BACKGROUND AND OBJECTIVE

Access to healthcare remains a challenge in most areas in the Philippines. Fifty-three percent (53%) of the Philippine population do not have access to a rural health unit (RHU) within a 30-minute travel t ime. As a response, the Department of Health (DOH) needs to construct an additional 2400 RHUs by 2025. This paper uses the Philippine Health Facility Development Plan 2020-2040 (PHFDP) as a reference to present a solution for locating sites for RHU placement in under-served areas using neural networks to meet the 30-minute travel time by maximizing population accessibility.

RHU accessibility was measured using geographic attributes as inputs to a back propagation neural network (BPNN) and a recurrent neural network (RNN): (1) land coverage and hazard data, representing geographical limitations; (2) population density and distribution, indicating demand for healthcare services; and (3) infrastructure-related features, such as road networks, points of interest, and the locations of existing RHUs, which influence healthcare accessibility. The models were trained to identify underserved areas and were implemented on a nationwide scale, excluding NCR, to locate candidate areas to increase population access to the new RHUs. The models were validated using a healthcare facility accessibility index (HCFAI) to assess RHU coverage improvement.

The BPNN showed stronger generalization across regions, achieving 79.1% average accuracy in distinguishing low from high accessible areas on Region 1 and identifying 1668 out of 3305 locations in the region as candidate sites. The RNN, better capturing unique regional characteristics, required separate training: 77.2% average accuracy on Region 1, identifying 1593 candidate sites. Our findings suggest expanding the use of land improves population access to healthcare facilities. Both models found more than the needed number of RHUs by 2040. The BPNN was more consistent than RNN to improve a region’s overall accessibility by increasing the HCFAI. The BPNN can increase population access to an RHU from 2.5-98.5% from its original population with access to an RHU.

The study demonstrates the usage of geographic attributes and neural networks to improve healthcare accessibility. The BPNN and RNN are adequate algorithms to find under-served areas and candidate sites for RHU construction to maximize population accessibility. The HCFAI metric validates the locations to highlight which neural network maximizes more of the region’s populat ion. The study contributes to ongoing efforts to improve healthcare infrastructure and accessibility, offering datadriven recommendations for RHU locations.

Human ; Humans ; Humanities ; Health ; Forecasting ; Algorithms

Objective To mine and analyze the routine blood test data of children with allergic rhinitis (AR), identify routine blood parameters related to childhood allergic rhinitis, establish an effective diagnostic model, and evaluate the performance of the model. Methods This study was a retrospective study of clinical cases. The experimental group comprised a total of 1110 children diagnosed with AR at the First Affiliated Hospital of Air Force Medical University during the period from December 12, 2020 to December 12, 2021, while the control group included 1109 children without a history of allergic rhinitis or other allergic diseases who underwent routine physical examinations during the same period. Information such as age, sex and routine blood test results was collected for all subjects. The levels of routine blood test indicators were compared between AR children and healthy children using comprehensive intelligent baseline analysis, with indicators of P≥0.05 excluded; variables were screened by Lasso regression. Binary Logistic regression was used to further evaluate the influence of multiple routine blood indexes on the results. Five kinds of machine model algorithms were used, namely extreme value gradient lift (XGBoost), logistic regression (LR), gradient lift decision tree (LGBMC), Random forest (RF) and adaptive lift algorithm (AdaBoost), to establish the diagnostic models. The receiver operating characteristic (ROC) curve was used to screen the optimal model. The best LightGBM algorithm was used to build an online patient risk assessment tool for clinical application. Results Statistically significant differences were observed between the AR group and the control group in the following routine blood test indicators: mean cellular hemoglobin concentration (MCHC), hemoglobin (HGB), absolute value of basophils (BASO), absolute value of eosinophils (EOS), large platelet ratio (P-LCR), mean platelet volume (MPV), platelet distribution width (PDW), platelet count (PLT), absolute values of leukocyte neutrophil (W-LCC), leukocyte monocyte (W-MCC), leukocyte lymphocyte (W-SCC), and age. Lasso regression identified these variables as important predictors, and binary Logistic regression further analyzed the significant influence of these variables on the results. The optimal machine learning algorithm LightGBM was used to establish a multi-index joint detection model. The model showed robust prediction performance in the training set, with AUC values of 0.8512 and 0.8103 in the internal validation set. Conclusion The identified routine blood parameters can be used as potential biomarkers for early diagnosis and risk assessment of AR, which can improve the accuracy and efficiency of diagnosis. The established model provides scientific basis for more accurate diagnostic tools and personalized prevention strategies. Future studies should prospectively validate these findings and explore their applicability in other related diseases.
Humans ; Male ; Female ; Rhinitis, Allergic/blood* ; Child ; Biomarkers/blood* ; Retrospective Studies ; Early Diagnosis ; Child, Preschool ; ROC Curve ; Logistic Models ; Hematologic Tests ; Algorithms ; Adolescent ; Machine Learning

PURPOSE: Intertrochanteric fracture (ITF) classification is crucial for surgical decision-making. However, orthopedic trauma surgeons have shown lower accuracy in ITF classification than expected. The objective of this study was to utilize an artificial intelligence (AI) method to improve the accuracy of ITF classification. METHODS: We trained a network called YOLOX-SwinT, which is based on the You Only Look Once X (YOLOX) object detection network with Swin Transformer (SwinT) as the backbone architecture, using 762 radiographic ITF examinations as the training set. Subsequently, we recruited 5 senior orthopedic trauma surgeons (SOTS) and 5 junior orthopedic trauma surgeons (JOTS) to classify the 85 original images in the test set, as well as the images with the prediction results of the network model in sequence. Statistical analysis was performed using the SPSS 20.0 (IBM Corp., Armonk, NY, USA) to compare the differences among the SOTS, JOTS, SOTS + AI, JOTS + AI, SOTS + JOTS, and SOTS + JOTS + AI groups. All images were classified according to the AO/OTA 2018 classification system by 2 experienced trauma surgeons and verified by another expert in this field. Based on the actual clinical needs, after discussion, we integrated 8 subgroups into 5 new subgroups, and the dataset was divided into training, validation, and test sets by the ratio of 8:1:1. RESULTS: The mean average precision at the intersection over union (IoU) of 0.5 (mAP50) for subgroup detection reached 90.29%. The classification accuracy values of SOTS, JOTS, SOTS + AI, and JOTS + AI groups were 56.24% ± 4.02%, 35.29% ± 18.07%, 79.53% ± 7.14%, and 71.53% ± 5.22%, respectively. The paired t-test results showed that the difference between the SOTS and SOTS + AI groups was statistically significant, as well as the difference between the JOTS and JOTS + AI groups, and the SOTS + JOTS and SOTS + JOTS + AI groups. Moreover, the difference between the SOTS + JOTS and SOTS + JOTS + AI groups in each subgroup was statistically significant, with all p < 0.05. The independent samples t-test results showed that the difference between the SOTS and JOTS groups was statistically significant, while the difference between the SOTS + AI and JOTS + AI groups was not statistically significant. With the assistance of AI, the subgroup classification accuracy of both SOTS and JOTS was significantly improved, and JOTS achieved the same level as SOTS. CONCLUSION In conclusion, the YOLOX-SwinT network algorithm enhances the accuracy of AO/OTA subgroups classification of ITF by orthopedic trauma surgeons.
Humans ; Hip Fractures/diagnostic imaging* ; Orthopedic Surgeons ; Algorithms ; Artificial Intelligence

PURPOSE: To construct a decision-making app for pre-hospital damage control resuscitation (PHDCR) for severely injured patients, and to make a preliminary trial test on the effectiveness and usability aspects of the constructed app. METHODS: Decision-making algorithms were first established by a thorough literature review, and were then used to be learned by computer with 3 kinds of text segmentation algorithms, i.e., dictionary-based segmentation, machine learning algorithms based on labeling, and deep learning algorithms based on understanding. B/S architecture mode and Spring Boot were used as a framework to construct the app. A total of 16 Grade-5 medical students were recruited to test the effectiveness and usability aspects of the app by using an animal model-based test on simulated PHDCR. Twelve adult Bama miniature pigs were subjected to penetrating abdominal injuries and were randomly assigned to the 16 students, who were randomly divided into 2 groups (n = 8 each): group A (decided on PHDCR by themselves) and group B (decided on PHDCR with the aid of the app). The students were asked to complete the PHDCR within 1 h, and then blood samples were taken and thromboelastography, routine coagulation test, blood cell count, and blood gas analysis were examined. The lab examination results along with the value of mean arterial pressure were used to compare the resuscitation effects between the 2 groups. Furthermore, a 4-statement-based post-test survey on a 5-point Likert scale was performed in group B students to test the usability aspects of the constructed app. RESULTS: With the above 3 kinds of text segmentation algorithm, B/S architecture mode, and Spring Boot as the development framework, the decision-making app for PHDCR was successfully constructed. The time to decide PHDCR was (28.8 ± 3.41) sec in group B, much shorter than that in group A (87.5 ± 8.53) sec (p < 0.001). The outcomes of animals treated by group B students were much better than that by group A students as indicated by higher mean arterial pressure, oxygen saturation and fibrinogen concentration and maximum amplitude, and lower R values in group B than those in group A. The post-test survey revealed that group B students gave a mean score of no less than 4 for all 4 statements. CONCLUSION A decision-making app for PHDCR was constructed in the present study and the preliminary trial test revealed that it could help to improve the resuscitation effect in animal models of penetrating abdominal injury.
Animals ; Swine ; Resuscitation/methods* ; Mobile Applications ; Humans ; Algorithms ; Emergency Medical Services/methods* ; Male ; Decision Making ; Female

PURPOSE: Septic shock is associated with high mortality and poor outcomes among sepsis patients with coagulopathy. Although traditional statistical methods or machine learning (ML) algorithms have been proposed to predict septic shock, these potential approaches have never been systematically compared. The present work aimed to develop and compare models to predict septic shock among patients with sepsis. METHODS: It is a retrospective cohort study based on 484 patients with sepsis who were admitted to our intensive care units between May 2018 and November 2022. Patients from the 908th Hospital of Chinese PLA Logistical Support Force and Nanchang Hongdu Hospital of Traditional Chinese Medicine were respectively allocated to training (n=311) and validation (n=173) sets. All clinical and laboratory data of sepsis patients characterized by comprehensive coagulation indexes were collected. We developed 5 models based on ML algorithms and 1 model based on a traditional statistical method to predict septic shock in the training cohort. The performance of all models was assessed using the area under the receiver operating characteristic curve and calibration plots. Decision curve analysis was used to evaluate the net benefit of the models. The validation set was applied to verify the predictive accuracy of the models. This study also used Shapley additive explanations method to assess variable importance and explain the prediction made by a ML algorithm. RESULTS: Among all patients, 37.2% experienced septic shock. The characteristic curves of the 6 models ranged from 0.833 to 0.962 and 0.630 to 0.744 in the training and validation sets, respectively. The model with the best prediction performance was based on the support vector machine (SVM) algorithm, which was constructed by age, tissue plasminogen activator-inhibitor complex, prothrombin time, international normalized ratio, white blood cells, and platelet counts. The SVM model showed good calibration and discrimination and a greater net benefit in decision curve analysis. CONCLUSION The SVM algorithm may be superior to other ML and traditional statistical algorithms for predicting septic shock. Physicians can better understand the reliability of the predictive model by Shapley additive explanations value analysis.
Humans ; Shock, Septic/blood* ; Machine Learning ; Male ; Female ; Retrospective Studies ; Middle Aged ; Aged ; Sepsis/complications* ; ROC Curve ; Cohort Studies ; Adult ; Intensive Care Units ; Algorithms ; Blood Coagulation ; Critical Illness

This review focuses on the diagnostic algorithm for nonobstructive azoospermia (NOA), a significant male factor contributing to infertility. NOA, characterized by the absence of sperm in the ejaculate, requires a systematic diagnostic approach to identify reversible conditions, genetic factors, and prognosis for achieving pregnancy. The diagnostic pathway involves semen analysis and a comprehensive evaluation for hormonal deficiencies, anatomical abnormalities, and genetic factors. The importance of medical history, physical examination, endocrine evaluation, imaging, and genetic testing is emphasized. This review highlights the significance of differentiating NOA from obstructive azoospermia (OA) and outlines key considerations for effective management, including surgical sperm retrieval and assisted reproductive techniques. Testicular biopsy is discussed as a definitive method to distinguish obstructive cases from nonobstructive cases, providing valuable prognostic information. Overall, a thorough and systematic diagnostic approach is essential for the effective management of men suspected with NOA, offering insights into potential treatment options and reproductive outcomes.
Humans ; Azoospermia/therapy* ; Male ; Algorithms ; Semen Analysis ; Testis/pathology* ; Sperm Retrieval ; Biopsy ; Infertility, Male/etiology*

OBJECTIVE: To explore the influencing factors on the prognosis of patients with multiple myeloma (MM) after bortezomib treatment, and construct a decision tree risk prediction model based on the influencing factors. METHODS: One hundred and seventy MM patients admitted to the People's Hospital of Jianyang City from January 2019 to June 2022 were selected as research subjects, and divided into poor prognosis group and good prognosis group according to the prognosis after bortezomib treatment. The clinical data of the patients were analyzed, univariate and logistic regression analysis were used to screen influencing factors, SPSS Modeler software was used to construct a decision tree prediction model, and the diagnostic performance of the decision tree risk prediction model was analyzed. RESULTS: The incidence of poor prognosis in 170 MM patients after bortezomib-based chemotherapy was 21.18%. Kappa light chain level≥19.4 mg/L, platelet count (PLT) ≤100×10⁹/L, homocysteine (Hcy) >22 μmol/L, serum creatinine (Scr) ≥176 μmol/L, lactate dehydrogenase (LDH) ≥300 U/L, serum ferritin (SF) >500 mg/L, and β₂-microglobulin (MG) >6 μg/L were independent risk factors for poor prognosis in MM patients after bortezomib treatment (all P < 0.05). The decision tree model selected 7 explanatory variables (Kappa light chain level, LDH, PLT, SF, β₂-MG, Scr, and Hcy) as nodes of the model, among which Kappa light chain level was the most important predictor. In addition, the area under the ROC curve (AUC) values of the decision tree model and logistic regression model were 0.895 and 0.881, respectively. The prediction performance of the decision tree model was better than that of the logistic regression model ( Z=3.325, P =0.005). CONCLUSION The decision tree model has high value in predicting the prognosis after bortezomib treatment in MM patients, which can screen high-risk factors that affect poor prognosis, providing practical references for clinical healthcare professionals to take preventive treatment for high-risk MM patients.
Humans ; Bortezomib/therapeutic use* ; Multiple Myeloma/diagnosis* ; Decision Trees ; Prognosis ; Algorithms ; Risk Factors ; Male ; Female ; Middle Aged

BACKGROUND: Hypertension is a serious chronic disease that can significantly lead to various cardiovascular diseases, affecting vital organs such as the heart, brain, and kidneys. Our goal is to predict the risk of new onset hypertension using machine learning algorithms and identify the characteristics of patients with new onset hypertension. METHODS: We analyzed data from the 2011 China Health and Nutrition Survey cohort of individuals who were not hypertensive at baseline and had follow-up results available for prediction by 2015. We tested and evaluated the performance of four traditional machine learning algorithms commonly used in epidemiological studies: Logistic Regression, Support Vector Machine, XGBoost, LightGBM, and two deep learning algorithms: TabNet and AMFormer model. We modeled using 16 and 29 features, respectively. SHAP values were applied to select key features associated with new onset hypertension. RESULTS: A total of 4,982 participants were included in the analysis, of whom 1,017 developed hypertension during the 4-year follow-up. Among the 16-feature models, Logistic Regression had the highest AUC of 0.784(0.775∼0.806). In the 29-feature prediction models, AMFormer performed the best with an AUC of 0.802(0.795∼0.820), and also scored the highest in MCC (0.417, 95%CI: 0.400∼0.434) and F1 (0.503, 95%CI: 0.484∼0.505) metrics, demonstrating superior overall performance compared to the other models. Additionally, key features selected based on the AMFormer, such as age, province, waist circumference, urban or rural location, education level, employment status, weight, WHR, and BMI, played significant roles. CONCLUSION We used the AMFormer model for the first time in predicting new onset hypertension and achieved the best results among the six algorithms tested. Key features associated with new onset hypertension can be determined through this algorithm. The practice of machine learning algorithms can further enhance the predictive efficacy of diseases and identify risk factors for diseases.
Humans ; China/epidemiology* ; Hypertension/diagnosis* ; Machine Learning ; Male ; Female ; Middle Aged ; Adult ; Nutrition Surveys ; Algorithms ; Aged ; Risk Factors

OBJECTIVE: To propose a new protocol for personalized mandibular reconstruction assisted by three-dimensional (3D) retrieval model based on fully connected neural network (FCNN) and a database of mandibles, and to verify clinical feasibility of the protocol. METHODS: A database of mandibles of 300 normal northern Chinese Han people was established. On the basis of cephalometry, the mandible landmarks with good stability were further screened. Mandibular landmarks were selected and geometric features of the mandible were extracted. A 3D retrieval algorithm was developed, which could retrieve the mandible most similar to a given mandible from the database. A FCNN was built to train the algorithm to improve accuracy of the 3D retrieval model. Using Geomagic Control 2014 software, matching accuracy of the 3D retrieval model was based on aforementioned mandible database and algorithm. From December 2019 to March 2021, a total of 5 patients underwent personalized mandibular reconstruction assisted by a 3D retrieval model based on mandible database and FCNN in the Department of Oral and Maxillofacial Surgery, Peking University School and Hospital of Stomatology. The most similar mandible was retrieved from mandible database through 3D retrieval algorithm. It was used to restore the premorbid morphology of defect area and guide mandibular reconstruction. For the 5 patients, mandible was reconstructed with iliac flap. Virtual surgical plan was transformed using individual surgical guides. RESULTS: Through screening, mandibular landmarks with high reproducibility and stability were identified and composed of mandibular landmarker protocols. After training, the average deviation between most similar mandible retrieved from the 300-case mandible database through 3D retrieval model based on FCNN and given mandible was (1.77±0.44) mm. And the root-mean-square deviation between the most similar mandible retrieved from the database and given mandible was (2.58±0.86) mm. The mandibular reconstruction surgery was successful in all the 5 patients. Their facial symmetry and occlusion were restored. All the patients were satisfied with postoperative appearance. The mean deviation between postoperative mandible and preoperative design was (0.98±0.17) mm. The area with a deviation ≤1 mm accounted for 61.34%±14. 13%, ≤2 mm accounted for 83.82%±7.35%, and ≤3 mm accounted for 93.94%± 2.87%. CONCLUSION The personalized mandibular reconstruction assisted by 3D retrieval model based on the 300-case mandible database and FCNN is feasible clinically.
Humans ; Neural Networks, Computer ; Mandibular Reconstruction/methods* ; Mandible/diagnostic imaging* ; Imaging, Three-Dimensional/methods* ; Adult ; Databases, Factual ; Female ; Male ; Algorithms ; Middle Aged ; Cephalometry