Early and Accurate Prediction of Clinical Response to Methotrexate Treatment in Juvenile Idiopathic Arthritis Using Machine Learning

The emerging paradigm in pediatric rheumatology: harnessing the power of artificial intelligence

Artificial intelligence algorithms, with roots extending into the past but experiencing a resurgence and evolution in recent years due to their superiority over traditional methods and contributions to human capabilities, have begun to make their presence felt in the field of pediatric rheumatology. In the ever-evolving realm of pediatric rheumatology, there have been incremental advancements supported by artificial intelligence in understanding and stratifying diseases, developing biomarkers, refining visual analyses, and facilitating individualized treatment approaches. However, like in many other domains, these strides have yet to gain clinical applicability and validation, and ethical issues remain unresolved. Furthermore, mastering different and novel terminologies appears challenging for clinicians. This review aims to provide a comprehensive overview of the current literature, categorizing algorithms and their applications, thus offering a fresh perspective on the nascent relationship between pediatric rheumatology and artificial intelligence, highlighting both its advancements and constraints.

Machine learning and artificial intelligence within pediatric autoimmune diseases: applications, challenges, future perspective

INTRODUCTION

Autoimmune disorders affect 4.5% to 9.4% of children, significantly reducing their quality of life. The diagnosis and prognosis of autoimmune diseases are uncertain because of the variety of onset and development. Machine learning can identify clinically relevant patterns from vast amounts of data. Hence, its introduction has been beneficial in the diagnosis and management of patients.

AREAS COVERED

This narrative review was conducted through searching various electronic databases, including PubMed, Scopus, and Web of Science. This study thoroughly explores the current knowledge and identifies the remaining gaps in the applications of machine learning specifically in the context of pediatric autoimmune and related diseases.

EXPERT OPINION

Machine learning algorithms have the potential to completely change how pediatric autoimmune disorders are identified, treated, and managed. Machine learning can assist physicians in making more precise and fast judgments, identifying new biomarkers and therapeutic targets, and personalizing treatment strategies for each patient by utilizing massive datasets and powerful analytics.

A machine learning case study to predict rare clinical event of interest: imbalanced data, interpretability, and practical considerations

Accurate prediction of a rare and clinically important event following study treatment has been crucial in drug development. For instance, the rarity of an adverse event is often commensurate with the seriousness of medical consequences, and delayed detection of the rare adverse event can pose significant or even life-threatening health risks to patients. In this machine learning case study, we demonstrate with an example originated from a real clinical trial setting how to define and solve the rare clinical event prediction problem using machine learning in pharmaceutical industry. The unique contributions of this work include the proposal of a six-step investigation framework that facilitates the communication with non-technical stakeholders and the interpretation of the model performance in terms of practical consequences in the context of patient screenings for conducting a future clinical trial. In terms of machine learning methodology, for data splitting into the training and test sets, we adapt the rare-event stratified split approach (from scikit-learn) to further account for group splitting for multiple records of a patient simultaneously. To handle imbalanced data due to rare events in model training, the cost-sensitive learning approach is employed to give more weights to the minor class and the metrics precision together with recall are used to capture prediction performance instead of the raw accuracy rate. Finally, we demonstrate how to apply the state-of-the-art SHAP values to identify important risk factors to improve model interpretability.

Towards stratified treatment of JIA: machine learning identifies subtypes in response to methotrexate from four UK cohorts

BACKGROUND

Methotrexate (MTX) is the gold-standard first-line disease-modifying anti-rheumatic drug for juvenile idiopathic arthritis (JIA), despite only being either effective or tolerated in half of children and young people (CYP). To facilitate stratified treatment of early JIA, novel methods in machine learning were used to i) identify clusters with distinct disease patterns following MTX initiation; ii) predict cluster membership; and iii) compare clusters to existing treatment response measures.

METHODS

Discovery and verification cohorts included CYP who first initiated MTX before January 2018 in one of four UK multicentre prospective cohorts of JIA within the CLUSTER consortium. JADAS components (active joint count, physician (PGA) and parental (PGE) global assessments, ESR) were recorded at MTX start and over the following year. Clusters of MTX 'response' were uncovered using multivariate group-based trajectory modelling separately in discovery and verification cohorts. Clusters were compared descriptively to ACR Pedi 30/90 scores, and multivariate logistic regression models predicted cluster-group assignment.

FINDINGS

The discovery cohorts included 657 CYP and verification cohorts 1241 CYP. Six clusters were identified: Fast improvers (11%), Slow Improvers (16%), Improve-Relapse (7%), Persistent Disease (44%), Persistent PGA (8%) and Persistent PGE (13%), the latter two characterised by improvement in all features except one. Factors associated with clusters included ethnicity, ILAR category, age, PGE, and ESR scores at MTX start, with predictive model area under the curve values of 0.65-0.71. Singular ACR Pedi 30/90 scores at 6 and 12 months could not capture speeds of improvement, relapsing courses or diverging disease patterns.

INTERPRETATION

Six distinct patterns following initiation of MTX have been identified using methods in artificial intelligence. These clusters demonstrate the limitations in traditional yes/no treatment response assessment (e.g., ACRPedi30) and can form the basis of a stratified medicine programme in early JIA.

FUNDING

Medical Research Council, Versus Arthritis, Great Ormond Street Hospital Children's Charity, Olivia's Vision, and the National Institute for Health Research.

Integrating Multi-Omics Data With EHR for Precision Medicine Using Advanced Artificial Intelligence

With the recent advancement of novel biomedical technologies such as high-throughput sequencing and wearable devices, multi-modal biomedical data ranging from multi-omics molecular data to real-time continuous bio-signals are generated at an unprecedented speed and scale every day. For the first time, these multi-modal biomedical data are able to make precision medicine close to a reality. However, due to data volume and the complexity, making good use of these multi-modal biomedical data requires major effort. Researchers and clinicians are actively developing artificial intelligence (AI) approaches for data-driven knowledge discovery and causal inference using a variety of biomedical data modalities. These AI-based approaches have demonstrated promising results in various biomedical and healthcare applications. In this review paper, we summarize the state-of-the-art AI models for integrating multi-omics data and electronic health records (EHRs) for precision medicine. We discuss the challenges and opportunities in integrating multi-omics data with EHRs and future directions. We hope this review can inspire future research and developing in integrating multi-omics data with EHRs for precision medicine.

Machine learning: Predicting hospital length of stay in patients admitted for lupus flares

BACKGROUND

Although rare, severe systemic lupus erythematosus (SLE) flares requiring hospitalization account for most of the direct costs of SLE care. New machine learning (ML) methods may optimize lupus care by predicting which patients will have a prolonged hospital length of stay (LOS). Our study uses a machine learning approach to predict the LOS in patients admitted for lupus flares and assesses which features prolong LOS.

METHODS

Our study sampled 5831 patients admitted for lupus flares from the National Inpatient Sample Database 2016-2018 and collected 90 demographics and comorbidity features. Four machine learning (ML) models were built (XGBoost, Linear Support Vector Machines, K Nearest Neighbors, and Logistic Regression) to predict LOS, and their performance was evaluated using multiple metrics, including accuracy, receiver operator area under the curve (ROC-AUC), precision-recall area under the curve (PR- AUC), and F1-score. Using the highest-performing model (XGBoost), we assessed the feature importance of our input features using Shapley value explanations (SHAP) to rank their impact on LOS.

RESULTS

Our XGB model performed the best with a ROC-AUC of 0.87, PR-AUC of 0.61, an F1 score of 0.56, and an accuracy of 95%. The features with the most significant impact on the model were "the need for a central line," "acute dialysis," and "acute renal failure." Other top features include those related to renal and infectious comorbidities.

CONCLUSION

Our results were consistent with the established literature and showed promise in ML over traditional methods of predictive analyses, even with rare rheumatic events such as lupus flare hospitalizations.

The effect of Shengmai injection in patients with coronary heart disease in real world and its personalized medicine research using machine learning techniques

Objective: Shengmai injection is a common treatment for coronary heart disease. The accurate dose regimen is important to maximize effectiveness and minimize adverse reactions. We aim to explore the effect of Shengmai injection in patients with coronary heart disease based on real-world data and establish a personalized medicine model using machine learning and deep learning techniques. Methods: 211 patients were enrolled. The length of hospital stay was used to explore the effect of Shengmai injection in a case-control study. We applied propensity score matching to reduce bias and Wilcoxon rank sum test to compare results between the experimental group and the control group. Important variables influencing the dose regimen of Shengmai injection were screened by XGBoost. A personalized medicine model of Shengmai injection was established by XGBoost selected from nine algorithm models. SHapley Additive exPlanations and confusion matrix were used to interpret the results clinically. Results: Patients using Shengmai injection had shorter length of hospital stay than those not using Shengmai injection (median 10.00 days vs. 11.00 days, p = 0.006). The personalized medicine model established via XGBoost shows accuracy = 0.81 and AUC = 0.87 in test cohort and accuracy = 0.84 and AUC = 0.84 in external verification. The important variables influencing the dose regimen of Shengmai injection include lipid-lowering drugs, platelet-lowering drugs, levels of GGT, hemoglobin, prealbumin, and cholesterol at admission. Finally, the personalized model shows precision = 75%, recall rate = 83% and F1-score = 79% for predicting 40 mg of Shengmai injection; and precision = 86%, recall rate = 79% and F1-score = 83% for predicting 60 mg of Shengmai injection. Conclusion: This study provides evidence supporting the clinical effectiveness of Shengmai injection, and established its personalized medicine model, which may help clinicians make better decisions.

The prognostic value of whole-genome DNA methylation in response to Leflunomide in patients with Rheumatoid Arthritis

Objective

Although Leflunomide (LEF) is effective in treating rheumatoid arthritis (RA), there are still a considerable number of patients who respond poorly to LEF treatment. Till date, few LEF efficacy-predicting biomarkers have been identified. Herein, we explored and developed a DNA methylation-based predictive model for LEF-treated RA patient prognosis.

Methods

Two hundred forty-five RA patients were prospectively enrolled from four participating study centers. A whole-genome DNA methylation profiling was conducted to identify LEF-related response signatures via comparison of 40 samples using Illumina 850k methylation arrays. Furthermore, differentially methylated positions (DMPs) were validated in the 245 RA patients using a targeted bisulfite sequencing assay. Lastly, prognostic models were developed, which included clinical characteristics and DMPs scores, for the prediction of LEF treatment response using machine learning algorithms.

Results

We recognized a seven-DMP signature consisting of cg17330251, cg19814518, cg20124410, cg21109666, cg22572476, cg23403192, and cg24432675, which was effective in predicting RA patient's LEF response status. In the five machine learning algorithms, the support vector machine (SVM) algorithm provided the best predictive model, with the largest discriminative ability, accuracy, and stability. Lastly, the AUC of the complex model(the 7-DMP scores with the lymphocyte and the diagnostic age) was higher than the simple model (the seven-DMP signature, AUC:0.74 vs 0.73 in the test set).

Conclusion

In conclusion, we constructed a prognostic model integrating a 7-DMP scores with the clinical patient profile to predict responses to LEF treatment. Our model will be able to effectively guide clinicians in determining whether a patient is LEF treatment sensitive or not.

Machine-learning predictive model of pregnancy-induced hypertension in the first trimester

In the first trimester of pregnancy, accurately predicting the occurrence of pregnancy-induced hypertension (PIH) is important for both identifying high-risk women and adopting early intervention. In this study, we used four machine-learning models (LASSO logistic regression, random forest, backpropagation neural network, and support vector machines) to predict the occurrence of PIH in a prospective cohort. Candidate features for predicting the occurrence of middle and late PIH were acquired using a LASSO algorithm. The performance of predictive models was assessed using receiver operating characteristic analysis. Finally, a nomogram was established with the model scores, age, and nulliparity. Calibration, clinical usefulness, and internal validation were used to assess the performance of the nomogram. In the training set (2258 pregnant women), eleven candidate factors in the first trimester were significantly associated with the occurrence of PIH (P < 0.001 in the training set). Four models showed AUCs from 0.780 to 0.816 in the training set. For the validation set (939 pregnant women), AUCs varied from 0.516 to 0.795. The nomogram showed good discrimination, with an AUC of 0.847 (95% CI: 0.805-0.889) in the training set and 0.753 (95% CI: 0.653-0.853) in the validation set. Decision curve analysis suggested that the model was clinically useful. The model developed using LASSO logistic regression achieved the best performance in predicting the occurrence of PIH. The derived nomogram, which incorporates the model score and maternal risk factors, can be used to predict PIH in clinical practice. We develop a model with good performance for clinical prediction of PIH in the first trimester.

Early prediction of acute kidney injury in patients with gastrointestinal bleeding admitted to the intensive care unit based on extreme gradient boosting

Background

Acute kidney injury (AKI) is a common and important complication in patients with gastrointestinal bleeding who are admitted to the intensive care unit. The present study proposes an artificial intelligence solution for acute kidney injury prediction in patients with gastrointestinal bleeding admitted to the intensive care unit.

Methods

Data were collected from the eICU Collaborative Research Database (eICU-CRD) and Medical Information Mart for Intensive Care-IV (MIMIC-IV) database. The prediction model was developed using the extreme gradient boosting (XGBoost) model. The area under the receiver operating characteristic curve, accuracy, precision, area under the precision-recall curve (AUC-PR), and F1 score were used to evaluate the predictive performance of each model.

Results

Logistic regression, XGBoost, and XGBoost with severity scores were used to predict acute kidney injury risk using all features. The XGBoost-based acute kidney injury predictive models including XGBoost and XGBoost+severity scores model showed greater accuracy, recall, precision AUC, AUC-PR, and F1 score compared to logistic regression.

Conclusion

The XGBoost model obtained better risk prediction for acute kidney injury in patients with gastrointestinal bleeding admitted to the intensive care unit than the traditional logistic regression model, suggesting that machine learning (ML) techniques have the potential to improve the development and validation of predictive models in patients with gastrointestinal bleeding admitted to the intensive care unit.

Understanding the role and adoption of artificial intelligence techniques in rheumatology research: An in-depth review of the literature

The major and upward trend in the number of published research related to rheumatic and musculoskeletal diseases, in which artificial intelligence plays a key role, has exhibited the interest of rheumatology researchers in using these techniques to answer their research questions. In this review, we analyse the original research articles that combine both worlds in a five- year period (2017-2021). In contrast to other published papers on the same topic, we first studied the review and recommendation articles that were published during that period, including up to October 2022, as well as the publication trends. Secondly, we review the published research articles and classify them into one of the following categories: disease identification and prediction, disease classification, patient stratification and disease subtype identification, disease progression and activity, treatment response, and predictors of outcomes. Thirdly, we provide a table with illustrative studies in which artificial intelligence techniques have played a central role in more than twenty rheumatic and musculoskeletal diseases. Finally, the findings of the research articles, in terms of disease and/or data science techniques employed, are highlighted in a discussion. Therefore, the present review aims to characterise how researchers are applying data science techniques in the rheumatology medical field. The most immediate conclusions that can be drawn from this work are: multiple and novel data science techniques have been used in a wide range of rheumatic and musculoskeletal diseases including rare diseases; the sample size and the data type used are heterogeneous, and new technical approaches are expected to arrive in the short-middle term.

Comparison and development of machine learning for thalidomide-induced peripheral neuropathy prediction of refractory Crohn’s disease in Chinese population

BACKGROUND

Thalidomide is an effective treatment for refractory Crohn’s disease (CD). However, thalidomide-induced peripheral neuropathy (TiPN), which has a large individual variation, is a major cause of treatment failure. TiPN is rarely predictable and recognized, especially in CD. It is necessary to develop a risk model to predict TiPN occurrence.

AIM

To develop and compare a predictive model of TiPN using machine learning based on comprehensive clinical and genetic variables.

METHODS

A retrospective cohort of 164 CD patients from January 2016 to June 2022 was used to establish the model. The National Cancer Institute Common Toxicity Criteria Sensory Scale (version 4.0) was used to assess TiPN. With 18 clinical features and 150 genetic variables, five predictive models were established and evaluated by the confusion matrix receiver operating characteristic curve (AUROC), area under the precision-recall curve (AUPRC), specificity, sensitivity (recall rate), precision, accuracy, and F1 score.

RESULTS

The top-ranking five risk variables associated with TiPN were interleukin-12 rs1353248 [P = 0.0004, odds ratio (OR): 8.983, 95% confidence interval (CI): 2.497-30.90], dose (mg/d, P = 0.002), brain-derived neurotrophic factor (BDNF) rs2030324 (P = 0.001, OR: 3.164, 95%CI: 1.561-6.434), BDNF rs6265 (P = 0.001, OR: 3.150, 95%CI: 1.546-6.073) and BDNF rs11030104 (P = 0.001, OR: 3.091, 95%CI: 1.525-5.960). In the training set, gradient boosting decision tree (GBDT), extremely random trees (ET), random forest, logistic regression and extreme gradient boosting (XGBoost) obtained AUROC values > 0.90 and AUPRC > 0.87. Among these models, XGBoost and GBDT obtained the first two highest AUROC (0.90 and 1), AUPRC (0.98 and 1), accuracy (0.96 and 0.98), precision (0.90 and 0.95), F1 score (0.95 and 0.98), specificity (0.94 and 0.97), and sensitivity (1). In the validation set, XGBoost algorithm exhibited the best predictive performance with the highest specificity (0.857), accuracy (0.818), AUPRC (0.86) and AUROC (0.89). ET and GBDT obtained the highest sensitivity (1) and F1 score (0.8). Overall, compared with other state-of-the-art classifiers such as ET, GBDT and RF, XGBoost algorithm not only showed a more stable performance, but also yielded higher ROC-AUC and PRC-AUC scores, demonstrating its high accuracy in prediction of TiPN occurrence.

CONCLUSION

The powerful XGBoost algorithm accurately predicts TiPN using 18 clinical features and 14 genetic variables. With the ability to identify high-risk patients using single nucleotide polymorphisms, it offers a feasible option for improving thalidomide efficacy in CD patients.

A Hybrid Generic Framework for Heart Problem Diagnosis Based on a Machine Learning Paradigm

The early, valid prediction of heart problems would minimize life threats and save lives, while lack of prediction and false diagnosis can be fatal. Addressing a single dataset alone to build a machine learning model for the identification of heart problems is not practical because each country and hospital has its own data schema, structure, and quality. On this basis, a generic framework has been built for heart problem diagnosis. This framework is a hybrid framework that employs multiple machine learning and deep learning techniques and votes for the best outcome based on a novel voting technique with the intention to remove bias from the model. The framework contains two consequent layers. The first layer contains simultaneous machine learning models running over a given dataset. The second layer consolidates the outputs of the first layer and classifies them as a second classification layer based on novel voting techniques. Prior to the classification process, the framework selects the top features using a proposed feature selection framework. It starts by filtering the columns using multiple feature selection methods and considers the top common features selected. Results from the proposed framework, with 95.6% accuracy, show its superiority over the single machine learning model, classical stacking technique, and traditional voting technique. The main contribution of this work is to demonstrate how the prediction probabilities of multiple models can be exploited for the purpose of creating another layer for final output; this step neutralizes any model bias. Another experimental contribution is proving the complete pipeline's ability to be retrained and used for other datasets collected using different measurements and with different distributions.

A model based on machine learning for the prediction of cyclosporin A trough concentration in Chinese allo-HSCT patients

BACKGROUND

Cyclosporin A is a calcineurin inhibitor which has a narrow therapeutic window and high interindividual variability. Various population pharmacokinetic models have been reported; however, professional software and technical personnel were needed and the variables of the models were limited. Therefore, the aim of this study was to establish a model based on machine learning to predict CsA trough concentrations in Chinese allo-HSCT patients.

METHODS

A total of 7874 cases of CsA therapeutic drug monitoring data from 2069 allo-HSCT patients were retrospectively included. Sequential forward selection was used to select variable subsets, and eight different algorithms were applied to establish the prediction model.

RESULTS

XGBoost exhibited the highest prediction ability. Except for the variables that were identified by previous studies, some rarely reported variables were found, such as norethindrone, WBC, PAB, and hCRP. The prediction accuracy within ±30% of the actual trough concentration was above 0.80, and the predictive ability of the models was demonstrated to be effective in external validation.

CONCLUSION

In this study, models based on machine learning technology were established to predict CsA levels 3-4 days in advance during the early inpatient phase after HSCT. A new perspective for CsA clinical application is provided.

Tacrolimus in the treatment of childhood nephrotic syndrome: Machine learning detects novel biomarkers and predicts efficacy

STUDY OBJECTIVE

The pharmacokinetics and pharmacodynamics of tacrolimus (TAC) vary greatly among individuals, hindering its precise utilization. Moreover, effective models for the early prediction of TAC efficacy in patients with nephrotic syndrome (NS) are lacking. We aimed to identify key factors affecting TAC efficacy and develop efficacy prediction models for childhood NS using machine learning algorithms.

DESIGN

This was an observational cohort study of patients with pediatric refractory NS.

SETTING

Guangzhou Women and Children's Medical Center between June 2013 and December 2018.

PATIENTS

203 patients with pediatric refractory NS were used for model generation and 35 patients were used for model validation.

INTERVENTION

All patients regularly received double immunosuppressive therapy comprising TAC and low-dose prednisone or methylprednisolone. In this observational cohort study of 203 pediatric patients with refractory NS, clinical and genetic variables, including single-nucleotide polymorphism (SNPs), were identified. TAC efficacy was evaluated 3 months after administration according to two different evaluation criteria: response or non-response (Group 1) and complete remission, partial remission, or non-remission (Group 2).

MEASUREMENTS

Logistic regression, extremely random trees, gradient boosting decision trees, random forest, and extreme gradient boosting algorithms were used to develop and validate the models. Prediction models were validated among a cohort of 35 patients with NS.

MAIN RESULTS

The random forest models performed best in both groups, and the area under the receiver operating characteristics curve of these two models was 80.7% (Group 1) and 80.3% (Group 2). These prediction models included urine erythrocyte count before administration, steroid types, and eight SNPs (ITGB4 rs2290460, TRPC6 rs3824934, CTGF rs9399005, IL13 rs20541, NFKBIA rs8904, NFKBIA rs8016947, MAP3K11 rs7946115, and SMARCAL1 rs11886806).

CONCLUSIONS

Two pre-administration models with good predictive performance for TAC response of patients with NS were developed and validated using machine learning algorithms. These accurate models could assist clinicians in predicting TAC efficacy in pediatric patients with NS before utilization to avoid treatment failure or adverse effects.

An individualized medication model of sodium valproate for patients with bipolar disorder based on machine learning and deep learning techniques

Valproic acid/sodium valproate (VPA) is a widely used anticonvulsant drug for maintenance treatment of bipolar disorders. In order to balance the efficacy and adverse events of VPA treatment, an individualized dose regimen is necessary. This study aimed to establish an individualized medication model of VPA for patients with bipolar disorder based on machine learning and deep learning techniques. The sequential forward selection (SFS) algorithm was applied for selecting a feature subset, and random forest was used for interpolating missing values. Then, we compared nine models using XGBoost, LightGBM, CatBoost, random forest, GBDT, SVM, logistic regression, ANN, and TabNet, and CatBoost was chosen to establish the individualized medication model with the best performance (accuracy = 0.85, AUC = 0.91, sensitivity = 0.85, and specificity = 0.83). Three important variables that correlated with VPA daily dose included VPA TDM value, antipsychotics, and indirect bilirubin. SHapley Additive exPlanations was applied to visually interpret their impacts on VPA daily dose. Last, the confusion matrix presented that predicting a daily dose of 0.5 g VPA had a precision of 55.56% and recall rate of 83.33%, and predicting a daily dose of 1 g VPA had a precision of 95.83% and a recall rate of 85.19%. In conclusion, the individualized medication model of VPA for patients with bipolar disorder based on CatBoost had a good prediction ability, which provides guidance for clinicians to propose the optimal medication regimen.

Age-Stratified Analysis of COVID-19 Outcome Using Machine Learning Predictive Models

Since the emergence of COVID-19, most health systems around the world have experienced a series of spikes in the number of infected patients, leading to collapse of the health systems in many countries. The use of clinical laboratory tests can serve as a discriminatory method for disease severity, defining the profile of patients with a higher risk of mortality. In this paper, we study the results of applying predictive models to data regarding COVID-19 outcome, using three datasets after age stratification of patients. The extreme gradient boosting (XGBoost) algorithm was employed as the predictive method, yielding excellent results. The area under the receiving operator characteristic curve (AUROC) value was 0.97 for the subgroup of patients up to 65 years of age. In addition, SHAP (Shapley additive explanations) was used to analyze the feature importance in the resulting models.

Predicting Lapatinib Dose Regimen Using Machine Learning and Deep Learning Techniques Based on a Real-World Study

Lapatinib is used for the treatment of metastatic HER2(+) breast cancer. We aim to establish a prediction model for lapatinib dose using machine learning and deep learning techniques based on a real-world study. There were 149 breast cancer patients enrolled from July 2016 to June 2017 at Fudan University Shanghai Cancer Center. The sequential forward selection algorithm based on random forest was applied for variable selection. Twelve machine learning and deep learning algorithms were compared in terms of their predictive abilities (logistic regression, SVM, random forest, Adaboost, XGBoost, GBDT, LightGBM, CatBoost, TabNet, ANN, Super TML, and Wide&Deep). As a result, TabNet was chosen to construct the prediction model with the best performance (accuracy = 0.82 and AUC = 0.83). Afterward, four variables that strongly correlated with lapatinib dose were ranked via importance score as follows: treatment protocols, weight, number of chemotherapy treatments, and number of metastases. Finally, the confusion matrix was used to validate the model for a dose regimen of 1,250 mg lapatinib (precision = 81% and recall = 95%), and for a dose regimen of 1,000 mg lapatinib (precision = 87% and recall = 64%). To conclude, we established a deep learning model to predict lapatinib dose based on important influencing variables selected from real-world evidence, to achieve an optimal individualized dose regimen with good predictive performance.

A Prediction Model for Tacrolimus Daily Dose in Kidney Transplant Recipients With Machine Learning and Deep Learning Techniques

Tacrolimus is a major immunosuppressor against post-transplant rejection in kidney transplant recipients. However, the narrow therapeutic index of tacrolimus and considerable variability among individuals are challenges for therapeutic outcomes. The aim of this study was to compare different machine learning and deep learning algorithms and establish individualized dose prediction models by using the best performing algorithm. Therefore, among the 10 commonly used algorithms we compared, the TabNet algorithm outperformed other algorithms with the highest R² (0.824), the lowest prediction error [mean absolute error (MAE) 0.468, mean square error (MSE) 0.558, and root mean square error (RMSE) 0.745], and good performance of overestimated (5.29%) or underestimated dose percentage (8.52%). In the final prediction model, the last tacrolimus daily dose, the last tacrolimus therapeutic drug monitoring value, time after transplantation, hematocrit, serum creatinine, aspartate aminotransferase, weight, CYP3A5, body mass index, and uric acid were the most influential variables on tacrolimus daily dose. Our study provides a reference for the application of deep learning technique in tacrolimus dose estimation, and the TabNet model with desirable predictive performance is expected to be expanded and applied in future clinical practice.

A machine-learning-based prediction method for easy COPD classification based on pulse oximetry clinical use

Chronic Obstructive Pulmonary Disease (COPD) is a progressive, obstructive lung disease that restricts airflow from the lungs. COPD patients are at risk of sudden and acute worsening of symptoms called exacerbations. Early identification and classification of COPD exacerbation can reduce COPD risks and improve patient’s healthcare and management. Pulse oximetry is a non-invasive technique used to assess patients with acutely worsening symptoms. As part of manual diagnosis based on pulse oximetry, clinicians examine three warning signs to classify COPD patients. This may lack high sensitivity and specificity which requires a blood test. However, laboratory tests require time, further delayed treatment and additional costs. This research proposes a prediction method for COPD patients’ classification based on pulse oximetry three manual warning signs and the resulting derived few key features that can be obtained in a short time. The model was developed on a robust physician labeled dataset with clinically diverse patient cases. Five classification algorithms were applied on the mentioned dataset and the results showed that the best algorithm is XGBoost with the accuracy of 91.04%, precision of 99.86%, recall of 82.19%, F1 measure value of 90.05% with an AUC value of 95.8%. Age, current and baseline heart rate, current and baseline pulse ox. (SPO2) were found the top most important predictors. These findings suggest the strength of XGBoost model together with the availability and the simplicity of input variables in classifying COPD daily living using a (wearable) pulse oximeter.

A Machine Learning Approach for Predicting Sustained Remission in Rheumatoid Arthritis Patients on Biologic Agents

METHODS

In this longitudinal study, patients with RA who started a biological disease-modifying antirheumatic drug (bDMARD) in a tertiary care center were analyzed. Demographic and clinical characteristics were collected at treatment baseline, 12-month, and 24-month follow-up. A wrapper feature selection algorithm was used to determine an attribute core set. Four different ML algorithms, namely, LR, random forest, K-nearest neighbors, and extreme gradient boosting, were then trained and validated with 10-fold cross-validation to predict 24-month sustained DAS28 (Disease Activity Score on 28 joints) remission. The performances of the algorithms were then compared assessing accuracy, precision, and recall.

RESULTS

Our analysis included 367 patients (female 323/367, 88%) with mean age ± SD of 53.7 ± 12.5 years at bDMARD baseline. Sustained DAS28 remission was achieved by 175 (47.2%) of 367 patients. The attribute core set used to train algorithms included acute phase reactant levels, Clinical Disease Activity Index, Health Assessment Questionnaire-Disability Index, as well as several clinical characteristics. Extreme gradient boosting showed the best performance (accuracy, 72.7%; precision, 73.2%; recall, 68.1%), outperforming random forest (accuracy, 65.9%; precision, 65.6%; recall, 59.3%), LR (accuracy, 64.9%; precision, 62.6%; recall, 61.9%), and K-nearest neighbors (accuracy, 63%; precision, 61.5%; recall, 54.8%).

CONCLUSIONS

We showed that ML models can be used to predict sustained remission in RA patients on bDMARDs. Furthermore, our method only relies on a few easy-to-collect patient attributes. Our results are promising but need to be tested on longitudinal cohort studies.

Supervised Machine Learning for Predicting Length of Stay After Lumbar Arthrodesis: A Comprehensive Artificial Intelligence Approach

INTRODUCTION

Few studies have evaluated the utility of machine learning techniques to predict and classify outcomes, such as length of stay (LOS), for lumbar fusion patients. Six supervised machine learning algorithms may be able to predict and classify whether a patient will experience a short or long hospital LOS after lumbar fusion surgery with a high degree of accuracy.

METHODS

Data were obtained from the National Surgical Quality Improvement Program between 2009 and 2018. Demographic and comorbidity information was collected for patients who underwent anterior, anterolateral, or lateral transverse process technique arthrodesis procedure; anterior lumbar interbody fusion (ALIF); posterior, posterolateral, or lateral transverse process technique arthrodesis procedure; posterior lumbar interbody fusion/transforaminal lumbar interbody fusion (PLIF/TLIF); and posterior fusion procedure posterior spine fusion (PSF). Machine learning algorithmic analyses were done with the scikit-learn package in Python on a high-performance computing cluster. In the total sample, 85% of patients were used for training the models, whereas the remaining patients were used for testing the models. C-statistic area under the curve and prediction accuracy (PA) were calculated for each of the models to determine their accuracy in correctly classifying the test cases.

RESULTS

In total, 12,915 ALIF patients, 27,212 PLIF/TLIF patients, and 23,406 PSF patients were included in the algorithmic analyses. The patient factors most strongly associated with LOS were sex, ethnicity, dialysis, and disseminated cancer. The machine learning algorithms yielded area under the curve values of between 0.673 and 0.752 (PA: 69.6% to 80.1%) for ALIF, 0.673 and 0.729 (PA: 66.0% to 81.3%) for PLIF/TLIF, and 0.698 and 0.749 (PA: 69.9% to 80.4%) for PSF.

CONCLUSION

Machine learning classification algorithms were able to accurately predict long LOS for ALIF, PLIF/TLIF, and PSF patients. Supervised machine learning algorithms may be useful in clinical and administrative settings. These data may additionally help inform predictive analytic models and assist in setting patient expectations.

LEVEL III

Diagnostic study, retrospective cohort study.

Prediction of Tacrolimus Dose/Weight-Adjusted Trough Concentration in Pediatric Refractory Nephrotic Syndrome: A Machine Learning Approach

Purpose

Tacrolimus (TAC) is a first-line immunosuppressant for patients with refractory nephrotic syndrome (NS). However, there is a high inter-patient variability of TAC pharmacokinetics, thus therapeutic drug monitoring (TDM) is required. In this study, we aimed to employ machine learning algorithms to investigate the impact of clinical and genetic variables on the TAC dose/weight-adjusted trough concentration (C₀/D) in Chinese children with refractory NS, and then develop and validate the TAC C₀/D prediction models.

Patients and Methods

The association of 82 clinical variables and 244 single nucleotide polymorphisms (SNPs) with TAC C₀/D in the third month since TAC treatment was examined in 171 children with refractory NS. Extremely randomized trees (ET), gradient boosting decision tree (GBDT), random forest (RF), extreme gradient boosting (XGBoost), and Lasso regression were carried out to establish and validate prediction models, respectively. The best prediction models were validated on a cohort of 30 refractory NS patients.

Results

GBDT algorithm performed best in the whole group (R²=0.444, MSE=591.032, MAE=20.782, MedAE=18.980) and CYP3A5 nonexpresser group (R²=0.264, MSE=477.948, MAE=18.119, MedAE=18.771), while ET algorithm performed best in the CYP3A5 expresser group (R²=0.380, MSE=1839.459, MAE=31.257, MedAE=19.399). These prediction models included 3 clinical variables (ALB0, AGE0, and gender) and 10 SNPs (ACTN4 rs3745859, ACTN4 rs56113315, ACTN4 rs62121818, CTLA4 rs4553808, CYP3A5 rs776746, IL2RA rs12722489, INF2 rs1128880, MAP3K11 rs7946115, MYH9 rs2239781, and MYH9 rs4821478).

Conclusion

The association between the clinical and genetic variables and TAC C₀/D was described, and three TAC C₀/D prediction models integrating clinical and genetic variables were developed and validated using machine learning, which may support individualized TAC dosing.

The inclusion of augmented intelligence in medicine: A framework for successful implementation

Artificial intelligence (AI) algorithms are being applied across a large spectrum of everyday life activities. The implementation of AI algorithms in clinical practice has been met with some skepticism and concern, mainly because of the uneasiness that stems, in part, from a lack of understanding of how AI operates, together with the role of physicians and patients in the decision-making process; uncertainties regarding the reliability of the data and the outcomes; as well as concerns regarding the transparency, accountability, liability, handling of personal data, and monitoring and system upgrades. In this viewpoint, we take these issues into consideration and offer an integrated regulatory framework to AI developers, clinicians, researchers, and regulators, aiming to facilitate the adoption of AI that rests within the FDA’s pathway, in research, development, and clinical medicine.

•

Concerns hamper the implementation of augmented intelligence in clinical practice

•

Transparency and external validation increase trust in developed algorithms

•

A regulatory framework is needed for adoption of augmented intelligence in medicine

Prediction of endotracheal tube size in pediatric patients: Development and validation of machine learning models

OBJECTIVE

We aimed to construct and validate machine learning models for endotracheal tube (ETT) size prediction in pediatric patients.

METHODS

Data of 990 pediatric patients underwent endotracheal intubation were retrospectively collected between November 2019 and October 2021, and separated into cuffed and uncuffed endotracheal tube subgroups. Six machine learning algorithms, including support vector regression (SVR), logistic regression (LR), random forest (RF), gradient boosting tree (GBR), decision tree (DTR) and extreme gradient boosting tree (XGBR), were selected to construct and validate models using ten-fold cross validation in training set. The optimal models were selected, and the performance were compared with traditional predictive formulas and clinicians. Furthermore, additional data of 71 pediatric patients were collected to perform external validation.

RESULTS

The optimal 7 uncuffed and 5 cuffed variables were screened out by feature selecting. The RF models had the best performance with minimizing prediction error for both uncuffed ETT size (MAE = 0.275 mm and RMSE = 0.349 mm) and cuffed ETT size (MAE = 0.243 mm and RMSE = 0.310 mm). The RF models were also superior in predicting power than formulas in both uncuffed and cuffed ETT size prediction. In addition, the RF models performed slightly better than senior clinicians, while they significantly outperformed junior clinicians. Based on SVR models, we proposed 3 novel linear formulas for uncuffed and cuffed ETT size respectively.

CONCLUSION

We have developed machine learning models with excellent performance in predicting optimal ETT size in both cuffed and uncuffed endotracheal intubation in pediatric patients, which provides powerful decision support for clinicians to select proper ETT size. Novel formulas proposed based on machine learning models also have relatively better predictive performance. These models and formulas can serve as important clinical references for clinicians, especially for performers with rare experience or in remote areas.

Machine Learning in Rheumatic Diseases

With advances in information technology, the demand for using data science to enhance healthcare and disease management is rapidly increasing. Among these technologies, machine learning (ML) has become ubiquitous and indispensable for solving complex problems in many scientific fields, including medical science. ML allows the development of guidelines and framing of the evaluation system for complex diseases based on massive data. In the analysis of rheumatic diseases, which are chronic and remarkably heterogeneous, ML can be anticipated to be extremely helpful in deciphering and revealing the inherent interrelationships in disease development and progression, which can further enhance the overall understanding of the disease, optimize patients' stratification, calibrate therapeutic strategies, and predict prognosis and outcomes. In this review, the basics of ML, its potential clinical applications in rheumatology, together with its strengths and limitations are summarized.

Early Prediction of Tacrolimus-Induced Tubular Toxicity in Pediatric Refractory Nephrotic Syndrome Using Machine Learning

Background and Aims: Tacrolimus(TAC)-induced nephrotoxicity, which has a large individual variation, may lead to treatment failure or even the end-stage renal disease. However, there is still a lack of effective models for the early prediction of TAC-induced nephrotoxicity, especially in nephrotic syndrome(NS). We aimed to develop and validate a predictive model of TAC-induced tubular toxicity in children with NS using machine learning based on comprehensive clinical and genetic variables. Materials and Methods: A retrospective cohort of 218 children with NS admitted between June 2013 and December 2018 was used to establish the models, and 11 children were prospectively enrolled for external validation. We screened 47 clinical features and 244 genetic variables. The changes in urine N- acetyl- β-D- glucosaminidase(NAG) levels before and after administration was used as an indicator of renal tubular toxicity. Results: Five machine learning algorithms, including extreme gradient boosting (XGBoost), gradient boosting decision tree (GBDT), extremely random trees (ET), random forest (RF), and logistic regression (LR) were used for model generation and validation. Four genetic variables, including TRPC6 rs3824934_GG, HSD11B1 rs846910_AG, MAP2K6 rs17823202_GG, and SCARB2 rs6823680_CC were incorporated into the final model. The XGBoost model has the best performance: sensitivity 75%, specificity 77.8%, accuracy 77.3%, and AUC 78.9%. Conclusion: A pre-administration model with good performance for predicting TAC-induced nephrotoxicity in NS was developed and validated using machine learning based on genetic factors. Physicians can estimate the possibility of nephrotoxicity in NS patients using this simple and accurate model to optimize treatment regimen before administration or to intervene in time after administration to avoid kidney damage.

Machine Learning Applied to Clinical Laboratory Data in Spain for COVID-19 Outcome Prediction: Model Development and Validation

BACKGROUND

The COVID-19 pandemic is probably the greatest health catastrophe of the modern era. Spain's health care system has been exposed to uncontrollable numbers of patients over a short period, causing the system to collapse. Given that diagnosis is not immediate, and there is no effective treatment for COVID-19, other tools have had to be developed to identify patients at the risk of severe disease complications and thus optimize material and human resources in health care. There are no tools to identify patients who have a worse prognosis than others.

OBJECTIVE

This study aimed to process a sample of electronic health records of patients with COVID-19 in order to develop a machine learning model to predict the severity of infection and mortality from among clinical laboratory parameters. Early patient classification can help optimize material and human resources, and analysis of the most important features of the model could provide more detailed insights into the disease.

METHODS

After an initial performance evaluation based on a comparison with several other well-known methods, the extreme gradient boosting algorithm was selected as the predictive method for this study. In addition, Shapley Additive Explanations was used to analyze the importance of the features of the resulting model.

RESULTS

After data preprocessing, 1823 confirmed patients with COVID-19 and 32 predictor features were selected. On bootstrap validation, the extreme gradient boosting classifier yielded a value of 0.97 (95% CI 0.96-0.98) for the area under the receiver operator characteristic curve, 0.86 (95% CI 0.80-0.91) for the area under the precision-recall curve, 0.94 (95% CI 0.92-0.95) for accuracy, 0.77 (95% CI 0.72-0.83) for the F-score, 0.93 (95% CI 0.89-0.98) for sensitivity, and 0.91 (95% CI 0.86-0.96) for specificity. The 4 most relevant features for model prediction were lactate dehydrogenase activity, C-reactive protein levels, neutrophil counts, and urea levels.

CONCLUSIONS

Our predictive model yielded excellent results in the differentiating among patients who died of COVID-19, primarily from among laboratory parameter values. Analysis of the resulting model identified a set of features with the most significant impact on the prediction, thus relating them to a higher risk of mortality.

Complex Machine-Learning Algorithms and Multivariable Logistic Regression on Par in the Prediction of Insufficient Clinical Response to Methotrexate in Rheumatoid Arthritis

The goals of this study were to examine whether machine-learning algorithms outperform multivariable logistic regression in the prediction of insufficient response to methotrexate (MTX); secondly, to examine which features are essential for correct prediction; and finally, to investigate whether the best performing model specifically identifies insufficient responders to MTX (combination) therapy. The prediction of insufficient response (3-month Disease Activity Score 28-Erythrocyte-sedimentation rate (DAS28-ESR) > 3.2) was assessed using logistic regression, least absolute shrinkage and selection operator (LASSO), random forest, and extreme gradient boosting (XGBoost). The baseline features of 355 rheumatoid arthritis (RA) patients from the “treatment in the Rotterdam Early Arthritis CoHort” (tREACH) and the U-Act-Early trial were combined for analyses. The model performances were compared using area under the curve (AUC) of receiver operating characteristic (ROC) curves, 95% confidence intervals (95% CI), and sensitivity and specificity. Finally, the best performing model following feature selection was tested on 101 RA patients starting tocilizumab (TCZ)-monotherapy. Logistic regression (AUC = 0.77 95% CI: 0.68–0.86) performed as well as LASSO (AUC = 0.76, 95% CI: 0.67–0.85), random forest (AUC = 0.71, 95% CI: 0.61 = 0.81), and XGBoost (AUC = 0.70, 95% CI: 0.61–0.81), yet logistic regression reached the highest sensitivity (81%). The most important features were baseline DAS28 (components). For all algorithms, models with six features performed similarly to those with 16. When applied to the TCZ-monotherapy group, logistic regression’s sensitivity significantly dropped from 83% to 69% (p = 0.03). In the current dataset, logistic regression performed equally well compared to machine-learning algorithms in the prediction of insufficient response to MTX. Models could be reduced to six features, which are more conducive for clinical implementation. Interestingly, the prediction model was specific to MTX (combination) therapy response.

A Machine Learning Based Dose Prediction of Lutein Supplements for Individuals With Eye Fatigue

Purpose: Nutritional intervention was always implemented based on "one-size-fits-all" recommendation instead of personalized strategy. We aimed to develop a machine learning based model to predict the optimal dose of a botanical combination of lutein ester, zeaxanthin, extracts of black currant, chrysanthemum, and goji berry for individuals with eye fatigue. Methods: 504 features, including demographic, anthropometrics, eye-related indexes, blood biomarkers, and dietary habits, were collected at baseline from 303 subjects in a randomized controlled trial. An aggregated score of visual health (VHS) was developed from total score of eye fatigue symptoms, visuognosis persistence, macular pigment optical density, and Schirmer test to represent an overall eye fatigue level. VHS at 45 days after intervention was predicted by XGBoost algorithm using all features at baseline to show the eye fatigue improvement. Optimal dose of the combination was chosen based on the predicted VHS. Results: After feature selection and parameter optimization, a model was trained and optimized with a Pearson's correlation coefficient of 0.649, 0.638, and 0.685 in training, test and validation set, respectively. After removing the features collected by invasive blood test and costly optical coherence tomography, the model remained good performance. Among 58 subjects in test and validation sets, 39 should take the highest dose as the optimal option, 17 might take a lower dose, while 2 could not benefit from the combination. Conclusion: We applied XGBoost algorithm to develop a model which could predict optimized dose of the combination to provide personalized nutrition solution for individuals with eye fatigue.

Personalized prediction of delayed graft function for recipients of deceased donor kidney transplants with machine learning

Machine learning (ML) has shown its potential to improve patient care over the last decade. In organ transplantation, delayed graft function (DGF) remains a major concern in deceased donor kidney transplantation (DDKT). To this end, we harnessed ML to build personalized prognostic models to predict DGF. Registry data were obtained on adult DDKT recipients for model development (n = 55,044) and validation (n = 6176). Incidence rates of DGF were 25.1% and 26.3% for the development and validation sets, respectively. Twenty-six predictors were identified via recursive feature elimination with random forest. Five widely-used ML algorithms-logistic regression (LR), elastic net, random forest, artificial neural network (ANN), and extreme gradient boosting (XGB) were trained and compared with a baseline LR model fitted with previously identified risk factors. The new ML models, particularly ANN with the area under the receiver operating characteristic curve (ROC-AUC) of 0.732 and XGB with ROC-AUC of 0.735, exhibited superior performance to the baseline model (ROC-AUC = 0.705). This study demonstrates the use of ML as a viable strategy to enable personalized risk quantification for medical applications. If successfully implemented, our models may aid in both risk quantification for DGF prevention clinical trials and personalized clinical decision making.

Early Prediction of Clinical Response to Etanercept Treatment in Juvenile Idiopathic Arthritis Using Machine Learning

Background and Aims

At present, there is a lack of simple and reliable model for early prediction of the efficacy of etanercept in the treatment of juvenile idiopathic arthritis (JIA). This study aimed to generate and validate prediction models of etanercept efficacy in patients with JIA before administration using machine learning algorithms based on electronic medical record (EMR).

Materials and Methods

EMR data of 87 JIA patients treated with etanercept between January 2011 and December 2018 were collected retrospectively. The response of etanercept was evaluated by using DAS44/ESR-3 simplified standard. The stepwise forward and backward method based on information gain was applied to select features. Five machine learning algorithms, including Extreme Gradient Boosting (XGBoost), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), Extremely Random Trees (ET) and Logistic Regression (LR) were used for model generation and validation with fifty-fold stratified cross-validation. EMR data of additional 14 patients were collected for external validation of the model.

Results

Tender joint count (TJC), Time interval, Lymphocyte percentage (LYM), and Weight were screened out and included in the final model. The model generated by the XGBoost algorithm based on the above 4 features had the best predictive performance: sensitivity 75%, specificity 66.67%, accuracy 72.22%, AUC 79.17%, respectively.

Conclusion

A pre-administration model with good prediction performance for etanercept response in JIA was developed using advanced machine learning algorithms. Clinicians and pharmacists can use this simple and accurate model to predict etanercept response of JIA early and avoid treatment failure or adverse effects.

Machine learning versus conventional clinical methods in guiding management of heart failure patients-a systematic review

Machine learning (ML) algorithms “learn” information directly from data, and their performance improves proportionally with the number of high-quality samples. The aim of our systematic review is to present the state of the art regarding the implementation of ML techniques in the management of heart failure (HF) patients. We manually searched MEDLINE and Cochrane databases as well the reference lists of the relevant review studies and included studies. Our search retrieved 122 relevant studies. These studies mainly refer to (a) the role of ML in the classification of HF patients into distinct categories which may require a different treatment strategy, (b) discrimination of HF patients from the healthy population or other diseases, (c) prediction of HF outcomes, (d) identification of HF patients from electronic records and identification of HF patients with similar characteristics who may benefit form a similar treatment strategy, (e) supporting the extraction of important data from clinical notes, and (f) prediction of outcomes in HF populations with implantable devices (left ventricular assist device, cardiac resynchronization therapy). We concluded that ML techniques may play an important role for the efficient construction of methodologies for diagnosis, management, and prediction of outcomes in HF patients.

XGBoost, a Machine Learning Method, Predicts Neurological Recovery in Patients with Cervical Spinal Cord Injury

The accurate prediction of neurological outcomes in patients with cervical spinal cord injury (SCI) is difficult because of heterogeneity in patient characteristics, treatment strategies, and radiographic findings. Although machine learning algorithms may increase the accuracy of outcome predictions in various fields, limited information is available on their efficacy in the management of SCI. We analyzed data from 165 patients with cervical SCI, and extracted important factors for predicting prognoses. Extreme gradient boosting (XGBoost) as a machine learning model was applied to assess the reliability of a machine learning algorithm to predict neurological outcomes compared with that of conventional methodology, such as a logistic regression or decision tree. We used regularly obtainable data as predictors, such as demographics, magnetic resonance variables, and treatment strategies. Predictive tools, including XGBoost, a logistic regression, and a decision tree, were applied to predict neurological improvements in the functional motor status (ASIA [American Spinal Injury Association] Impairment Scale [AIS] D and E) 6 months after injury. We evaluated predictive performance, including accuracy and the area under the receiver operating characteristic curve (AUC). Regarding predictions of neurological improvements in patients with cervical SCI, XGBoost had the highest accuracy (81.1%), followed by the logistic regression (80.6%) and the decision tree (78.8%). Regarding AUC, the logistic regression showed 0.877, followed by XGBoost (0.867) and the decision tree (0.753). XGBoost reliably predicted neurological alterations in patients with cervical SCI. The utilization of predictive machine learning algorithms may enhance personalized management choices through pre-treatment categorization of patients.