AutoScore-Survival: Developing interpretable machine learning-based time-to-event scores with right-censored survival data

A universal AutoScore framework to develop interpretable scoring systems for predicting common types of clinical outcomes

The AutoScore framework can automatically generate data-driven clinical scores in various clinical applications. Here, we present a protocol for developing clinical scoring systems for binary, survival, and ordinal outcomes using the open-source AutoScore package. We describe steps for package installation, detailed data processing and checking, and variable ranking. We then explain how to iterate through steps for variable selection, score generation, fine-tuning, and evaluation to generate understandable and explainable scoring systems using data-driven evidence and clinical knowledge. For complete details on the use and execution of this protocol, please refer to Xie et al. (2020),¹ Xie et al. (2022)², Saffari et al. (2022)³ and the online tutorial https://nliulab.github.io/AutoScore/.

Development and Asian-wide validation of the Grade for Interpretable Field Triage (GIFT) for predicting mortality in pre-hospital patients using the Pan-Asian Trauma Outcomes Study (PATOS)

Background

Field triage is critical in injury patients as the appropriate transport of patients to trauma centers is directly associated with clinical outcomes. Several prehospital triage scores have been developed in Western and European cohorts; however, their validity and applicability in Asia remains unclear. Therefore, we aimed to develop and validate an interpretable field triage scoring systems based on a multinational trauma registry in Asia.

Methods

This retrospective and multinational cohort study included all adult transferred injury patients from Korea, Malaysia, Vietnam, and Taiwan between 2016 and 2018. The outcome of interest was a death in the emergency department (ED) after the patients' ED visit. Using these results, we developed the interpretable field triage score with the Korea registry using an interpretable machine learning framework and validated the score externally. The performance of each country's score was assessed using the area under the receiver operating characteristic curve (AUROC). Furthermore, a website for real-world application was developed using R Shiny.

Findings

The study population included 26,294, 9404, 673 and 826 transferred injury patients between 2016 and 2018 from Korea, Malaysia, Vietnam, and Taiwan, respectively. The corresponding rates of a death in the ED were 0.30%, 0.60%, 4.0%, and 4.6% respectively. Age and vital sign were found to be the significant variables for predicting mortality. External validation showed the accuracy of the model with an AUROC of 0.756-0.850.

Interpretation

The Grade for Interpretable Field Triage (GIFT) score is an interpretable and practical tool to predict mortality in field triage for trauma.

Funding

This research was supported by a grant of the Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI), funded by the Ministry of Health & Welfare, Republic of Korea (Grant Number: HI19C1328).

Benchmarking emergency department prediction models with machine learning and public electronic health records

The demand for emergency department (ED) services is increasing across the globe, particularly during the current COVID-19 pandemic. Clinical triage and risk assessment have become increasingly challenging due to the shortage of medical resources and the strain on hospital infrastructure caused by the pandemic. As a result of the widespread use of electronic health records (EHRs), we now have access to a vast amount of clinical data, which allows us to develop prediction models and decision support systems to address these challenges. To date, there is no widely accepted clinical prediction benchmark related to the ED based on large-scale public EHRs. An open-source benchmark data platform would streamline research workflows by eliminating cumbersome data preprocessing, and facilitate comparisons among different studies and methodologies. Based on the Medical Information Mart for Intensive Care IV Emergency Department (MIMIC-IV-ED) database, we created a benchmark dataset and proposed three clinical prediction benchmarks. This study provides future researchers with insights, suggestions, and protocols for managing data and developing predictive tools for emergency care.

A novel interpretable machine learning system to generate clinical risk scores: An application for predicting early mortality or unplanned readmission in a retrospective cohort study

Risk scores are widely used for clinical decision making and commonly generated from logistic regression models. Machine-learning-based methods may work well for identifying important predictors to create parsimonious scores, but such 'black box' variable selection limits interpretability, and variable importance evaluated from a single model can be biased. We propose a robust and interpretable variable selection approach using the recently developed Shapley variable importance cloud (ShapleyVIC) that accounts for variability in variable importance across models. Our approach evaluates and visualizes overall variable contributions for in-depth inference and transparent variable selection, and filters out non-significant contributors to simplify model building steps. We derive an ensemble variable ranking from variable contributions across models, which is easily integrated with an automated and modularized risk score generator, AutoScore, for convenient implementation. In a study of early death or unplanned readmission after hospital discharge, ShapleyVIC selected 6 variables from 41 candidates to create a well-performing risk score, which had similar performance to a 16-variable model from machine-learning-based ranking. Our work contributes to the recent emphasis on interpretability of prediction models for high-stakes decision making, providing a disciplined solution to detailed assessment of variable importance and transparent development of parsimonious clinical risk scores.

AutoScore-Imbalance: An Interpretable Machine Learning Tool for Development of Clinical Scores with Rare Events Data

BACKGROUND

Medical decision-making impacts both individual and public health. Clinical scores are commonly used among various decision-making models to determine the degree of disease deterioration at the bedside. AutoScore was proposed as a useful clinical score generator based on machine learning and a generalized linear model. However, its current framework still leaves room for improvement when addressing unbalanced data of rare events.

METHODS

Using machine intelligence approaches, we developed AutoScore-Imbalance, which comprises three components: training dataset optimization, sample weight optimization, and adjusted AutoScore. Baseline techniques for performance comparison included the original AutoScore, full logistic regression, stepwise logistic regression, least absolute shrinkage and selection operator (LASSO), full random forest, and random forest with a reduced number of variables. These models were evaluated based on their area under the curve (AUC) in the receiver operating characteristic analysis and balanced accuracy (i.e., mean value of sensitivity and specificity). By utilizing a publicly accessible dataset from Beth Israel Deaconess Medical Center, we assessed the proposed model and baseline approaches to predict inpatient mortality.

RESULTS

AutoScore-Imbalance outperformed baselines in terms of AUC and balanced accuracy. The nine-variable AutoScore-Imbalance sub-model achieved the highest AUC of 0.786 (0.732-0.839), while the eleven-variable original AutoScore obtained an AUC of 0.723 (0.663-0.783), and the logistic regression with 21 variables obtained an AUC of 0.743 (0.685-0.800). The AutoScore-Imbalance sub-model (using a down-sampling algorithm) yielded an AUC of 0.771 (0.718-0.823) with only five variables, demonstrating a good balance between performance and variable sparsity. Furthermore, AutoScore-Imbalance obtained the highest balanced accuracy of 0.757 (0.702-0.805), compared to 0.698 (0.643-0.753) by the original AutoScore and the maximum of 0.720 (0.664-0.769) by other baseline models.

CONCLUSIONS

We have developed an interpretable tool to handle clinical data imbalance, presented its structure, and demonstrated its superiority over baselines. The AutoScore-Imbalance tool can be applied to highly unbalanced datasets to gain further insight into rare medical events and facilitate real-world clinical decision-making.

Development and validation of an interpretable machine learning scoring tool for estimating time to emergency readmissions

BACKGROUND

Emergency readmission poses an additional burden on both patients and healthcare systems. Risk stratification is the first step of transitional care interventions targeted at reducing readmission. To accurately predict the short- and intermediate-term risks of readmission and provide information for further temporal risk stratification, we developed and validated an interpretable machine learning risk scoring system.

METHODS

In this retrospective study, all emergency admission episodes from January 1st 2009 to December 31st 2016 at a tertiary hospital in Singapore were assessed. The primary outcome was time to emergency readmission within 90 days post discharge. The Score for Emergency ReAdmission Prediction (SERAP) tool was derived via an interpretable machine learning-based system for time-to-event outcomes. SERAP is six-variable survival score, and takes the number of emergency admissions last year, age, history of malignancy, history of renal diseases, serum creatinine level, and serum albumin level during index admission into consideration.

FINDINGS

A total of 293,589 ED admission episodes were finally included in the whole cohort. Among them, 203,748 episodes were included in the training cohort, 50,937 episodes in the validation cohort, and 38,904 in the testing cohort. Readmission within 90 days was documented in 80,213 (27.3%) episodes, with a median time to emergency readmission of 22 days (Interquartile range: 8-47). For different time points, the readmission rates observed in the whole cohort were 6.7% at 7 days, 10.6% at 14 days, 13.6% at 21 days, 16.4% at 30 days, and 23.0% at 60 days. In the testing cohort, the SERAP achieved an integrated area under the curve of 0.737 (95% confidence interval: 0.730-0.743). For a specific 30-day readmission prediction, SERAP outperformed the LACE index (Length of stay, Acuity of admission, Charlson comorbidity index, and Emergency department visits in past six months) and the HOSPITAL score (Hemoglobin at discharge, discharge from an Oncology service, Sodium level at discharge, Procedure during the index admission, Index Type of admission, number of Admissions during the last 12 months, and Length of stay). Besides 30-day readmission, SERAP can predict readmission rates at any time point during the 90-day period.

INTERPRETATION

Better performance in risk prediction was achieved by the SERAP than other existing scores, and accurate information about time to emergency readmission was generated for further temporal risk stratification and clinical decision-making. In the future, external validation studies are needed to evaluate the SERAP at different settings and assess their real-world performance.

FUNDING

This study was supported by the Singapore National Medical Research Council under the PULSES Center Grant, and Duke-NUS Medical School.