INTRODUCTION: Obstructive sleep apnoea (OSA) is a serious but underdiagnosed condition. Demand for the gold standard diagnostic polysomnogram (PSG) far exceeds its availability. More efficient diagnostic methods are needed, even in tertiary settings. Machine learning (ML) models have strengths in disease prediction and early diagnosis. We explored the use of ML with oximetry, demographic and anthropometric data to diagnose OSA. METHODS: A total of 2,996 patients were included for modelling and divided into test and training sets. Seven commonly used supervised learning algorithms were trained with the data. Sensitivity (recall), specificity, positive predictive value (PPV) (precision), negative predictive value, area under the receiver operating characteristic curve (AUC) and F1 measure were reported for each model. RESULTS: In the best performing four-class model (neural network model predicting no, mild, moderate or severe OSA), a prediction of moderate and/or severe disease had a combined PPV of 94%; one out of 335 patients had no OSA and 19 had mild OSA. In the best performing two-class model (logistic regression model predicting no-mild vs. moderate-severe OSA), the PPV for moderate-severe OSA was 92%; two out of 350 patients had no OSA and 26 had mild OSA. CONCLUSION Our study showed that the prediction of moderate-severe OSA in a tertiary setting with an ML approach is a viable option to facilitate early identification of OSA. Prospective studies with home-based oximeters and analysis of other oximetry variables are the next steps towards formal implementation.
Humans ; Oximetry/methods* ; Sleep Apnea, Obstructive/diagnosis* ; Male ; Female ; Middle Aged ; Machine Learning ; Polysomnography ; Adult ; Anthropometry ; ROC Curve ; Aged ; Algorithms ; Predictive Value of Tests ; Sensitivity and Specificity ; Neural Networks, Computer ; Demography

INTRODUCTION: In this study, we aimed to compare the performance of a convolutional neural network (CNN)-based deep learning model that was trained on a dataset of normal and abnormal paediatric elbow radiographs with that of paediatric emergency department (ED) physicians on a binomial classification task. METHODS: A total of 1,314 paediatric elbow lateral radiographs (patient mean age 8.2 years) were retrospectively retrieved and classified based on annotation as normal or abnormal (with pathology). They were then randomly partitioned to a development set (993 images); first and second tuning (validation) sets (109 and 100 images, respectively); and a test set (112 images). An artificial intelligence (AI) model was trained on the development set using the EfficientNet B1 network architecture. Its performance on the test set was compared to that of five physicians (inter-rater agreement: fair). Performance of the AI model and the physician group was tested using McNemar test. RESULTS: The accuracy of the AI model on the test set was 80.4% (95% confidence interval [CI] 71.8%-87.3%), and the area under the receiver operating characteristic curve (AUROC) was 0.872 (95% CI 0.831-0.947). The performance of the AI model vs. the physician group on the test set was: sensitivity 79.0% (95% CI: 68.4%-89.5%) vs. 64.9% (95% CI: 52.5%-77.3%; P = 0.088); and specificity 81.8% (95% CI: 71.6%-92.0%) vs. 87.3% (95% CI: 78.5%-96.1%; P = 0.439). CONCLUSION The AI model showed good AUROC values and higher sensitivity, with the P-value at nominal significance when compared to the clinician group.
Humans ; Deep Learning ; Child ; Retrospective Studies ; Male ; Female ; Radiography/methods* ; ROC Curve ; Elbow/diagnostic imaging* ; Neural Networks, Computer ; Child, Preschool ; Elbow Joint/diagnostic imaging* ; Emergency Service, Hospital ; Adolescent ; Infant ; Artificial Intelligence

INTRODUCTION: The diagnosis of sarcopenia relies on key indicators such as handgrip strength, walking speed and muscle mass. Developing a composite index that integrates these measures could enhance clinical evaluation in older adults. This study aimed to standardise and combine these metrics to establish a z score for the sarcopenia composite index (ZoSCI) tailored for the ageing population. Additionally, we explore the risk factors associated with ZoSCI to provide insights into early prevention and intervention strategies. METHOD: This retrospective study analysed data between January 2017 and December 2021 from an elderly health programme in Taiwan, applying the Asian Working Group for Sarcopenia criteria to assess sarcopenia. ZoSCI was developed by standardising handgrip strength, walking speed and muscle mass into z scores and integrating them into a composite index. Receiver operating characteristic (ROC) curve analysis was used to determine optimal cut-off values, and multiple regression analysis identified factors influencing ZoSCI. RESULTS: Among the 5047 participants, the prevalence of sarcopenia was 3.7%, lower than the reported global prevalence of 3.9-15.4%. ROC curve analysis established optimal cut-off points for distinguishing sarcopenia in ZoSCI: -1.85 (sensitivity 0.91, specificity 0.88) for males and -1.97 (sensitivity 0.93, specificity 0.88) for females. Factors associated with lower ZoSCI included advanced age, lower education levels, reduced exercise frequency, lower body mass index and creatinine levels. CONCLUSION This study introduces ZoSCI, a new compo-site quantitative indicator for identifying sarcopenia in older adults. The findings highlight specific risk factors that can inform early intervention. Future studies should validate ZoSCI globally, with international collaborations to ensure broader applicability.
Humans ; Sarcopenia/physiopathology* ; Male ; Aged ; Female ; Retrospective Studies ; Hand Strength ; Taiwan/epidemiology* ; ROC Curve ; Aged, 80 and over ; Risk Factors ; Walking Speed ; Geriatric Assessment/methods* ; Prevalence ; Muscle, Skeletal ; Middle Aged

BACKGROUND: Postoperative pulmonary complications (PPCs) are major adverse events in neurosurgical patients. This study aimed to develop and validate machine learning models predicting PPCs after neurosurgery. METHODS: PPCs were defined according to the European Perioperative Clinical Outcome standards as occurring within 7 postoperative days. Data of cases meeting inclusion/exclusion criteria were extracted from the anesthesia information management system to create three datasets: The development (data of Huashan Hospital, Fudan University from 2018 to 2020), temporal validation (data of Huashan Hospital, Fudan University in 2021) and external validation (data of other three hospitals in 2023) datasets. Machine learning models of six algorithms were trained using either 35 retrievable and plausible features or the 11 features selected by Lasso regression. Temporal validation was conducted for all models and the 11-feature models were also externally validated. Independent risk factors were identified and feature importance in top models was analyzed. RESULTS: PPCs occurred in 712 of 7533 (9.5%), 258 of 2824 (9.1%), and 207 of 2300 (9.0%) patients in the development, temporal validation and external validation datasets, respectively. During cross-validation training, all models except Bayes demonstrated good discrimination with an area under the receiver operating characteristic curve (AUC) of 0.840. In temporal validation of full-feature models, deep neural network (DNN) performed the best with an AUC of 0.835 (95% confidence interval [CI]: 0.805-0.858) and a Brier score of 0.069, followed by Logistic regression (LR), random forest and XGBoost. The 11-feature models performed comparable to full-feature models with very close but statistically significantly lower AUCs, with the top models of DNN and LR in temporal and external validations. An 11-feature nomogram was drawn based on the LR algorithm and it outperformed the minimally modified Assess respiratory RIsk in Surgical patients in CATalonia (ARISCAT) and Laparoscopic Surgery Video Educational Guidelines (LAS VEGAS) scores with a higher AUC (LR: 0.824, ARISCAT: 0.672, LAS: 0.663). Independent risk factors based on multivariate LR mostly overlapped with Lasso-selected features, but lacked consistency with the important features using the Shapley additive explanation (SHAP) method of the LR model. CONCLUSIONS: The developed models, especially the DNN model and the nomogram, had good discrimination and calibration, and could be used for predicting PPCs in neurosurgical patients. The establishment of machine learning models and the ascertainment of risk factors might assist clinical decision support for improving surgical outcomes. TRIAL REGISTRATION ChiCTR 2100047474; https://www.chictr.org.cn/showproj.html?proj=128279 .
Adult ; Aged ; Female ; Humans ; Male ; Middle Aged ; Algorithms ; Lung Diseases/etiology* ; Machine Learning ; Neurosurgical Procedures/adverse effects* ; Postoperative Complications/diagnosis* ; Risk Factors ; ROC Curve

BACKGROUND: Concurrent chemo-radiotherapy (CCRT) is the standard treatment for locally advanced cervical cancer (LACC), but there are still many patients who suffer tumor recurrence. However, valuable predictors of treatment outcomes remain limited. This study aimed to assess the value of the serum immune biomarkers to predict the prognosis. METHODS: We reviewed cervical cancer patients treated with CCRT between January 2014 and May 2018 at Peking Union Medical College Hospital. The systemic immune inflammation index (SII), systemic inflammation response index (SIRI), and lactate dehydrogenase (LDH) were calculated using blood samples. The relationship between immune markers and the treatment outcome was analyzed. The area under the receiver operating characteristic (ROC) curve was used to evaluate the predictive efficiency. The Cox proportional hazards model and log-rank were used to predict overall survival (OS) and disease-free survival (DFS). RESULTS: This study included 667 patients. Among them, 195 (29.2%) patients were defined as treatment failure, including 127 (19.0%) patients with pelvic failure, 94 (14.1%) distant failure, and 25 (3.7%) concurrent pelvic and distant failure. It revealed that the tumor stage, size, metastatic lymph nodes (MLNs), and serum immune biomarkers, such as SII, SIRI, and LDH, were significantly related to treatment outcomes. We demonstrated that the optimal cut-off of the SII, SIRI, and LDH were 970.4 × 10 9 /L, 1.3 × 10 9 /L, and 207.52 U/L, respectively. Importantly, this study presented that LDH level had the highest OR (OR = 4.2; 95% CI [2.3-10.8]). Furthermore, the OS and DFS for patients with pre-SII ≥970.5 × 10 9 /L were significantly worse than those with pre-SII <970.5 × 10 9 /L. Similarly, pre-SIRI ≥1.25 × 10 9 /L and pre-LDH ≥207.5 U/L were related to poor survival outcomes. CONCLUSIONS This study demonstrated that the baseline SII, SIRI, and LDH levels can be used to accurately and effectively predict the treatment outcomes after CCRT and long-term prognosis. Our results may offer additional prognostic information in clinical, which helps to detect the potential recurrent metastasis in time.
Humans ; Female ; Uterine Cervical Neoplasms/drug therapy* ; Middle Aged ; Adult ; Aged ; Chemoradiotherapy/methods* ; L-Lactate Dehydrogenase/blood* ; Treatment Outcome ; Disease-Free Survival ; Prognosis ; ROC Curve ; Biomarkers, Tumor/blood* ; Proportional Hazards Models

OBJECTIVE: To investigate the diagnostic efficacy of ^99mTc-MDP three-phase bone scintigraphy (TPBS) combined with C-reactive protein (CRP) for periprosthetic joint infection (PJI). METHODS: The clinical data of 198 patients who underwent revision surgery of artificial joint between January 2017 and January 2024 and received TPBS examination before surgery were retrospectively analyzed. There were 77 males and 121 females with an average age of 63.74 years ranging from 24 to 92 years. There were 90 cases of hip arthroplasty and 108 cases of knee arthroplasty. PJI was diagnosed according to the 2013 American Musculoskeletal Infection Society (MSIS) standard diagnostic criteria. The sensitivity, specificity, accuracy, negative predictive value (NPV), and positive predict value (PPV) were calculated. The receiver operating characteristic (ROC) curve was used to compare the diagnostic performance of the three methods, and the area under curve (AUC) was used to evaluate the diagnostic performance. RESULTS: According to the 2013 MSIS criteria, 116 cases were diagnosed as PJI, and the remaining 82 cases were aseptic loosening. The cases of PJI diagnosed by TPBS, CRP, and TPBS-CRP were 125, 109, and 137 respectively, and the cases of aseptic loosening were 73, 89, and 61 respectively. The sensitivity, accuracy, NPV, and PPV of TPBS-CRP combination in the diagnosis of PJI were higher than those of TPBS and CRP, but the specificity was lower than that of TPBS and CRP. ROC curve analysis further showed that the AUC value of TPBS-CRP combination was better than that of TPBS and CRP. The severity of bone defect and the duration of symptoms in patients with false positive TPBS diagnosis were worse than those in patients with true negative TPBS diagnosis (P<0.05), but there was no significant difference in the survival time of prosthesis between the two groups (P>0.05). Among the patients diagnosed with PJI by TPBS, CRP, and TPBS-CRP, 49, 35, and 54 patients had received antibiotic treatment 2 weeks before diagnosis, respectively. There was no significant difference in the diagnostic accuracy of TPBS and TPBS-CRP before diagnosis between patients treated with and without antibiotics and those not treated (P>0.05). The diagnostic accuracy of antibiotic therapy before CRP diagnosis was significantly lower than that of untreated patients (P<0.05). CONCLUSION TPBS and CRP have limited specificity in differentiating PJI from aseptic loosening. The TPBS-CRP combination diagnostic method can synergize the local bone metabolic characteristics and systemic inflammatory response to achieve higher diagnostic accuracy, but caution should be exercised in patients with severe bone defects and longer symptom duration.
Humans ; Prosthesis-Related Infections/blood* ; Middle Aged ; Male ; Female ; Aged ; C-Reactive Protein/metabolism* ; Retrospective Studies ; Adult ; Radionuclide Imaging/methods* ; Arthroplasty, Replacement, Knee/adverse effects* ; Aged, 80 and over ; Technetium Tc 99m Medronate ; Arthroplasty, Replacement, Hip/adverse effects* ; Sensitivity and Specificity ; Knee Prosthesis/adverse effects* ; ROC Curve ; Reoperation ; Radiopharmaceuticals ; Young Adult

Objective Based on 25 indicators including immune factors, cell count classification, and smear results of the knee joint fluid, machine learning models were established to distinguish between osteoarthritis (OA) and rheumatoid arthritis (RA). Methods 100 OA and 40 RA patients scheduled for total knee arthroplasty were enrolled respectively. Each patient's knee joint fluid was collected preoperatively. Nucleated cells were counted and classified. The expression levels of immune factors, including tumor necrosis factor alpha (TNF-α), interleukin-1 beta (IL-1β), IL-6, IL-8, IL-15, matrix metalloproteinase 3 (MMP3), MMP9, MMP13, rheumatoid factor (RF), serum amyloid A (SAA), C-reactive protein (CRP), and others were measured. Smears and microscopic classification of all the immune factors were performed. Independent influencing factors for OA or RA were identified using univariate binary logistic regression, Lasso regression, and multivariate binary logistic regression. Based on the independent influencing factors, three machine learning models were constructed which are logistic regression, random forest, and support vector machine. Receiver operating characteristic curve (ROC), calibration curve and decision curve analysis (DCA) were used to evaluate and compare the models. Results A total of 5 indicators in the knee joint fluid were screened out to distinguish OA and RA, which were IL-1β(odds ratio(OR)=10.512, 95× confidence interval (95×CI) was 1.048-105.42, P=0.045), IL-6 (OR=1.007, 95×CI was 1.001-1.014, P=0.022), MMP9 (OR=3.202, 95×CI was 1.235-8.305, P=0.017), MMP13 (OR=1.002, 95× CI was 1-1.004, P=0.049), and RF (OR=1.091, 95×CI was 1.01-1.179, P=0.026). According to the results of ROC, calibration curve and DCA, the accuracy (0.979), sensitivity (0.98) and area under the curve (AUC, 0.996, 95×CI was 0.991-1) of the random forest model were the highest. It has good validity and feasibility, and its distinguishing ability is better than the other two models. Conclusion The machine learning model based on immune factors in the knee joint fluid holds significant value in distinguishing OA and RA. It provides an important reference for the clinical early differential diagnosis, prevention and treatment of OA and RA.
Humans ; Arthritis, Rheumatoid/metabolism* ; Machine Learning ; Male ; Female ; Middle Aged ; Aged ; Synovial Fluid/immunology* ; Osteoarthritis, Knee/metabolism* ; Knee Joint/metabolism* ; ROC Curve ; Diagnosis, Differential

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

Objective To explore the expression of coagulation indexes in rheumatoid arthritis (RA) and dry syndrome (pSS) and their relationships with inflammation and immune function. Methods A total of 61 patients with RA who were hospitalized in the Department of Rheumatology of Anhui Provincial Hospital of Traditional Chinese Medicine from March 12 to September 9, 2024 were selected as the RA group. And 61 patients with pSS who were hospitalized in the Department of Rheumatology of the same hospital September 4, 2023, to August 17, 2024, were selected as the pSS group. 61 healthy individuals who underwent routine medical checkups at the Physical Examination Center of Anhui Provincial Hospital of Traditional Chinese Medicine during the same period were included as the control group. Baseline clinical indexes before treatment were collected from patients in each group, including prothrombin time(PT), international normalized ratio(INR), thrombia time(TT), fibrinogen(FBG), activated partial thromboplastin time(APTT), fibrin (ogen) degradation products(FDP) and D-Dimer(D-D). Results The expression levels of PT, FBG, TT, FDP, and D-D in the RA group, the pSS group, and the normal group were significantly different. The expression levels of PT, FBG, FDP, and D-D in the RA group were all higher than those in the pSS group and the control group, respectively. And the expression level of TT in the pSS group was lower than that in control group. ROC curve analysis showed that the AUC of PT was 0.638, the AUC of FBG was 0.899, the AUC of FDP was 0.866, and the AUC of D-D was 0.919 in the RA group compared with the normal group. And the AUC of coagulation indexes for joint diagnosis of RA was higher than that of the indexes detected individually. pSS group had an AUC of PT of 0.618 compared with that of the normal group. The AUC of TT was 0.645, and the AUC of coagulation indexes for the joint diagnosis of pSS was higher than the AUC of each index detected separately. Association rule analysis showed that elevated D-D in RA patients had a significant correlation with elevated hs-CRP, CCP and RF, and elevated FBG had a significant correlation with elevated hs-CRP, ESR, RF and CCP. Elevated D-D in pSS patients had a correlation with elevated hs-CRP and anti-SSA, and elevated INR has correlation with elevated hs-CRP, anti-SSA and anti-SSB. Correlation analysis showed that PT, INR, FBG, FDP, and D-D were positively correlated with CRP and ESR, and TT was negatively correlated with CRP and ESR in the RA group. FBG, FDP, and D-D were positively correlated with CRP and ESR in the pSS group. Moreover, coagulation indexes were positively correlated with immune indexes in RA group and pSS group which were all significant. The results of multiple linear regression analysis showed that FBG was a positive correlate of hs-CRP and ESR in RA patients. For PSS patients, FBG and FDP were positive correlates of hs-CRP. APTT and FBG were positive correlates of ESR. Conclusion Compared with pSS, coagulation indexes (especially PT, FBG, FDP and D-D) are more informative for the early diagnosis of RA and the judgment of the degree of the disease, and can be used as an important predictor for the confirmation of the diagnosis of RA.
Humans ; Female ; Male ; Arthritis, Rheumatoid/diagnosis* ; Middle Aged ; Fibrin Fibrinogen Degradation Products/analysis* ; Blood Coagulation ; Adult ; Fibrinogen/metabolism* ; Partial Thromboplastin Time ; Prothrombin Time ; Aged ; Inflammation/immunology* ; ROC Curve

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