Duy Nguyen Anh Tran
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Duy Nguyen Anh Tran has a total of 41 co-authors. Here are the top co-authors by number of shared publications:
- Yi-Jie Kuo
Department of Orthopedics, Wan Fang Hospital, Taipei Medical University, Taipei City, Taiwan
6 shared publications - Yu-Pin Chen
Department of Orthopedics, Wan Fang Hospital, Taipei Medical University, Taipei City, Taiwan
6 shared publications - Bao Tu Thai Nguyen
Trường Đại học Y dược Cần Thơ
4 shared publications - Tan Thanh Nguyen
College of Medicine, Taipei Medical University, Taipei 11031, Taiwan
4 shared publications - Chung-Ying Lin
Institute of Allied Health Sciences, College of Medicine, National Cheng Kung University, Tainan, Taiwan
2 shared publications - Ming-Hsiu Chiang
Department of General Medicine, Kaohsiung Chang Gung Memorial Hospital, Kaohsiung 833, Taiwan
2 shared publications
Latest Publications
- Open Access
- 1 August 2026
- Published by SAGE Publications in Geriatric Orthopaedic Surgery & Rehabilitation
- Vol. 17
Application of Smart Walker-Assisted Walking Training for Postoperative Hip Fracture Patients: An In-Hospital Outcome and Feasibility Analysis
Background: Regaining independence in walking after hip fracture surgery is critical for improving quality of life (QoL) and reducing the risks of morbidity and mortality. Integrating advanced technologies into walking aids is an emerging trend that aims to assist patients in their rehabilitation and accelerate recovery. In this study, we evaluated the effectiveness of a novel smart walker compared to a conventional walker in facilitating walking training and recovery for patients undergoing rehabilitation after hip fracture surgery. Materials and Methods: This prospective cohort study included patients with hip fractures who underwent surgical treatment at our center between August 2023 and June 2024. On postoperative day 1, patients were enrolled for walking rehabilitation using either a conventional walker or a smart walker. Key outcomes were assessed before and after in-hospital training, including ambulation ability, mental status, functional independence, QoL, hip range of motion (ROM), hip muscle strength, and gait measures. Results: 32 patients with hip fractures were analyzed (mean age 81.7 years; 16 using a conventional walker, 16 using a smart walker). Both groups demonstrated significant improvements in functional and mobility outcomes during hospitalization. While discharge values were comparable between groups, the smart walker group showed greater improvements in hip ROM and ADLs, with additional gains in gait speed and stride angle that did not consistently remain significant after sensitivity analyses. Conclusions: Early postoperative rehabilitation with a smart walker was feasible and associated with greater short-term improvements in gait performance and functional recovery during hospitalization compared with a conventional walker.
- 1 August 2026
- Published by SAGE Publications in Geriatric Orthopaedic Surgery & Rehabilitation
- Vol. 17
Open AccessApplication of Smart Walker-Assisted Walking Training for Postoperative Hip Fracture Patients: An In-Hospital Outcome and Feasibility Analysis
Background: Regaining independence in walking after hip fracture surgery is critical for improving quality of life (QoL) and reducing the risks of morbidity and mortality. Integrating advanced technologies into walking aids is an emerging trend that aims to assist patients in their rehabilitation and accelerate recovery. In this study, we evaluated the effectiveness of a novel smart walker compared to a conventional walker in facilitating walking training and recovery for patients undergoing rehabilitation after hip fracture surgery. Materials and Methods: This prospective cohort study included patients with hip fractures who underwent surgical treatment at our center between August 2023 and June 2024. On postoperative day 1, patients were enrolled for walking rehabilitation using either a conventional walker or a smart walker. Key outcomes were assessed before and after in-hospital training, including ambulation ability, mental status, functional independence, QoL, hip range of motion (ROM), hip muscle strength, and gait measures. Results: 32 patients with hip fractures were analyzed (mean age 81.7 years; 16 using a conventional walker, 16 using a smart walker). Both groups demonstrated significant improvements in functional and mobility outcomes during hospitalization. While discharge values were comparable between groups, the smart walker group showed greater improvements in hip ROM and ADLs, with additional gains in gait speed and stride angle that did not consistently remain significant after sensitivity analyses. Conclusions: Early postoperative rehabilitation with a smart walker was feasible and associated with greater short-term improvements in gait performance and functional recovery during hospitalization compared with a conventional walker.
- 18 June 2026
- Published by Springer Nature in European Spine Journal
- p. 1-15
Role of paraspinal muscle fatty infiltration in predicting adjacent segment disease after lumbar spinal fusion: a systematic review and meta-analysis
Purpose To evaluate whether preoperative fat infiltration (FI) in paraspinal muscles (PSM), specifically the multifidus (MF) and erector spinae (ES), is a reliable predictor of adjacent segment disease (ASD) after lumbar spinal fusion in adults. Methods A systematic review and meta-analysis was conducted by searching PubMed, Embase, and Scopus from inception to March 2025. Studies with cohort or case–control designs reporting on preoperative FI and ASD development were included. Of 630 studies, 11 met the eligibility criteria, involving 1,474 patients, and were analyzed. Mean differences were pooled using a random-effects model. Results Pooled analysis showed that preoperative FI was significantly higher in the ASD development group (MD = 4.83%; 95% CI: 3.28 to 6.39; I² = 59.0%). Patients in the ASD group were significantly older compared to controls (MD = 1.88 years; 95% CI: 0.89 to 2.86). Subgroup analysis by fusion length (short vs. long) and muscle type (MF vs. PSM) revealed no significant differences in effect sizes, indicating the consistent predictive value of FI across groups. Meta-regression analyses indicated that fusion length and patient age did not significantly moderate the association between FI and ASD, suggesting that FI is an independent predictor regardless of these demographic and surgical factors. Conclusion: Preoperative PSM FI is associated with increased ASD risk after LSF. Incorporating FI assessment into preoperative surgical planning may help optimize outcomes, while targeted preoperative muscle optimization could offer a promising strategy to improve long-term results.
- 18 June 2026
- Published by Springer Nature in European Spine Journal
- p. 1-15
Role of paraspinal muscle fatty infiltration in predicting adjacent segment disease after lumbar spinal fusion: a systematic review and meta-analysis
Purpose To evaluate whether preoperative fat infiltration (FI) in paraspinal muscles (PSM), specifically the multifidus (MF) and erector spinae (ES), is a reliable predictor of adjacent segment disease (ASD) after lumbar spinal fusion in adults. Methods A systematic review and meta-analysis was conducted by searching PubMed, Embase, and Scopus from inception to March 2025. Studies with cohort or case–control designs reporting on preoperative FI and ASD development were included. Of 630 studies, 11 met the eligibility criteria, involving 1,474 patients, and were analyzed. Mean differences were pooled using a random-effects model. Results Pooled analysis showed that preoperative FI was significantly higher in the ASD development group (MD = 4.83%; 95% CI: 3.28 to 6.39; I² = 59.0%). Patients in the ASD group were significantly older compared to controls (MD = 1.88 years; 95% CI: 0.89 to 2.86). Subgroup analysis by fusion length (short vs. long) and muscle type (MF vs. PSM) revealed no significant differences in effect sizes, indicating the consistent predictive value of FI across groups. Meta-regression analyses indicated that fusion length and patient age did not significantly moderate the association between FI and ASD, suggesting that FI is an independent predictor regardless of these demographic and surgical factors. Conclusion: Preoperative PSM FI is associated with increased ASD risk after LSF. Incorporating FI assessment into preoperative surgical planning may help optimize outcomes, while targeted preoperative muscle optimization could offer a promising strategy to improve long-term results.
- Open Access
- 1 September 2025
- Published by Bioscientifica in EFORT Open Reviews
- Vol. 10 (9) , 709-717
One-year mortality rates of fragility fractures of the pelvis: a systematic review and meta-analysis
Purpose: Methods: Results: Conclusion:
- 1 September 2025
- Published by Bioscientifica in EFORT Open Reviews
- Vol. 10 (9) , 709-717
Open AccessOne-year mortality rates of fragility fractures of the pelvis: a systematic review and meta-analysis
Purpose: Methods: Results: Conclusion:
- Open Access
A Higher Charlson Comorbidity Index Is a Risk Factor for Hip Fracture in Older Adults During Low-Temperature Periods: A Cross-Sectional Study
Background and Objectives: The incidence of hip fractures is increasing, and there have been reports linking cold weather to a higher risk of fractures. This study aimed to evaluate clinical variables in hip fracture patients who may predispose them to such fractures under different temperatures. Materials and Methods: This is a cross-sectional study conducted at a single medical center, enrolling older adults (≥60 years) who had experienced a hip fracture. Comprehensive clinical histories and detailed information regarding each patient’s hip fracture were obtained. All meteorological data were extracted from the Taiwan Central Weather Bureau database. Multiple clinical parameters that may have a close connection with the temperature at which the hip fracture occurred were screened. Statistical analysis involved using the Pearson correlation test or the independent Student’s t test, followed by generalized estimating equation analysis. Results: The cohort comprised 506 older adults with hip fractures. Initial univariate analysis revealed that a history of past cerebrovascular diseases, Charlson Comorbidity Index, patient age, and preinjury Barthel Index were significantly related to the temperature at which the hip fractures occurred. The generalized estimating equation analysis indicated that only the Charlson Comorbidity Index had a considerably inverse association with temperature. This finding suggests that for older adults with a higher Charlson Comorbidity Index, hip fractures tend to occur at lower temperatures and vice versa. Conclusions: Comorbidities are the only clinical concern that predisposes older adults to hip fractures under colder temperatures. This epidemiological finding could guide future patient education and hip fracture prevention programs.
Open AccessA Higher Charlson Comorbidity Index Is a Risk Factor for Hip Fracture in Older Adults During Low-Temperature Periods: A Cross-Sectional Study
Background and Objectives: The incidence of hip fractures is increasing, and there have been reports linking cold weather to a higher risk of fractures. This study aimed to evaluate clinical variables in hip fracture patients who may predispose them to such fractures under different temperatures. Materials and Methods: This is a cross-sectional study conducted at a single medical center, enrolling older adults (≥60 years) who had experienced a hip fracture. Comprehensive clinical histories and detailed information regarding each patient’s hip fracture were obtained. All meteorological data were extracted from the Taiwan Central Weather Bureau database. Multiple clinical parameters that may have a close connection with the temperature at which the hip fracture occurred were screened. Statistical analysis involved using the Pearson correlation test or the independent Student’s t test, followed by generalized estimating equation analysis. Results: The cohort comprised 506 older adults with hip fractures. Initial univariate analysis revealed that a history of past cerebrovascular diseases, Charlson Comorbidity Index, patient age, and preinjury Barthel Index were significantly related to the temperature at which the hip fractures occurred. The generalized estimating equation analysis indicated that only the Charlson Comorbidity Index had a considerably inverse association with temperature. This finding suggests that for older adults with a higher Charlson Comorbidity Index, hip fractures tend to occur at lower temperatures and vice versa. Conclusions: Comorbidities are the only clinical concern that predisposes older adults to hip fractures under colder temperatures. This epidemiological finding could guide future patient education and hip fracture prevention programs.
- 11 September 2024
- Published by Elsevier in World Neurosurgery
- Vol. 191, e730-e745
Structural Allograft versus Polyetheretherketone Cage in Anterior Cervical Discectomy and Fusion: A Meta-Analysis
- 11 September 2024
- Published by Elsevier in World Neurosurgery
- Vol. 191, e730-e745
Structural Allograft versus Polyetheretherketone Cage in Anterior Cervical Discectomy and Fusion: A Meta-Analysis
- Open Access
- 1 August 2024
- Published by Bioscientifica in EFORT Open Reviews
- Vol. 9 (8) , 817-826
Adverse effect of smoking on surgical site infection following ankle and calcaneal fracture fixation: a meta-analysis
Purpose: Studies have reported conflicting findings on the relationship between smoking and surgical site infection (SSI) post fixation for ankle and calcaneal fractures. This meta-analysis explored the effect of smoking on SSI incidence following open reduction and internal fixation (ORIF) of these fractures. Methods: Full-text studies on smoking’s influence on post-ORIF SSI rates for closed ankle and calcaneal fractures were sourced from the PubMed, Embase, and Cochrane databases, with no consideration given to language or publication date. Study quality was appraised using the Newcastle–Ottawa Scale. Odds ratios (OR) and the corresponding 95% CIs were determined using random-effects models. This meta-analysis adhered to the PRISMA guidelines and was registered with PROSPERO (CRD42023429372). Results: The analysis incorporated data from 16 cohort and case–control studies, totaling 41 944 subjects, 9984 of whom were smokers, with 956 SSI cases. Results indicated smokers faced a higher SSI risk (OR: 1.62; 95% CI: 1.32–1.97, P < 0.0001) post ORIF, with low heterogeneity (I 2 = 26%). Smoking was identified as a significant deep SSI risk factor (OR: 2.09; 95% CI: 1.42–3.09; P = 0.0002; I 2 = 31%). However, the subgroup analysis revealed no association between smoking and superficial SSI (OR: 1.05; 95% CI: 0.82–1.33; P = 0.70; I 2 = 0%). Conclusion: Smoking is associated with increased SSI risk after ORIF for closed ankle and calcaneus fractures. Although no clear link was found between superficial SSI and smoking, the data underscore the negative influence of smoking on deep SSI incidence.
- 1 August 2024
- Published by Bioscientifica in EFORT Open Reviews
- Vol. 9 (8) , 817-826
Open AccessAdverse effect of smoking on surgical site infection following ankle and calcaneal fracture fixation: a meta-analysis
Purpose: Studies have reported conflicting findings on the relationship between smoking and surgical site infection (SSI) post fixation for ankle and calcaneal fractures. This meta-analysis explored the effect of smoking on SSI incidence following open reduction and internal fixation (ORIF) of these fractures. Methods: Full-text studies on smoking’s influence on post-ORIF SSI rates for closed ankle and calcaneal fractures were sourced from the PubMed, Embase, and Cochrane databases, with no consideration given to language or publication date. Study quality was appraised using the Newcastle–Ottawa Scale. Odds ratios (OR) and the corresponding 95% CIs were determined using random-effects models. This meta-analysis adhered to the PRISMA guidelines and was registered with PROSPERO (CRD42023429372). Results: The analysis incorporated data from 16 cohort and case–control studies, totaling 41 944 subjects, 9984 of whom were smokers, with 956 SSI cases. Results indicated smokers faced a higher SSI risk (OR: 1.62; 95% CI: 1.32–1.97, P < 0.0001) post ORIF, with low heterogeneity (I 2 = 26%). Smoking was identified as a significant deep SSI risk factor (OR: 2.09; 95% CI: 1.42–3.09; P = 0.0002; I 2 = 31%). However, the subgroup analysis revealed no association between smoking and superficial SSI (OR: 1.05; 95% CI: 0.82–1.33; P = 0.70; I 2 = 0%). Conclusion: Smoking is associated with increased SSI risk after ORIF for closed ankle and calcaneus fractures. Although no clear link was found between superficial SSI and smoking, the data underscore the negative influence of smoking on deep SSI incidence.
- Open Access
The Association between Red Blood Cell Distribution Width and Mortality Risk after Hip Fracture: A Meta-Analysis
Background and Objectives: Hip fractures in the elderly pose a considerable health risk and cause concern. Red blood cell distribution width (RDW) is a valuable marker for identifying patients at high risk of age-related mortality and various disorders and diseases. However, its association with poor patient outcomes following hip fractures has yet to be fully established. Hence, the purpose of this meta-analysis was to investigate and gain a better understanding of the relationship between RDW levels and the risk of mortality after hip fractures. Materials and Methods: PubMed, Embase, Web of Science, and other databases were comprehensively searched until April 2023 to identify relevant studies. The meta-analysis included observational studies finding the association between RDW at admission or preoperation and short-term and long-term mortality rates following hip fractures. The results were presented in terms of odds ratios (ORs) or hazard ratios (HRs) with corresponding 95% confidence intervals (CIs). Results: This meta-analysis included 10 studies involving 5834 patients with hip fractures. Patients with preoperative RDW of over 14.5% had higher risks of 1-year (OR: 5.40, 95% CI: 1.89–15.48, p = 0.002) and 3-month (OR: 2.91, 95% CI: 1.42–5.95, p = 0.004) mortality. Higher admission or preoperative RDW was significantly associated with an 11% higher mortality risk after 1 year (HR: 1.11, 95% CI: 1.06–1.17, p < 0.00001). Patients with higher preoperative RDW had a significantly higher risk of 6-month mortality, which was three times that of those with lower preoperative RDW (OR: 3.00, 95% CI: 1.60–5.61, p = 0.0006). Higher preoperative RDW was correlated to a higher 30-day mortality risk (OR: 6.44, 95% CI: 3.32–12.47, p < 0.00001). Conclusions: Greater RDW values at admission or before surgery were associated with a higher risk of short-term and long-term mortality following hip fractures. Because RDW can be easily measured using a routine blood test at a low cost, this parameter is promising as an indicator of mortality in elderly patients with hip fractures.
Open AccessThe Association between Red Blood Cell Distribution Width and Mortality Risk after Hip Fracture: A Meta-Analysis
Background and Objectives: Hip fractures in the elderly pose a considerable health risk and cause concern. Red blood cell distribution width (RDW) is a valuable marker for identifying patients at high risk of age-related mortality and various disorders and diseases. However, its association with poor patient outcomes following hip fractures has yet to be fully established. Hence, the purpose of this meta-analysis was to investigate and gain a better understanding of the relationship between RDW levels and the risk of mortality after hip fractures. Materials and Methods: PubMed, Embase, Web of Science, and other databases were comprehensively searched until April 2023 to identify relevant studies. The meta-analysis included observational studies finding the association between RDW at admission or preoperation and short-term and long-term mortality rates following hip fractures. The results were presented in terms of odds ratios (ORs) or hazard ratios (HRs) with corresponding 95% confidence intervals (CIs). Results: This meta-analysis included 10 studies involving 5834 patients with hip fractures. Patients with preoperative RDW of over 14.5% had higher risks of 1-year (OR: 5.40, 95% CI: 1.89–15.48, p = 0.002) and 3-month (OR: 2.91, 95% CI: 1.42–5.95, p = 0.004) mortality. Higher admission or preoperative RDW was significantly associated with an 11% higher mortality risk after 1 year (HR: 1.11, 95% CI: 1.06–1.17, p < 0.00001). Patients with higher preoperative RDW had a significantly higher risk of 6-month mortality, which was three times that of those with lower preoperative RDW (OR: 3.00, 95% CI: 1.60–5.61, p = 0.0006). Higher preoperative RDW was correlated to a higher 30-day mortality risk (OR: 6.44, 95% CI: 3.32–12.47, p < 0.00001). Conclusions: Greater RDW values at admission or before surgery were associated with a higher risk of short-term and long-term mortality following hip fractures. Because RDW can be easily measured using a routine blood test at a low cost, this parameter is promising as an indicator of mortality in elderly patients with hip fractures.
- Open Access
- 29 February 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Higher Charlson Comorbidity Index is a Risk Factor for Hip Fracture in Older Adults at Lower Temperatures: A Cross-sectional Study (Preprint)
BACKGROUND The incidence of hip fractures is increasing, and there have been reports linking cold weather to a higher risk of fractures. OBJECTIVE The study aimed to evaluate clinical variables in hip fracture patients who may predispose them to such fractures under different temperatures. METHODS This is a cross-sectional study conducted at a single medical center, enrolling older adults (≥60 years) who had experienced a hip fracture. Comprehensive clinical histories and detailed information regarding each patient's hip fracture were obtained. All meteorological data were extracted from the Taiwan Central Weather Bureau database. Multiple clinical parameters that may have a close connection with the temperature at which the hip fracture occurred were screened. Statistical analysis involved using the Pearson correlation test or the independent Student’s t-test, followed by generalized estimating equation analysis. RESULTS The cohort comprised 506 older adults with hip fractures. Initial univariate analysis revealed that a history of past cerebrovascular accidents, Charlson Comorbidity Index, patient age, and preinjury Barthel Index were significantly related to the temperature at which the hip fractures occurred. The generalized estimating equation analysis indicated that only the Charlson Comorbidity Index had a considerably inverse association with temperature. This finding suggests that for older adults with a higher Charlson Comorbidity Index, hip fractures tend to occur at lower temperatures, and vice versa. CONCLUSIONS Comorbidities are the only clinical concern that predisposes older adults to hip fracture under colder temperatures. This epidemiological finding could guide future patient education and hip fracture prevention programs. CLINICALTRIAL TMU-JIRB N201709053
- 29 February 2024
- Published by JMIR Publications Inc. in JMIR Preprints
Open AccessHigher Charlson Comorbidity Index is a Risk Factor for Hip Fracture in Older Adults at Lower Temperatures: A Cross-sectional Study (Preprint)
BACKGROUND The incidence of hip fractures is increasing, and there have been reports linking cold weather to a higher risk of fractures. OBJECTIVE The study aimed to evaluate clinical variables in hip fracture patients who may predispose them to such fractures under different temperatures. METHODS This is a cross-sectional study conducted at a single medical center, enrolling older adults (≥60 years) who had experienced a hip fracture. Comprehensive clinical histories and detailed information regarding each patient's hip fracture were obtained. All meteorological data were extracted from the Taiwan Central Weather Bureau database. Multiple clinical parameters that may have a close connection with the temperature at which the hip fracture occurred were screened. Statistical analysis involved using the Pearson correlation test or the independent Student’s t-test, followed by generalized estimating equation analysis. RESULTS The cohort comprised 506 older adults with hip fractures. Initial univariate analysis revealed that a history of past cerebrovascular accidents, Charlson Comorbidity Index, patient age, and preinjury Barthel Index were significantly related to the temperature at which the hip fractures occurred. The generalized estimating equation analysis indicated that only the Charlson Comorbidity Index had a considerably inverse association with temperature. This finding suggests that for older adults with a higher Charlson Comorbidity Index, hip fractures tend to occur at lower temperatures, and vice versa. CONCLUSIONS Comorbidities are the only clinical concern that predisposes older adults to hip fracture under colder temperatures. This epidemiological finding could guide future patient education and hip fracture prevention programs. CLINICALTRIAL TMU-JIRB N201709053
- Open Access
- 3 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1
Predicting Tumor Mutational Burden and Survival in Head and Neck Squamous Cancer Patients Using Machine Learning and Bioinformatics Approaches
Head and neck squamous cancer (HNSC) is a prevalent malignancy with a complex genetic profile. Tumor Mutational Burden (TMB) is an emerging biomarker associated with prognostic and therapeutic implications. In this study, we aimed to develop machine-learning models for predicting TMB and patient survival using RNA sequencing data and clinical features. Methods: We collected RNA sequencing data and clinical information of HNSC patients from Gene Expression Omnibus (GEO) (GSE142083) and The Cancer Genome Atlas (TCGA) databases. Machine learning models, including Random Forest, Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Logistic Regression, were built to predict TMB levels based on patient gene expression profiles. The top 100 important features (genes) were selected from these models to create a survival prediction model. Results: Among the tested models, Random Forest showed the highest accuracy (0.8011), followed by SVM (0.796), kNN (0.777), and logistic regression (0.704). Using the top 100 important genes, we developed a model to predict HNSC patient survival (under 3 years, 3--5 years, and over 5 years). Random forest achieved an accuracy of 0.70, while SVM and kNN reached 0.65. We identified five genes (KRT14, KRT6B, COL1A1, FN1, KRT6C) most closely related to TMB and patient survival. Through KEGG pathway analysis and neural network approaches, we discovered that these genes play a significant role in three pathways: PI3K-Akt signaling pathway, Human papillomavirus infection, and Bacterial invasion of epithelial cells. In Conclusion, our study highlights the potential of machine learning in integrating bioinformatics for predicting TMB and patient survival in HNSC. The identified genes (KRT14, KRT6B, COL1A1, FN1, KRT6C) and related pathways may serve as potential biomarkers and therapeutic targets in HNSC treatment and prognosis.
- 3 September 2023
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessPredicting Tumor Mutational Burden and Survival in Head and Neck Squamous Cancer Patients Using Machine Learning and Bioinformatics Approaches
Head and neck squamous cancer (HNSC) is a prevalent malignancy with a complex genetic profile. Tumor Mutational Burden (TMB) is an emerging biomarker associated with prognostic and therapeutic implications. In this study, we aimed to develop machine-learning models for predicting TMB and patient survival using RNA sequencing data and clinical features. Methods: We collected RNA sequencing data and clinical information of HNSC patients from Gene Expression Omnibus (GEO) (GSE142083) and The Cancer Genome Atlas (TCGA) databases. Machine learning models, including Random Forest, Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Logistic Regression, were built to predict TMB levels based on patient gene expression profiles. The top 100 important features (genes) were selected from these models to create a survival prediction model. Results: Among the tested models, Random Forest showed the highest accuracy (0.8011), followed by SVM (0.796), kNN (0.777), and logistic regression (0.704). Using the top 100 important genes, we developed a model to predict HNSC patient survival (under 3 years, 3--5 years, and over 5 years). Random forest achieved an accuracy of 0.70, while SVM and kNN reached 0.65. We identified five genes (KRT14, KRT6B, COL1A1, FN1, KRT6C) most closely related to TMB and patient survival. Through KEGG pathway analysis and neural network approaches, we discovered that these genes play a significant role in three pathways: PI3K-Akt signaling pathway, Human papillomavirus infection, and Bacterial invasion of epithelial cells. In Conclusion, our study highlights the potential of machine learning in integrating bioinformatics for predicting TMB and patient survival in HNSC. The identified genes (KRT14, KRT6B, COL1A1, FN1, KRT6C) and related pathways may serve as potential biomarkers and therapeutic targets in HNSC treatment and prognosis.