Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records
Abstract Heart failure (HF) is a condition with periods of stability interrupted by periods of worsening symptoms, known as decompensation episodes. Digital interventions are promising tools to alleviate burdens on HF management through automated alerts at the earliest decompensation sign. To accomp...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-08-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-16376-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849226426256982016 |
|---|---|
| author | Shumit Saha Heather Ross Pedro Elkind Velmovitsky Chloe X. Wang Julie K. K. Vishram-Nielsen Cedric Manlhiot Bo Wang Joseph A. Cafazzo |
| author_facet | Shumit Saha Heather Ross Pedro Elkind Velmovitsky Chloe X. Wang Julie K. K. Vishram-Nielsen Cedric Manlhiot Bo Wang Joseph A. Cafazzo |
| author_sort | Shumit Saha |
| collection | DOAJ |
| description | Abstract Heart failure (HF) is a condition with periods of stability interrupted by periods of worsening symptoms, known as decompensation episodes. Digital interventions are promising tools to alleviate burdens on HF management through automated alerts at the earliest decompensation sign. To accomplish this, our lab developed Medly, an expert system-enhanced digital therapeutic program for HF patients. Medly’s algorithm is a knowledge-based system that analyzes weight, blood pressure, and heart rate and sends automated alerts to clinicians and patients if deterioration is identified. Rules were set conservatively to account for false negatives. However, reducing false negatives resulted in an increase in false positives, which can lead to unnecessary clinical workload. Further, patients’ electronic health records (EHR) were not used when developing the rules-based algorithm. This study aimed to enhance Medly’s performance with machine learning and include a richer set of data, including EHR, for predicting decompensated HF episodes. We performed a retrospective study using XGBoost for the binary classification of whether the patient needed to be contacted for a possible decompensation episode. Features included blood pressure, weight change, heart rate, and EHR data (e.g., blood work, medication history). We further performed interpretability analysis to investigate the importance of including EHR data in the model. The enhanced algorithm achieved 98.08% accuracy, 95.26% sensitivity, 98.86% specificity, and a PPV of 88.18% – a marked improvement over the 55.8% in the rules-based algorithm. EHR data, mainly B-type natriuretic peptide (BNP) and total cholesterol, was crucial in predicting decompensation and correcting false-positive alerting. |
| format | Article |
| id | doaj-art-65d276ea46f7472da71ae914b6b58ec5 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-65d276ea46f7472da71ae914b6b58ec52025-08-24T11:21:38ZengNature PortfolioScientific Reports2045-23222025-08-0115111110.1038/s41598-025-16376-9Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health recordsShumit Saha0Heather Ross1Pedro Elkind Velmovitsky2Chloe X. Wang3Julie K. K. Vishram-Nielsen4Cedric Manlhiot5Bo Wang6Joseph A. Cafazzo7Centre for Digital Therapeutics, Techna Institute, University Health NetworkTed Rogers Centre for Heart Research, University Health NetworkCentre for Digital Therapeutics, Techna Institute, University Health NetworkPeter Munk Cardiac Centre, University Health NetworkTed Rogers Centre for Heart Research, University Health NetworkTed Rogers Centre for Heart Research, University Health NetworkPeter Munk Cardiac Centre, University Health NetworkCentre for Digital Therapeutics, Techna Institute, University Health NetworkAbstract Heart failure (HF) is a condition with periods of stability interrupted by periods of worsening symptoms, known as decompensation episodes. Digital interventions are promising tools to alleviate burdens on HF management through automated alerts at the earliest decompensation sign. To accomplish this, our lab developed Medly, an expert system-enhanced digital therapeutic program for HF patients. Medly’s algorithm is a knowledge-based system that analyzes weight, blood pressure, and heart rate and sends automated alerts to clinicians and patients if deterioration is identified. Rules were set conservatively to account for false negatives. However, reducing false negatives resulted in an increase in false positives, which can lead to unnecessary clinical workload. Further, patients’ electronic health records (EHR) were not used when developing the rules-based algorithm. This study aimed to enhance Medly’s performance with machine learning and include a richer set of data, including EHR, for predicting decompensated HF episodes. We performed a retrospective study using XGBoost for the binary classification of whether the patient needed to be contacted for a possible decompensation episode. Features included blood pressure, weight change, heart rate, and EHR data (e.g., blood work, medication history). We further performed interpretability analysis to investigate the importance of including EHR data in the model. The enhanced algorithm achieved 98.08% accuracy, 95.26% sensitivity, 98.86% specificity, and a PPV of 88.18% – a marked improvement over the 55.8% in the rules-based algorithm. EHR data, mainly B-type natriuretic peptide (BNP) and total cholesterol, was crucial in predicting decompensation and correcting false-positive alerting.https://doi.org/10.1038/s41598-025-16376-9Heart failureDecompensated HFMachine learningElectronic health recordsEHR |
| spellingShingle | Shumit Saha Heather Ross Pedro Elkind Velmovitsky Chloe X. Wang Julie K. K. Vishram-Nielsen Cedric Manlhiot Bo Wang Joseph A. Cafazzo Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records Scientific Reports Heart failure Decompensated HF Machine learning Electronic health records EHR |
| title | Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records |
| title_full | Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records |
| title_fullStr | Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records |
| title_full_unstemmed | Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records |
| title_short | Machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records |
| title_sort | machine learning enhanced expert system for detecting heart failure decompensation using patient reported vitals and electronic health records |
| topic | Heart failure Decompensated HF Machine learning Electronic health records EHR |
| url | https://doi.org/10.1038/s41598-025-16376-9 |
| work_keys_str_mv | AT shumitsaha machinelearningenhancedexpertsystemfordetectingheartfailuredecompensationusingpatientreportedvitalsandelectronichealthrecords AT heatherross machinelearningenhancedexpertsystemfordetectingheartfailuredecompensationusingpatientreportedvitalsandelectronichealthrecords AT pedroelkindvelmovitsky machinelearningenhancedexpertsystemfordetectingheartfailuredecompensationusingpatientreportedvitalsandelectronichealthrecords AT chloexwang machinelearningenhancedexpertsystemfordetectingheartfailuredecompensationusingpatientreportedvitalsandelectronichealthrecords AT juliekkvishramnielsen machinelearningenhancedexpertsystemfordetectingheartfailuredecompensationusingpatientreportedvitalsandelectronichealthrecords AT cedricmanlhiot machinelearningenhancedexpertsystemfordetectingheartfailuredecompensationusingpatientreportedvitalsandelectronichealthrecords AT bowang machinelearningenhancedexpertsystemfordetectingheartfailuredecompensationusingpatientreportedvitalsandelectronichealthrecords AT josephacafazzo machinelearningenhancedexpertsystemfordetectingheartfailuredecompensationusingpatientreportedvitalsandelectronichealthrecords |