standard in obstructive sleep apnea (OSA) diagnostics is nocturnal full-night polysomnography (PSG). Due to high costs and high time effort portable respiratory polygraphy (PG or home sleep apnea testing-HSAT) has been developed. In contrast to PG the PSG gains relevant further information concerning sleep stages, arousals and leg movements. However, the role of PG in the diagnostic of OSA remains largely undefined. The aim of this study was to investigate the difference of PG- and PSG- related metrics in OSA, to understand if there is a difference in PG and PSG-based treatment decision and show up the time between performed PG and PSG.

99 consecutive patients with existing outpatient performed PG and followed PSG in our tertiary care otorhinolaryngology department between February 2020 and December 2023 were retrospectively assessed. All patients were treatment-naive at the time of consultation. The time between performed outpatient PG and PSG was calculated. Furthermore, clinical baseline parameter and PG as well as PSG data were evaluated. All data were then blinded presented with relevant comorbid diseases to two experts in sleep medicine in our tertiary care centre to decide whether PAP therapy was indicated or not.

Mean AHI was significantly higher in PSG (32.32 ± 22.78/h) compared to PG (22.60 ± 15.12/h) (p<0.001). Mean duration between performed PG and PSG was 194.99 ± 131.96 days (range between 37 and 842 days). Only in two patients PAP-therapy was indicated with PG results but not with PSG results. Only in one case PAP-therapy was not indicated with PG results but with PSG results.

These data suggest initiating OSA therapy based on PG results for patients with at least moderate OSA on PG, followed by a confirming PSG and a control PSG under treatment to avoid unnecessary prolongation of treatment start.

Obstructive sleep apnea (OSA), a common sleep-disordered breathing condition, is characterized by intermittent hypoxia (IH) and sleep fragmentation and has been implicated in the pathogenesis and severity of nonalcoholic fatty liver disease (NAFLD). Abnormal molecular changes mediated by IH, such as high expression of hypoxia-inducible factors, are reportedly involved in abnormal pathophysiological states, including insulin resistance, abnormal lipid metabolism, cell death, and inflammation, which mediate the development of NAFLD. However, the relationship between IH and NAFLD remains to be fully elucidated. In this review, we discuss the clinical correlation between OSA and NAFLD, focusing on the molecular mechanisms of IH in NAFLD progression. We meticulously summarize clinical studies evaluating the therapeutic efficacy of continuous positive airway pressure treatment for NAFLD in OSA. Additionally, we compile potential molecular biomarkers for the co-occurrence of OSA and NAFLD. Finally, we discuss the current research progress and challenges in the field of OSA and NAFLD and propose future directions and prospects.

Obstructive sleep apnea (OSA) is a very prevalent disease and its diagnosis is based on polysomnography (PSG). We investigated whether snoring-sound-, very low frequency electrocardiogram (ECG-VLF)- and thoraco-abdominal effort- PSG signal entropy values could be used as surrogate markers for detection of OSA and OSA severity classification.

The raw data of the snoring-, ECG- and abdominal and thoracic excursion signal recordings of two consecutive full-night PSGs of 86 consecutive patients (22 female, 53.74 ± 12.4 years) were analyzed retrospectively. Four epochs (30 s each, manually scored according to the American Academy of Sleep Medicine standard) of each sleep stage (N1, N2, N3, REM, awake) were used as the ground truth. Sampling entropy (SampEn) of all the above signals was calculated and group comparisons between the OSA severity groups were performed. In total, (86x4x5 = )1720 epochs/group/night were included in the training set as an input for a support vector machine (SVM) algorithm to classify the OSA severity classes. Analyses were performed for first- and second-night PSG recordings separately.

Twenty-seven patients had mild (RDI = ≥ 5/h but <15/h), 21 patients moderate (RDI ≥15/h but <30/h) and 23 patients severe OSA (RDI ≥30/h). Fifteen patients had an RDI <5/h and were therefore considered non-OSA. Using SE on the above three PSG signal data and using a SVM pipeline, it was possible to distinguish between the four OSA severity classes. The best metric was snoring signal-SE. The area-under-the-curve (AUC) calculations showed reproducible significant results for both nights of PSG. The second night data were even more significant, with non-OSA (R) vs. light OSA (L) 0.61, R vs. moderate (M) 0.68, R vs. heavy OSA (H) 0.84, L vs. M 0.63, M vs. H 0.65 and L vs. H 0.82. The results were not confounded by age or gender.

SampEn of either snoring-, very low ECG-frequencies- or thoraco-abdominal effort signals alone may be used as a surrogate marker to diagnose OSA and even predict OSA severity. More specifically, in this exploratory study snoring signal SampEn showed the greatest predictive accuracy for OSA among the three signals. Second night data showed even more accurate results for all three parameters than first-night recordings. Therefore, technologies using only parts of the PSG signal, e.g. sound-recording devices, may be used for OSA screening and OSA severity group classification.

Hypertensive patients with obstructive sleep apnea (OSA) are at a high risk of cardiovascular disease (CVD), but assessments of CVD risk in this population are frequently constrained by the presence of comorbid medical conditions. The noninvasive and convenient hepatic steatosis index (HSI) can not only predict the degree of fatty liver degeneration but also correlates well with the severity of numerous diseases. However, the relationship between the HSI and CVD in hypertensive patients with OSA remains unclear.

This retrospective cohort study included patients aged ≥ 18 years with hypertension and a primary diagnosis of OSA and grouped them according to their baseline HSI. The primary outcome was new or recurrent major adverse cardiovascular and cerebrovascular events (MACCE), while the secondary outcomes were cardiac and cerebrovascular events. The relationship between the baseline HSI and the risk of endpoint events was evaluated using Kaplan-Meier curves, risk-factor graphs, and Cox regression models, while generalized additive models were used to identify linear relationships. The C-statistic, integrated discrimination improvement (IDI), and net reclassification index (NRI) were used to evaluate the predictive value of HSI increments for endpoint events.

A total of 2467 participants were included in the analysis and separated into four groups (Q1-Q4) based on their HSI quartiles. Kaplan-Meier survival curves indicated that patients in the Q4 group had the lowest survival time. The Q4 group also showed a significantly higher risk of MACCE (HR [hazard ratio], 2.95; 95% CI [confidence interva]: 1.99-4.39; p < 0.001), cardiac events (HR, 2.80; 95% CI: 1.68-4.66; p < 0.001), and cerebrovascular events (HR, 3.21; 95% CI: 1.71-6.03; p < 0.001). The dose-response curve revealed a linear association between the HSI and the occurrence of endpoint events. For every unit increase in the HSI, the risks of MACCE, cardiac events, and cerebrovascular events increased by 43%, 38%, and 51%, respectively. The C-statistic, IDI, and NRI all indicated that the model including the HSI showed better discriminatory and classification efficacy for endpoint events in comparison with the conventional model (p < 0.05).

The HSI showed a linear relationship with the risk of MACCE in hypertensive OSA patients.

The objective of this study was to investigate to which extent anatomic features of the nasal and pharyngeal region contribute to the severity of obstructive sleep apnea (OSA) and positive airway pressure (PAP) therapy response. Therefore, 93 patients (mean age 57.5 ± 13.0 years, mean body mass index 32.2 ± 5.80 kg/m2, 75 males, 18 females) diagnosed with OSA who subsequently started PAP therapy were randomly selected from the databank of a sleep laboratory of a tertiary university medical center. Patients were subdivided based on nasal anatomy (septal deviation, turbinate hyperplasia, their combination, or none of the above), pharyngeal anatomy (webbing, tonsillar hyperplasia, their combination, or none of the above), and (as a separate group) tongue base anatomy (no tongue base hyperplasia or tongue base hyperplasia). Then, polysomnographic data (e.g., arousal index, ARI; respiratory disturbance index, RDI; apnea index, AI; hypopnea index, HI; and oxygen desaturation index, ODI) of diagnostic polysomnography (PSG) and PAP therapy control PSG were collected, grouped, and evaluated. Septal deviation, turbinate hyperplasia, or their combination did not significantly affect the assessed PSG parameters or the response to PAP therapy compared with patients without nasal obstruction (p > 0.05 for all parameters). Accordingly, most PSG parameters and the response to PAP therapy were not significantly affected by webbing, tonsil hyperplasia, or their combination compared with patients without pharyngeal obstruction (p > 0.05 for RDI, AI, HI, and ODI, respectively). However, in the pharyngeal anatomy group, ARI was significantly higher in patients with tonsil hyperplasia (p = 0.018). Further, patients with tongue base hyperplasia showed a significantly higher HI in the diagnostic PSG (p = 0.025) compared with patients with normal tongue base anatomy, but tongue base anatomy did not significantly affect the response to PAP therapy (p > 0.05 for all parameters). The influence of anatomic features of the nasal and pharyngeal region on PAP therapy response appears to be small, and generalizability of these results requires further studies.

Obstructive sleep apnea (OSA) has been associated with various acute and chronic inflammatory diseases, as has serum ferritin, an intracellular iron storage protein. Little is known about the relationship between severity of OSA and serum ferritin levels in otherwise healthy subjects. In this study, all polysomnographic recordings, serum levels of ferritin, C-reactive protein (CRP), and hemoglobin, as well as patient files from 90 consecutive, otherwise healthy individuals with suspected OSA who presented to a tertiary sleep medical center were retrospectively analyzed. For comparison, three groups were formed based on apnea-hypopnea index (AHI; none or mild OSA: <15/h vs. moderate OSA: 15-30/h vs. severe OSA: >30/h). Serum ferritin levels were significantly positively correlated with AHI (r = 0.3240, p = 0.0020). A clear trend of higher serum ferritin levels was found when patients with severe OSA were compared to those without or with mild OSA. Serum CRP and serum hemoglobin levels did not differ significantly among OSA severity groups. Age and body-mass index (BMI) tended to be higher with increasing OSA severity. The BMI was significant higher in patients with severe OSA compared to those without or with mild (p < 0.001). Therefore, serum ferritin levels may provide a biochemical surrogate marker for OSA severity.

Hypoglossal nerve stimulation (HGNS) is a treatment for obstructive sleep apnea (OSA) patients with intolerance of positive airway pressure therapy. Comorbid insomnia is quite prevalent in OSA patients. We investigated the impact of insomnia and excessive daytime sleepiness (EDS) on polysomnography metrics after HGNS treatment. Data of 27 consecutive patients (9 female; mean age 55.52 ± 8.6 years) were retrospectively evaluated. Insomnia was assessed using the ISI (insomnia severity index) and EDS using the Epworth sleepiness scale (ESS). The median ISI was reduced significantly 3 months after HGNS activation (preoperative: 19; postoperative: 14; p < 0.01). Significant correlations emerged between preoperative ISI and postoperative AHI (apnea/hypopnea index; Spearman’s rho = 0.4, p < 0.05), ∆ AHI (r = −0.51, p < 0.01) and ∆ ODI (oxygen desaturation index; r = −0.48, p < 0.05). ISI correlated strongly with EES both preoperatively (r = 0.46; p < 0.02) and postoperatively (r = 0.79; p < 0.001). Therefore, HGNS therapy is associated with a significant reduction of insomnia-related symptoms, in addition to the improvement in respiratory metrics in OSA. Nonetheless, the preoperative severity of patient-reported insomnia symptoms was inversely correlated with the respiratory PSG-outcomes after HGNS. Insomnia should be considered in studies of EDS in OSA patients, especially those treated with HGNS.

Snoring may play an important role in a variety of diseases, especially metabolic diseases. However, there are no reports on the relationship between snoring and the risk of metabolic-associated fatty liver disease (MAFLD). This study aimed to investigate the association between snoring and MAFLD.

A cross-sectional analysis was performed based on the National Health and Nutrition Examination Survey (NHANES) 2017-2018. Self-reported snoring frequency was grouped into four categories (never, rarely, occasionally, and frequently). MAFLD was diagnosed based on the evidence of hepatic steatosis and any of the following three conditions: overweight/obesity, diabetes mellitus or metabolic dysfunction. Logistic regression with sampling weights was used to examine the association between snoring and MAFLD.

A total of 5016 patients were included, and 50.14% of individuals had MAFLD. Compared with nonsnorers, those who snored frequently were associated with increased odds for MAFLD (odds ratio (OR): 1.376, 95% confidence interval (CI): 1.122-1.688, p trend <0.001). The subgroup analyses suggested that no significant interactions were found between snoring and other potential effect modifiers, including age, sex, body mass index (BMI), smoking status, chronic obstructive pulmonary disease (COPD) and hypertension.

Snoring was independently and positively associated with a higher prevalence of MAFLD, suggesting that attention to snoring may contribute to the early detection of MAFLD.

Hypoglossal nerve stimulation (HGNS) is a therapeutic option for patients with obstructive sleep apnea (OSA) and intolerance of positive airway pressure (PAP) therapy. Most reported data are based on multicentre pivotal trials with selected baseline core clinical features. Our aim was to investigate polysomnography (PSG)-based outcomes of HGNS-therapy in a patient cohort with higher average AHI and BMI than previously reported. Data of 29 consecutive patients (nine female; mean age: 55.52 ± 8.6 years, mean BMI 30.13 ± 3.93 kg/m²) were retrospectively evaluated. Numerical values of PSG- based metrics were compared before and after intervention using Wilcoxon's rank-sum test. AHI (38.57/h ± 12.71, 24.43/h ± 13.3, p < 0.001), hypopnea index (24.05/h ± 9.4, 15.27/h ± 8.23, p < 0.001), apnea index (14.5/h ± 12.05, 9.17/h ± 10.86, p < 0.01), snoring index (262.68/h ± 170.35, 143.48/h ± 162.79, p < 0.001), cortical arousal index (20.8/h ± 10.34 vs. 14.9/h ± 8.36, p < 0.01) and cumulative duration of apnea and hypopnea during sleep (79.79 min ± 40.32 vs. 48.62 min ± 30.56, p < 0.001) were significantly lower after HGNS. HGNS provides an effective therapy option for selected patients not tolerating PAP-therapy with higher average AHI and BMI than usually reported. HGNS-therapy appears to suppress central nervous system arousal circuits while not eliciting peripheral autonomous sympathetic activation. Such metrics as the snoring index and the cumulative duration of respiratory events during sleep may be considered in future HGNS studies.

Nonalcoholic fatty liver disease (NAFLD) is strongly associated with sleep apnea syndrome (SAS). Many NAFLD patients have SAS, and obstructive sleep apnea hypopnea syndrome is also considered to be an independent risk factor for NAFLD, as it contributes to the progression of NAFLD via oxidative stress, lipid peroxidation, inflammation, and insulin resistance. This review aims to provide some recommendations for the management of NAFLD patients with SAS, including diet, exercise, weight loss, and continuous positive airway pressure. This review also highlights the importance of effective strategies in NAFLD prevention and treatment.

Human papillomavirus (HPV) is recognized as the most important risk factor in oral cavity cancer and pre-malignant lesions; however, the etiological association of concomitant infection with other oncogenic viruses as a co-factor has not been definitively proven. The present study aimed to determine the prevalence of co-infection with HPV, Epstein-Barr virus (EBV) and Merkel Cell PolyomaVirus (MCPyV) in oral cavity lesions in Iranian patients. One hundred and fourteen oral cavity samples, including 33 oral squamous cell carcinoma, 28 oral lichen planus, 16 oral epithelial dysplasia and 37 oral irritation fibromas were analyzed for the HPV, EBV and MCPyV infection by quantitative real-time PCR. According to histological features 32.5% and 28.9% of cases were oral irritation fibroma and oral squamous cell carcinoma, respectively. Infection with at least two viruses was detected in 21.1% of patients. In this group, co-infection with HPV/EBV was identified in 37.5% of cases, HPV/MCPyV in 29.2%, EBV/MCPyV in 12.5%, and HPV/EBV/MCPyV in 20.8%. There was no statistically significant difference between multiple infections and anatomical locations of cancer. The prevalence of triple viral infection (HPV/EBV/MCPyV) in well differentiated tumors was higher than EBV or MCPyV single infection. This study revealed that co-infection of HPV, EBV and MCPyV can be detected in both malignant and non-malignant oral cavity tissues, and co-infection with all three viruses in well differentiated tumors can be shown as a synergistic hypothesis of the pathogenic role of these viruses in oral malignant transformation.