Efficacy of a machine learning model integrating clinical-psychosocial factors in predicting posttraumatic bone nonunion and bone defects

doi:10.5498/wjp.119455

Advanced Search

BPG is committed to discovery and dissemination of knowledge

Home / Archive / Volume 16, Issue 9

This Article

(2)

(0)

(2)

Peer-Review Report of This Article

CrossCheck and Google Search of This Article

Academic Rules and Norms of This Article

Citation of this article

Corresponding Author of This Article

Research Domain of This Article

Article-Type of This Article

Open-Access Policy of This Article

Times Cited Counts in Google of This Article

Journal Information of This Article

Publication Name

World Journal of Psychiatry

ISSN

2220-3206

Publisher of This Article

Baishideng Publishing Group Inc, 7041 Koll Center Parkway, Suite 160, Pleasanton, CA 94566, USA

Retrospective Study

Copyright: ©Author(s) 2026. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution-NonCommercial (CC BY-NC 4.0) license. No commercial re-use. See permissions. Published by Baishideng Publishing Group Inc.

World J Psychiatry. Sep 19, 2026; 16(9): 119455
Published online Sep 19, 2026. doi: 10.5498/wjp.119455

Table 1 Baseline data comparison (nonunion vs healing), n (%)

Indicators	Nonunion group (n = 17)	Healing group (n = 128)	t/χ²	P value
Age (years)	58.24 ± 11.14	46.29 ± 14.76	3.213	0.002
Gender			0.024	0.878
Male	12 (70.59)	88 (68.75)
Female	5 (29.41)	40 (31.25)
Body mass index (kg/m²)	25.19 ± 4.10	23.70 ± 2.80	5.993	< 0.001
Comorbidity
Hypertension	8 (47.06)	55 (42.97)	0.102	0.749
Diabetes	7 (41.18)	21 (16.41)	5.909	0.015
Atherosclerosis	5 (29.41)	20 (15.63)	1.999	0.157
Open fracture	10 (58.8)	28 (21.9)	10.590	0.001
Bone defect length (mm)	51.82 ± 14.43	38.44 ± 12.01	7.362	< 0.001
Distraction start time (days)	12.59 ± 5.81	10.20 ± 3.49	2.420	0.017
Distraction period (days)	45.24 ± 10.65	42.78 ± 9.72	0.968	0.335
Bone mineralization time (days)	275.18 ± 102.43	191.45 ± 87.24	3.639	0.004
Depression (PHQ-9)	16.82 ± 4.25	11.28 ± 3.10	11.374	< 0.001
Anxiety (GAD-7)	15.24 ± 4.12	10.51 ± 2.40	6.908	< 0.001
Social support (MSPSS)	48.53 ± 9.98	58.83 ± 10.53	3.810	< 0.001
Current smoker	9 (52.9)	35 (27.3)	4.652	0.031
Low-income	11 (64.7)	48 (37.5)	4.603	0.032

PHQ-9: Patient Health Questionnaire-9; GAD-7: Generalized Anxiety Disorder-7; MSPSS: Multidimensional Scale of Perceived Social Support.

Full Size Table

Table 2 Baseline data comparison in the external validation cohort (nonunion vs healing), n (%)

Indicators	Nonunion group (n = 10)	Healing group (n = 43)	t/χ²	P value
Age (years)	55.80 ± 15.02	47.78 ± 13.57	1.654	0.104
Gender			0.024	0.876
Male	7 (70.00)	30 (69.77)
Female	3 (30.00)	13 (33.23)
Body mass index (kg/m²)	25.75 ± 3.21	24.79 ± 3.12	0.867	0.390
Comorbidity
Hypertension	5 (50.00)	18 (69.57)	0.219	0.640
Diabetes	4 (40.00)	8 (18.60)	2.120	0.145
Atherosclerosis	3 (30.00)	7 (16.28)	0.998	0.318
Open fracture	6 (60.00)	9 (20.93)	6.103	0.014
Bone defect length (mm)	46.90 ± 14.11	40.77 ± 12.76	1.342	0.185
Distraction start time (days)	10.20 ± 2.82	9.35 ± 3.31	0.751	0.456
Distraction period (days)	44.80 ± 9.68	43.35 ± 8.75	0.463	0.645
Bone mineralization time (days)	197.10 ± 110.76	211.05 ± 91.30	0.418	0.678
Depression (PHQ-9)	16.50 ± 4.12	14.60 ± 3.02	1.664	0.102
Anxiety (GAD-7)	15.00 ± 3.74	12.70 ± 2.41	2.438	0.018
Social support (MSPSS)	49.20 ± 9.20	62.86 ± 10.07	3.922	< 0.001
Current smoker	5 (50.00)	11 (25.58)	2.442	0.118
Low-income	6 (60.00)	17 (39.54)	1.383	0.239

PHQ-9: Patient Health Questionnaire-9; GAD-7: Generalized Anxiety Disorder-7; MSPSS: Multidimensional Scale of Perceived Social Support.

Full Size Table

Table 3 Baseline data comparison (development vs external validation), n (%)

	Development cohort (n = 145)	External validation cohort (n = 53)	t/χ²	P value
Nonunion	17 (11.72)	10 (18.87)	1.682	0.195
Age (years)	47.69 ± 14.86	49.28 ± 14.06	0.677	0.499
Gender			0.013	0.909
Male	100 (68.97)	37 (69.81)
Female	45 (31.03)	16 (30.19)
Body mass index (kg/m²)	23.87 ± 3.00	24.97 ± 3.13	2.248	0.026
Bone defect length (mm)	40.01 ± 13.00	41.92 ± 13.11	0.917	0.360
Distraction start time (days)	10.48 ± 3.88	9.51 ± 3.21	1.632	0.104
Distraction period (days)	43.07 ± 9.82	43.62 ± 8.86	0.360	0.719
Bone mineralization time (days)	201.26 ± 92.78	208.42 ± 94.27	0.479	0.633
Open fracture	38 (26.21)	15 (28.30)	0.087	0.768
Comorbidity
Hypertension	63 (43.45)	23 (43.40)	0.007	0.995
Diabetes	28 (19.31)	12 (22.64)	0.267	0.605
Atherosclerosis	25 (17.24)	10 (18.87)	0.071	0.791
Depression (PHQ-9)	11.93 ± 3.70	14.96 ± 3.30	5.249	0.000
Anxiety (GAD-7)	11.06 ± 3.95	13.13 ± 2.81	4.313	0.000
Social support (MSPSS)	57.62 ± 10.95	60.28 ± 11.21	1.505	0.134
Current smoker	44 (30.34)	16 (30.19)	0.080	0.983
Low-income earner	59 (40.69)	23 (43.40)	0.117	0.732

PHQ-9: Patient Health Questionnaire-9; GAD-7: Generalized Anxiety Disorder-7; MSPSS: Multidimensional Scale of Perceived Social Support.

Full Size Table

Table 4 Summary of internal validation model performance indicators for the development cohort

	Traditional clinical model	Integrated model
AUC (95%CI)	0.854 (0.788-0.919)	0.923 (0.856-0.990)
Sensitivity	0.588	0.882
Specificity	0.883	0.891
Accuracy	0.849	0.890
F1 score	0.476	0.640
DeLong’s test	-	P < 0.05

AUC: Area under the curve; CI: Confidence interval.

Full Size Table

Table 5 Summary of model performance indicators for the external validation cohort

	Traditional clinical model	Integrated model
AUC (95%CI)	0.823 (0.692-0.954)	0.888 (0.764-1.000)
Sensitivity	0.200	0.400
Specificity	0.884	0.978
Accuracy	0.750	0.867
F1 score	0.235	0.533
DeLong’s test	-	P < 0.05

AUC: Area under the curve; CI: Confidence interval.

Full Size Table

Citation: Luan FF, Chen JY, Zheng YZ, Hu MH, Huang F, Zheng CX. Efficacy of a machine learning model integrating clinical-psychosocial factors in predicting posttraumatic bone nonunion and bone defects. World J Psychiatry 2026; 16(9): 119455
URL: https://www.wjgnet.com/2220-3206/full/v16/i9/119455.htm
DOI: https://dx.doi.org/10.5498/wjp.119455

Luan FF, Chen JY, Zheng YZ, Hu MH, Huang F, Zheng CX. Efficacy of a machine learning model integrating clinical-psychosocial factors in predicting posttraumatic bone nonunion and bone defects. World J Psychiatry 2026; 16(9): 119455 [DOI: 10.5498/wjp.119455]

All content on this site: Copyright © 1993-2026 Baishideng Publishing Group Inc, its licensors, and contributors. All rights are reserved, including those for text and data mining, AI training, and similar technologies. For all open access content, the relevant licensing terms apply.