Dementia risks identified by vocal features via telephone conversations: A novel machine learning prediction model.

Background and AimTreatment response to ursodeoxycholic acid may predict the prognosis of patients with primary biliary cholangitis (PBC). Recent studies have suggested the benefits of using machine learning (ML) to forecast complex medical predictions. We aimed to predict treatment response in patients with PBC using ML and pretreatment data.MethodsWe conducted a single‐center retrospective study and collected data from 194 patients with PBC who were followed up for at least 12 months after treatment initiation. Patient data were analyzed with five ML models, namely random forest, extreme gradient boosting (XGB), decision tree, naïve Bayes, or logistic regression, to predict treatment response using the Paris II criteria. The established models were assessed using an out‐of‐sample validation. The area under the curve (AUC) was used to evaluate the efficacy of each algorithm. Overall survival and liver‐related deaths were analyzed using Kaplan–Meier analysis.ResultsCompared to logistic regression (AUC = 0.595, P = 0.0219, 0.031 models), ML analyses showed significantly high AUC in the random forest (AUC = 0.84) and XGB (AUC = 0.83) models; however, the AUC was not significantly high for decision tree (AUC = 0.633) or naïve Bayes (AUC = 0.584) models. Kaplan–Meier analysis showed significantly improved prognoses in patients predicted to achieve the Paris II criteria by XGB (log‐rank = 0.005 and 0.007).ConclusionML algorithms could improve treatment response prediction using pretreatment data, which could lead to better prognoses. In addition, the ML model using XGB could predict the prognosis of patients before treatment initiation.

Clinical prediction rules could help identify children at risk of slowed growth after an episode of diarrheal illness, and these rules may be generalizable to all children, regardless of diarrhea status.

Predicting traditional Chinese medicine constitutions in adults aged ≥ 65 years: A machine learning approach.

Accurate risk assessment of high-risk patients is essential in clinical practice. However, there is no practical method to predict or monitor the prognosis of patients with ST-segment elevation myocardial infarction (STEMI) complicated by hyperuricemia. We aimed to evaluate the performance of different machine learning models for the prediction of 1-year mortality in STEMI patients with hyperuricemia. We compared five machine learning models (logistic regression, k-nearest neighbor, CatBoost, random forest, and XGBoost) with the traditional global (GRACE) risk score for acute coronary event registrations. We registered patients aged >18 years diagnosed with STEMI and hyperuricemia at the Affiliated Hospital of Zunyi Medical University between January 2016 and January 2020. Overall, 656 patients were enrolled (average age, 62.5 ± 13.6 years; 83.6%, male). All patients underwent emergency percutaneous coronary intervention. We evaluated the performance of five machine learning classifiers and the GRACE risk model in predicting 1-year mortality. The area under the curve (AUC) of the six models, including the GRACE risk model, ranged from 0.75 to 0.88. Among all the models, CatBoost had the highest predictive accuracy (0.89), AUC (0.87), precision (0.84), and F1 value (0.44). After hybrid sampling technique optimization, CatBoost had the highest accuracy (0.96), AUC (0.99), precision (0.95), and F1 value (0.97). Machine learning algorithms, especially the CatBoost model, can accurately predict the mortality associated with STEMI complicated by hyperuricemia after a 1-year follow-up.

Although cerebrospinal fluid (CSF) amyloid-β42 peptide (Aβ42) and phosphorylated tau (p-tau) and blood p-tau are valuable for differential diagnosis of Alzheimer's disease (AD) from cognitively normal (CN) there is a lack of validated biomarkers for mild cognitive impairment (MCI). This study sought to determine how plasma and CSF protein markers compared in the characterization of MCI and AD status. This cohort study included Alzheimer's Disease Neuroimaging Initiative (ADNI) participants who had baseline levels of 75 proteins measured commonly in plasma and CSF (257 total, 46 CN, 143 MCI, and 68 AD). Logistic regression, least absolute shrinkage and selection operator (LASSO) and Random Forest (RF) methods were used to identify the protein candidates for the disease classification. We observed that six plasma proteins panel (APOE, AMBP, C3, IL16, IGFBP2, APOD) outperformed the seven CSF proteins panel (VEGFA, HGF, PRL, FABP3, FGF4, CD40, RETN) as well as AD markers (CSF p-tau and Aβ42) to distinguish the MCI from AD [area under the curve (AUC) = 0.75 (plasma proteins), AUC = 0.60 (CSF proteins) and AUC = 0.56 (CSF p-tau and Aβ42)]. Also, these six plasma proteins performed better than the CSF proteins and were in line with CSF p-tau and Aβ42 in differentiating CN versus MCI subjects [AUC = 0.89 (plasma proteins), AUC = 0.85 (CSF proteins) and AUC = 0.89 (CSF p-tau and Aβ42)]. These results were adjusted for age, sex, education, and APOEϵ4 genotype. This study suggests that the combination of 6 plasma proteins can serve as an effective marker for differentiating MCI from AD and CN.

BackgroundMachine learning (ML) gained recent popularity because of its usefulness and applicability in medicine. Surgical specialties utilize ML for patient selection, optimization, and prediction of outcomes.ObjectivesThe aim of the authors of this study is to develop, validate, and compare ML algorithms for prediction of gender-affirming mastectomy complications.MethodsAnalysis of gender-affirming mastectomies performed by the senior author was performed retrospectively. Six ML algorithms were trained and optimized based on a portion of the data and tested on the remainder. Models were compared in accuracy of prediction, sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV). Receiver operating characteristic (ROC) curves were computed for each model, and the area under the curve (AUC) was calculated.ResultsA total of 268 patients comprised the entire dataset, of which 214 were utilized to train the models. Random forest (RF) and K-nearest neighbors demonstrated the highest model accuracies of 92.6%, closely followed by XGBoost with 90.7%, and neural networks and support vector machine with 88.9%. Logistic regression recorded the lowest final accuracy of 87.0%. Sensitivity ranged from 61.90% for the K-nearest neighbors model to 90.48% for the neural networks model, whereas specificity reached 100% in RF and XGBoost. Logistic regression, RF, and support vector machine showed strong PPV and NPV metrics. AUC score was led by RF, at 0.904.ConclusionsRF demonstrated the highest accuracy and AUC, with similarly high specificity value and PPV. Application of ML algorithms may be useful for predicting gender-affirming mastectomy complications and could aid surgeons in patient selection.Level of Evidence: 5 (Therapeutic)

Mild Cognitive Impairment (MCI) is a recognized precursor to Alzheimer's Disease (AD), presenting a significant risk of progression. Early detection and intervention in MCI can potentially slow disease advancement, offering substantial clinical benefits. This study employed radiomics and machine learning methodologies to distinguish between MCI and Normal Cognition (NC) groups. The study included 172 MCI patients and 183 healthy controls from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database, all of whom had 3D-T1 weighted MRI structural images. The cerebellar gray and white matter were segmented automatically using volBrain software, and radiomic features were extracted and screened through Pyradiomics. The screened features were then input into various machine learning models, including Random Forest (RF), Logistic Regression (LR), eXtreme Gradient Boosting (XGBoost), Support Vector Machines (SVM), K Nearest Neighbors (KNN), Extra Trees, Light Gradient Boosting Machine (LightGBM), and Multilayer Perceptron (MLP). Each model was optimized for penalty parameters through 5-fold cross-validation to construct radiomic models. The DeLong test was used to evaluate the performance of different models. The LightGBM model, which utilizes a combination of cerebellar gray and white matter features (comprising eight gray matter and eight white matter features), emerges as the most effective model for radiomics feature analysis. The model demonstrates an Area Under the Curve (AUC) of 0.863 for the training set and 0.776 for the test set. Radiomic features based on the cerebellar gray and white matter, combined with machine learning, can objectively diagnose MCI, which provides significant clinical value for assisted diagnosis.

To apply machine learning to extract radiomics features from thyroid two-dimensional ultrasound (2D-US) combined with contrast-enhanced ultrasound (CEUS) images to classify and predict benign and malignant thyroid nodules, classified according to the Chinese version of the thyroid imaging reporting and data system (C-TIRADS) as category 4. This retrospective study included 313 pathologically diagnosed thyroid nodules (203 malignant and 110 benign). Two 2D-US images and five CEUS key frames ("2nd second after the arrival time" frame, "time to peak" frame, "2nd second after peak" frame, "first-flash" frame, and "second-flash" frame) were selected to manually label the region of interest using the "Labelme" tool. A total of 7 images of each nodule and their annotates were imported into the Darwin Research Platform for radiomics analysis. The datasets were randomly split into training and test cohorts in a 9:1 ratio. Six classifiers, namely, support vector machine, logistic regression, decision tree, random forest (RF), gradient boosting decision tree and extreme gradient boosting, were used to construct and test the models. Performance was evaluated using a receiver operating characteristic curve analysis. The area under the curve (AUC), sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy (ACC), and F1-score were calculated. One junior radiologist and one senior radiologist reviewed the 2D-US image and CEUS videos of each nodule and made a diagnosis. We then compared their AUC and ACC with those of our best model. The AUC of the diagnosis of US, CEUS and US combined CEUS by junior radiologist and senior radiologist were 0.755, 0.750, 0.784, 0.800, 0.873, 0.890, respectively. The RF classifier performed better than the other five, with an AUC of 1 for the training cohort and 0.94 (95% confidence interval 0.88-1) for the test cohort. The sensitivity, specificity, accuracy, PPV, NPV, and F1-score of the RF model in the test cohort were 0.82, 0.93, 0.90, 0.85, 0.92, and 0.84, respectively. The RF model with 2D-US combined with CEUS key frames achieved equivalent performance as the senior radiologist (AUC: 0.94 vs. 0.92, P = 0.798; ACC: 0.90 vs. 0.92) and outperformed the junior radiologist (AUC: 0.94 vs. 0.80, P = 0.039, ACC: 0.90 vs. 0.81) in the test cohort. Our model, based on 2D-US and CEUS key frames radiomics features, had good diagnostic efficacy for thyroid nodules, which are classified as C-TIRADS 4. It shows promising potential in assisting less experienced junior radiologists.

Chronic Hepatitis B (CHB) is a leading cause of liver fibrosis. Accurate and non-invasive diagnosis of liver fibrosis in CHB patients is of critical clinical importance. This study aimed to develop and validate machine learning (ML)-based models for predicting significant liver fibrosis in CHB patients. This retrospective cohort study included 328 CHB patients (225 with non-significant liver fibrosis and 103 with significant liver fibrosis) from 2017 to 2022. Four ML models were constructed based on four selected features identified through the least absolute shrinkage and selection operator (LASSO) regression. Model performance was assessed using the receiver operating characteristic (ROC) curve, and the area under the curve (AUC), accuracy, sensitivity, specificity, and SHapley Additive exPlanations (SHAP) analysis. The random forest (RF) model demonstrated the highest predictive performance, with an AUC of 0.874 (95% CI: 0.813-0.934) in the training set and 0.863 (95% CI: 0.772-0.955) in the test set, outperforming extreme gradient boosting (XGBoost), logistic regression (LR), and support vector machine (SVM). Compared with the traditional fibrosis indices such as aspartate aminotransferase to platelet ratio index (APRI) (AUC = 0.585) and fibrosis-4 (FIB-4) (AUC = 0.633), the RF model (AUC = 0.863) demonstrated significantly higher predictive accuracy. SHAP analysis identified platelet count (PLT) as the most influential predictor in the RF model. The ML-based RF model offers a highly accurate, non-invasive interpretable tool for predicting significant liver fibrosis in patients with CHB, offering potential for clinical application in routine fibrosis risk assessment.

Background: Cardiometabolic syndrome (CMS) poses a significant public health concern. The study aimed to investigate the predictive value of age and CMS for incident Alzheimer’s disease (AD) in women aged≥50. Methods: A cohort of women aged 50-79 (n = 63,117) who participated in the Women’s Health Initiative Observational Study (WHIOS) in 1993-1998, without baseline AD and followed through to March 1, 2019, were analyzed. CMS was defined as having ≥3 of five CMS components: large waist circumference, HBP, elevated triglycerides, elevated glucose, and low HDL-cholesterol. AD was classified by physician-diagnoses of incident AD. Hazards ratios (HR) of AD risk associated with CMS by age were analyzed using Cox’s proportional hazards regression analysis. Machine learning (ML)-XGBoost and Lasso Cox models clustered individuals with low, mild, moderate, and severe risk of incident AD. Results: During a median follow-up of 20 years (range: 3.36 to 23.36 years), 8340 developed incident AD. The incident rate (95%CI) of AD was 8.6 (8.1-9.1) per 1000 person-years (PY) in women with CMS, and 7.0 (6.9-7.2) per 1000 PY in those without CMS (p<0.001). Multivariate Cox’s regression analysis indicated that women with CMS versus non-CMS had significantly higher risks of AD in those aged 50-59 [HR (95%CI): 1.37(1.12-1.68)], followed by in those aged 60-69 [1.26 (1.14-1.40)], but nonsignificant in those aged≥70 [1.00 (0.87-1.14)]. Elevated glucose concentration ranked as the top predictor for AD, followed by triglyceride and HBP. Four levels (low to severe) of AD risk were significantly clustered using ML-XGBoost and Lasso Cox models. Conclusions: Women aged 50-69 with CMS vs those without CMS had significantly higher relative risks of AD, but the risk was not significant in those aged≥70. The application of ML prediction models holds potential promise in the early identification of AD risk among U.S. adults.

This study trained six machine learning models to predict meteorological variables at a tropical location. The models used are: Multiple linear regression, Decision tree, Random forest, Support vector machine, Extreme gradient boosting and Multilayer perceptron. This was with the aim of determining the best machine learning model for weather forecasting in a tropical location. The meteorological variables that were predicted are: Temperature, Solar radiation, Relative humidity and Wind speed. To identify the efficiency and to quantify the predictive capacity of each models, evaluation metrics such as coefficient of determination (R2), mean absolute error (MAE), mean absolute percentage error (MAPE) and mean square error (RMSE) were employed. The best performed model for temperature is the Random Forest which has R2 of 0.93, MAE of 0.78 0C, MAPE of 2.84 % and RMSE of 1.13 0C. Also, the best performed model for solar radiation is the Random Forest having an R2 value of 0.72, MAE of 85.34 W/m2 and RMSE of 19008.45 W/m2. For relative humidity, Random Forest also has the best performance. From the evaluation metrics, it has R2 of 0.92, MAE of 3.41 %, MAPE of 0.75 % and RMSE of 24.71 %. The best performed technique for predicting the wind speed was also the Random Forest having an R2 value of 0.79, MAE of 0.16 m/s and RMSE of 0.044 m/s. The study concluded that the best machine learning model for predicting meteorological variables in a tropical location is the Random Forest.

Although the goal of rectal cancer treatment is to restore gastrointestinal continuity, some patients with rectal cancer develop a permanent stoma (PS) after sphincter-saving operations. Although many studies have identified the risk factors and causes of PS, few have precisely predicted the probability of PS formation before surgery. To validate whether an artificial intelligence model can accurately predict PS formation in patients with rectal cancer after sphincter-saving operations. Patients with rectal cancer who underwent a sphincter-saving operation at Taipei Medical University Hospital between January 1, 2012, and December 31, 2021, were retrospectively included in this study. A machine learning technique was used to predict whether a PS would form after a sphincter-saving operation. We included 19 routinely available preoperative variables in the artificial intelligence analysis. To evaluate the efficiency of the model, 6 performance metrics were utilized: accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiving operating characteristic curve. In our classification pipeline, the data were randomly divided into a training set (80% of the data) and a validation set (20% of the data). The artificial intelligence models were trained using the training dataset, and their performance was evaluated using the validation dataset. Synthetic minority oversampling was used to solve the data imbalance. A total of 428 patients were included, and the PS rate was 13.6% (58/428) in the training set. The logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest, decision tree and light gradient boosting machine (LightGBM) algorithms were employed. The accuracies of the logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest (RF), decision tree (DT) and light gradient boosting machine (LightGBM) models were 70%, 76%, 89%, 93%, 95%, 79% and 93%, respectively. The area under the receiving operating characteristic curve values were 0.79 for the LR model, 0.84 for the GNB, 0.95 for the XGB, 0.95 for the GB, 0.99 for the RF model, 0.79 for the DT model and 0.98 for the LightGBM model. The key predictors that were identified were the distance of the lesion from the anal verge, clinical N stage, age, sex, American Society of Anesthesiologists score, and preoperative albumin and carcinoembryonic antigen levels. Integration of artificial intelligence with available preoperative data can potentially predict stoma outcomes after sphincter-saving operations. Our model exhibited excellent predictive ability and can improve the process of obtaining informed consent.

Objective: Using methylation characteristics of human genes to construct machine learning predictive models for screening cervical cancer and precancerous lesions. Methods: Human DNA methylation detection was performed on 224 cervical exfoliated cell specimens from the Cancer Hospital of the Chinese Academy of Medical Sciences, Tianjin Central Hospital of Gynecology Obstetrics, Xinmi Maternal and Child Health Hospital of Henan Province, West China Second Affiliated Hospital of Sichuan University, and Heping Hospital Affiliated to Changzhi Medical College collected during April 2014 and March 2015. The hypermethylated gene fragments related to cervical cancer were selected by high-density, high-association, and hypermethylated gene fragment screening and the LASSO regression algorithm. Taking cervical intraepithelial neoplasia grade 2 (CIN2) or more severe lesions as the research outcome, machine learning predictive models based on the random forest (RF), naive Bayes (NB), and support vector machine (SVM) algorithm, respectively, were constructed. A total of 144 outpatient specimens were used as the training set and 80 cervical exfoliated cell specimens from women participating in the cervical cancer screening program were used as the test set to verify the predictive models. Using histological diagnosis results as the gold standard, the detection efficacy for CIN2 or more severe lesions of the three machine learning predictive models were compared with that of the human papilloma virus (HPV) detection and cytological diagnosis. Results: In the training set of 144 cases, there were 34 cases of HPV positivity, with a positive rate of 23.61%. Cytologically, there were 37 cases diagnosed as no intraepithelial lesion or malignancy (NILM), and 107 cases diagnosed as atypical squamous cells of undetermined significance (ASC-US) or above. Histologically, there were 28 cases without cervical intraepithelial neoplasia or benign cervical lesions, 31 cases of CIN1, 18 cases of CIN2, 31 cases of CIN3, and 36 cases of squamous cell carcinoma. Seven hypermethylated gene fragments were selected from 45 genes, and three machine learning prediction models based on the RF, NB, and SVM algorithm, respectively, were constructed. In the validation set of 80 cases, there were 28 cases of HPV positivity, with a positive rate of 35.00%. Cytologically, there were 65 cases diagnosed as NILM and 15 cases as ASC-US or above. Histologically, there were 39 cases without cervical intraepithelial neoplasia or benign cervical lesions, 10 cases of CIN1, 10 cases of CIN2, 11 cases of CIN3, and 10 cases of squamous cell carcinoma. In the validation set, the area under the curve (AUC) values of the RF model, NB model, SVM model, HPV detection, and cytological diagnosis of CIN2 or above were 0.90, 0.88, 0.82, 0.68, and 0.45, respectively. The DeLong test showed that there was no statistically significant difference in the AUC values between the RF, NB, and SVM models (all P＞0.05), and the AUC values of the RF and NB models were higher than that of HPV detection (both P＜0.01), and the AUC values of the RF, NB, and SVM models were higher than that of cytological diagnosis (all P＜0.01). Compared with the NB model, the sensitivity of the RF model was similar (80.65% vs. 77.42%), but the specificity of the NB model was much higher than that of the RF model (93.88% vs. 73.47%). Conclusion: Among the machine learning prediction models for cervical cancer and precancerous lesions constructed based on human DNA methylation, the NB model has good predictive performance for CIN2 and above lesions, and may be used for screening of cervical cancer and precancerous lesions.

ObjectivesThis study develops a machine learning model using dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) radiomics and clinical data to preoperatively differentiate hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and hepatic inflammatory pseudotumor (HIPT), addressing limitations of conventional diagnostics.Materials and methodsThis retrospective study included 280 patients (HCC = 160, ICC = 80, HIPT = 40) who underwent DCE-MRI from 2008 to 2024 at three hospitals. Radiomics features and clinical data were extracted and analyzed using LASSO regression and machine learning algorithms (Logistic Regression, Random Forest, and Extreme Gradient Boosting), with class weighting (HCC:ICC:HIPT = 1:2:4) to address class imbalance. Models were compared using macro-average Area Under the Curve (AUC), accuracy, recall, and precision.ResultsThe fusion model, integrating radiomics and clinical features, achieved an AUC of 0.933 (95% CI: 0.91–0.95) and 84.5% accuracy, outperforming radiomics-only (AUC = 0.856, 72.6%) and clinical-only (AUC = 0.795, 66.7%) models (p < 0.05). Rim enhancement is a key model feature for distinguishing HCC from ICC and HIPT, while hepatic lobe atrophy distinguishes ICC and HIPT from HCC.ConclusionThis study developed a novel preoperative imaging-based model to differentiate HCC, ICC, and HIPT. The fusion model performed exceptionally well, demonstrating superior accuracy in ICC identification, significantly outperforming traditional diagnostic methods (e.g., radiology and biomarkers) and single-modality machine learning models (p < 0.05). This noninvasive approach enhances diagnostic precision and supports personalized treatment planning in liver disease management.Critical relevance statementThis study develops a novel preoperative imaging-based machine learning model to differentiate hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and hepatic inflammatory pseudotumor (HIPT), improving diagnostic accuracy and advancing personalized treatment strategies in clinical radiology.Key PointsA machine learning model integrates DCE-MRI radiomics and clinical data for liver lesion differentiation.The fusion model outperforms single-modality models with 0.933 AUC and 84.5% accuracy.This model provides a noninvasive, reliable tool for personalized liver disease diagnosis and treatment planning.Graphical

Alzheimer’s disease (AD) is a degenerative neurological disease that primarily affects the elderly. Drug therapy is the main strategy for AD treatment, but current treatments suffer from poor efficacy and a number of side effects. Non-drug therapy is attracting more attention and may be a better strategy for treatment of AD. Hypoxia is one of the important factors that contribute to the pathogenesis of AD. Multiple cellular processes synergistically promote hypoxia, including aging, hypertension, diabetes, hypoxia/obstructive sleep apnea, obesity, and traumatic brain injury. Increasing evidence has shown that hypoxia may affect multiple pathological aspects of AD, such as amyloid-beta metabolism, tau phosphorylation, autophagy, neuroinflammation, oxidative stress, endoplasmic reticulum stress, and mitochondrial and synaptic dysfunction. Treatments targeting hypoxia may delay or mitigate the progression of AD. Numerous studies have shown that oxygen therapy could improve the risk factors and clinical symptoms of AD. Increasing evidence also suggests that oxygen therapy may improve many pathological aspects of AD including amyloid-beta metabolism, tau phosphorylation, neuroinflammation, neuronal apoptosis, oxidative stress, neurotrophic factors, mitochondrial function, cerebral blood volume, and protein synthesis. In this review, we summarized the effects of oxygen therapy on AD pathogenesis and the mechanisms underlying these alterations. We expect that this review can benefit future clinical applications and therapy strategies on oxygen therapy for AD.