Evaluating live performance of machine learning based prediction models for different clinical risks: a study of live systems in different hospitals (Preprint)

Assessing calibration and bias of a deployed machine learning malnutrition prediction model within a large healthcare system

Malnutrition is a frequently underdiagnosed condition leading to increased morbidity, mortality, and healthcare costs. The Mount Sinai Health System (MSHS) deployed a machine learning model (MUST-Plus) to detect malnutrition upon hospital admission. However, in diverse patient groups, a poorly calibrated model may lead to misdiagnosis, exacerbating health care disparities. We explored the model's calibration across different variables and methods to improve calibration. Data from adult patients admitted to five MSHS hospitals from January 1, 2021 - December 31, 2022, were analyzed. We compared MUST-Plus prediction to the registered dietitian's formal assessment. Hierarchical calibration was assessed and compared between the recalibration sample (N = 49,562) of patients admitted between January 1, 2021 - December 31, 2022, and the hold-out sample (N = 17,278) of patients admitted between January 1, 2023 - September 30, 2023. Statistical differences in calibration metrics were tested using bootstrapping with replacement. Before recalibration, the overall model calibration intercept was -1.17 (95% CI: -1.20, -1.14), slope was 1.37 (95% CI: 1.34, 1.40), and Brier score was 0.26 (95% CI: 0.25, 0.26). Both weak and moderate measures of calibration were significantly different between White and Black patients and between male and female patients. Logistic recalibration significantly improved calibration of the model across race and gender in the hold-out sample. The original MUST-Plus model showed significant differences in calibration between White vs. Black patients. It also overestimated malnutrition in females compared to males. Logistic recalibration effectively reduced miscalibration across all patient subgroups. Continual monitoring and timely recalibration can improve model accuracy.

Machine Learning for Predicting Risk and Prognosis of Acute Kidney Disease in Critically Ill Elderly Patients During Hospitalization: Internet-Based and Interpretable Model Study

BACKGROUND

Acute kidney disease (AKD) affects more than half of critically ill elderly patients with acute kidney injury (AKI), which leads to worse short-term outcomes.

OBJECTIVE

We aimed to establish 2 machine learning models to predict the risk and prognosis of AKD in the elderly and to deploy the models as online apps.

METHODS

Data on elderly patients with AKI (n=3542) and AKD (n=2661) from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database were used to develop 2 models for predicting the AKD risk and in-hospital mortality, respectively. Data collected from Xiangya Hospital of Central South University were for external validation. A bootstrap method was used for internal validation to obtain relatively stable results. We extracted the indicators within 24 hours of the first diagnosis of AKI and the fluctuation range of some indicators, namely delta (day 3 after AKI minus day 1), as features. Six machine learning algorithms were used for modeling; the area under the receiver operating characteristic curve (AUROC), decision curve analysis, and calibration curve for evaluating; Shapley additive explanation (SHAP) analysis for visually interpreting; and the Heroku platform for deploying the best-performing models as web-based apps.

RESULTS

For the model of predicting the risk of AKD in elderly patients with AKI during hospitalization, the Light Gradient Boosting Machine (LightGBM) showed the best overall performance in the training (AUROC=0.844, 95% CI 0.831-0.857), internal validation (AUROC=0.853, 95% CI 0.841-0.865), and external (AUROC=0.755, 95% CI 0.699-0.811) cohorts. In addition, LightGBM performed well for the AKD prognostic prediction in the training (AUROC=0.861, 95% CI 0.843-0.878), internal validation (AUROC=0.868, 95% CI 0.851-0.885), and external (AUROC=0.746, 95% CI 0.673-0.820) cohorts. The models deployed as online prediction apps allowed users to predict and provide feedback to submit new data for model iteration. In the importance ranking and correlation visualization of the model's top 10 influencing factors conducted based on the SHAP value, partial dependence plots revealed the optimal cutoff of some interventionable indicators. The top 5 factors predicting the risk of AKD were creatinine on day 3, sepsis, delta blood urea nitrogen (BUN), diastolic blood pressure (DBP), and heart rate, while the top 5 factors determining in-hospital mortality were age, BUN on day 1, vasopressor use, BUN on day 3, and partial pressure of carbon dioxide (PaCO2).

CONCLUSIONS

We developed and validated 2 online apps for predicting the risk of AKD and its prognostic mortality in elderly patients, respectively. The top 10 factors that influenced the AKD risk and mortality during hospitalization were identified and explained visually, which might provide useful applications for intelligent management and suggestions for future prospective research.

Factors influencing clinician and patient interaction with machine learning-based risk prediction models: a systematic review

Machine learning (ML)-based risk prediction models hold the potential to support the health-care setting in several ways; however, use of such models is scarce. We aimed to review health-care professional (HCP) and patient perceptions of ML risk prediction models in published literature, to inform future risk prediction model development. Following database and citation searches, we identified 41 articles suitable for inclusion. Article quality varied with qualitative studies performing strongest. Overall, perceptions of ML risk prediction models were positive. HCPs and patients considered that models have the potential to add benefit in the health-care setting. However, reservations remain; for example, concerns regarding data quality for model development and fears of unintended consequences following ML model use. We identified that public views regarding these models might be more negative than HCPs and that concerns (eg, extra demands on workload) were not always borne out in practice. Conclusions are tempered by the low number of patient and public studies, the absence of participant ethnic diversity, and variation in article quality. We identified gaps in knowledge (particularly views from under-represented groups) and optimum methods for model explanation and alerts, which require future research.

The Quality and Utility of Artificial Intelligence in Patient Care

BACKGROUND

Artificial intelligence (AI) is increasingly being used in patient care. In the future, physicians will need to understand not only the basic functioning of AI applications, but also their quality, utility, and risks.

METHODS

This article is based on a selective review of the literature on the principles, quality, limitations, and benefits AI applications in patient care, along with examples of individual applications.

RESULTS

The number of AI applications in patient care is rising, with more than 500 approvals in the United States to date. Their quality and utility are based on a number of interdependent factors, including the real-life setting, the type and amount of data collected, the choice of variables used by the application, the algorithms used, and the goal and implementation of each application. Bias (which may be hidden) and errors can arise at all these levels. Any evaluation of the quality and utility of an AI application must, therefore, be conducted according to the scientific principles of evidence-based medicine-a requirement that is often hampered by a lack of transparency.

CONCLUSION

AI has the potential to improve patient care while meeting the challenge of dealing with an ever-increasing surfeit of information and data in medicine with limited human resources. The limitations and risks of AI applications require critical and responsible consideration. This can best be achieved through a combination of scientific.

Recent advances in artificial intelligence, mechanistic models, and speed breeding offer exciting opportunities for precise and accelerated genomics-assisted breeding

Given the challenges of population growth and climate change, there is an urgent need to expedite the development of high-yielding stress-tolerant crop cultivars. While traditional breeding methods have been instrumental in ensuring global food security, their efficiency, precision, and labour intensiveness have become increasingly inadequate to address present and future challenges. Fortunately, recent advances in high-throughput phenomics and genomics-assisted breeding (GAB) provide a promising platform for enhancing crop cultivars with greater efficiency. However, several obstacles must be overcome to optimize the use of these techniques in crop improvement, such as the complexity of phenotypic analysis of big image data. In addition, the prevalent use of linear models in genome-wide association studies (GWAS) and genomic selection (GS) fails to capture the nonlinear interactions of complex traits, limiting their applicability for GAB and impeding crop improvement. Recent advances in artificial intelligence (AI) techniques have opened doors to nonlinear modelling approaches in crop breeding, enabling the capture of nonlinear and epistatic interactions in GWAS and GS and thus making this variation available for GAB. While statistical and software challenges persist in AI-based models, they are expected to be resolved soon. Furthermore, recent advances in speed breeding have significantly reduced the time (3-5-fold) required for conventional breeding. Thus, integrating speed breeding with AI and GAB could improve crop cultivar development within a considerably shorter timeframe while ensuring greater accuracy and efficiency. In conclusion, this integrated approach could revolutionize crop breeding paradigms and safeguard food production in the face of population growth and climate change.