Key result
Machine learning of telemonitored vitals predicts heart failure decompensation with modest accuracy of ~0.69 AUC.
Why the study?
Intervening before cardiac decompensation events in chronic heart failure patients is a major clinical challenge requiring timely and accurate prediction methods.
Does an artificial intelligence model based on telemonitored data accurately predict cardiac decompensation events in patients with chronic heart failure?
Observational (n=488)
No
Does an artificial intelligence model based on telemonitored data accurately predict cardiac decompensation events in patients with chronic heart failure?
An AI model using telemonitored vital signs and questionnaire data can predict heart failure decompensation events with moderate accuracy (AUC 0.69).
Answers are grounded in this paper and cite their sources.
AI models using telemonitored data may aid early CDE prediction but should not yet change practice; leaves open need for prospective validation.
Cardiovascular diseases are the leading cause of death globally, taking an estimated 17.9 million lives each year. Heart failure (HF) occurs when the heart is not able to pump enough blood to satisfy metabolic needs. People diagnosed with chronic HF may suffer from cardiac decompensation events (CDEs), which cause patients' worsening. Being able to intervene before decompensation occurs is the major challenge addressed in this study. The aim of this study is to exploit available patient data to develop an artificial intelligence (AI) model capable of predicting the risk of CDEs timely and accurately. Materials and Methods: The vital variables of patients (n = 488) diagnosed with chronic heart failure were monitored between 2014 and 2022. Several supervised classification models were trained with these monitoring data to predict CDEs, using clinicians' annotations as the gold standard. Feature extraction methods were applied to identify significant variables. Results: The XGBoost classifier achieved an AUC of 0.72 in the cross-validation process and 0.69 in the testing set. The most predictive physiological variables for CAE decompensations are weight gain, oxygen saturation in the final days, and heart rate. Additionally, the answers to questionnaires on wellbeing, orthopnoea, and ankles are strongly significant predictors.
No takes yet. Share an insight, caveat, or question.
Kerexeta et al. (2023) conducted an observational in Chronic heart failure (n=488). Telemonitored vital signs and questionnaire data (AI prediction model) was evaluated on Prediction of cardiac decompensation events (CDEs) within 7 days (AUC 0.694). An XGBoost machine learning model utilizing daily telemonitored vital signs and well-being questionnaires predicted heart failure decompensation events with an AUC of 0.694 in the testing set.
Synapse has enriched 10 related papers. Consider them for comparative context: