Prediction of heart failure decompensations using artificial intelligence and machine learning techniques
Introduction: Heart failure (HF) is a major concern in public health. We have used artificial intelligence to analyze information and improve patient outcomes. Method: An Observational, retrospective, and non-randomized study with patients enrolled in our telemonitoring program (May 2014-February 20...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Permanyer
2022-10-01
|
| Series: | Revista Colombiana de Cardiología |
| Subjects: | |
| Online Access: | https://www.rccardiologia.com/frame_esp.php?id=207 |
| _version_ | 1811186570311499776 |
|---|---|
| author | Vanessa Escolar Ainara Lozano Nekane Larburu Jon Kerexeta Roberto Álvarez Amaia Echebarria Alberto Azcona |
| author_facet | Vanessa Escolar Ainara Lozano Nekane Larburu Jon Kerexeta Roberto Álvarez Amaia Echebarria Alberto Azcona |
| author_sort | Vanessa Escolar |
| collection | DOAJ |
| description | Introduction: Heart failure (HF) is a major concern in public health. We have used artificial intelligence to analyze information and improve patient outcomes. Method: An Observational, retrospective, and non-randomized study with patients enrolled in our telemonitoring program (May 2014-February 2018). We collected patients’ clinical data, telemonitoring transmissions, and HF decompensations. Results: A total of 240 patients were enrolled with a follow-up of 13.44 ± 8.65 months. During this interval, 527 HF decompensations in 148 different patients were detected. Significant weight increases, desaturation below 90% and perception of clinical worsening are good predictors of HF decompensation. We have built a predictive model applying machine learning (ML) techniques, obtaining the best results with the combination of “Weight + Ankle + well-being plus alerts of systolic and diastolic blood pressure, oxygen saturation, and heart rate.” Conclusions: ML techniques are useful tools for the analysis of HF datasets and the creation of predictive models that improve the accuracy of the actual remote patient telemonitoring programs.
|
| first_indexed | 2024-04-11T13:48:43Z |
| format | Article |
| id | doaj.art-b15ac34aaf96400cb247f25a5c06e345 |
| institution | Directory Open Access Journal |
| issn | 2357-3260 |
| language | English |
| last_indexed | 2024-04-11T13:48:43Z |
| publishDate | 2022-10-01 |
| publisher | Permanyer |
| record_format | Article |
| series | Revista Colombiana de Cardiología |
| spelling | doaj.art-b15ac34aaf96400cb247f25a5c06e3452022-12-22T04:20:52ZengPermanyerRevista Colombiana de Cardiología2357-32602022-10-0129410.24875/RCCAR.21000023Prediction of heart failure decompensations using artificial intelligence and machine learning techniquesVanessa Escolar0Ainara Lozano1Nekane Larburu2Jon Kerexeta3Roberto Álvarez4Amaia Echebarria5Alberto Azcona6Cardiology Department, School of Medicine, Basurto University Hospital, Bilbao, San Sebastián, SpainCardiology Department, School of Medicine, Basurto University Hospital, Bilbao, San Sebastián, SpainBiomedical Department, Vicomtech Research and Technological Center, Donostia, San Sebastián, SpainBiomedical Department, Vicomtech Research and Technological Center, Donostia, San Sebastián, SpainBiomedical Department, Vicomtech Research and Technological Center, Donostia, San Sebastián, SpainCardiology Department, School of Medicine, Basurto University Hospital, Bilbao, San Sebastián, SpainCardiology Department, School of Medicine, Basurto University Hospital, Bilbao, San Sebastián, SpainIntroduction: Heart failure (HF) is a major concern in public health. We have used artificial intelligence to analyze information and improve patient outcomes. Method: An Observational, retrospective, and non-randomized study with patients enrolled in our telemonitoring program (May 2014-February 2018). We collected patients’ clinical data, telemonitoring transmissions, and HF decompensations. Results: A total of 240 patients were enrolled with a follow-up of 13.44 ± 8.65 months. During this interval, 527 HF decompensations in 148 different patients were detected. Significant weight increases, desaturation below 90% and perception of clinical worsening are good predictors of HF decompensation. We have built a predictive model applying machine learning (ML) techniques, obtaining the best results with the combination of “Weight + Ankle + well-being plus alerts of systolic and diastolic blood pressure, oxygen saturation, and heart rate.” Conclusions: ML techniques are useful tools for the analysis of HF datasets and the creation of predictive models that improve the accuracy of the actual remote patient telemonitoring programs. https://www.rccardiologia.com/frame_esp.php?id=207Heart failure decompensations. Hospital admissions. Remote patient telemonitoring. Artificial intelligence. Machine learning. Predictive models. |
| spellingShingle | Vanessa Escolar Ainara Lozano Nekane Larburu Jon Kerexeta Roberto Álvarez Amaia Echebarria Alberto Azcona Prediction of heart failure decompensations using artificial intelligence and machine learning techniques Revista Colombiana de Cardiología Heart failure decompensations. Hospital admissions. Remote patient telemonitoring. Artificial intelligence. Machine learning. Predictive models. |
| title | Prediction of heart failure decompensations using artificial intelligence and machine learning techniques |
| title_full | Prediction of heart failure decompensations using artificial intelligence and machine learning techniques |
| title_fullStr | Prediction of heart failure decompensations using artificial intelligence and machine learning techniques |
| title_full_unstemmed | Prediction of heart failure decompensations using artificial intelligence and machine learning techniques |
| title_short | Prediction of heart failure decompensations using artificial intelligence and machine learning techniques |
| title_sort | prediction of heart failure decompensations using artificial intelligence and machine learning techniques |
| topic | Heart failure decompensations. Hospital admissions. Remote patient telemonitoring. Artificial intelligence. Machine learning. Predictive models. |
| url | https://www.rccardiologia.com/frame_esp.php?id=207 |
| work_keys_str_mv | AT vanessaescolar predictionofheartfailuredecompensationsusingartificialintelligenceandmachinelearningtechniques AT ainaralozano predictionofheartfailuredecompensationsusingartificialintelligenceandmachinelearningtechniques AT nekanelarburu predictionofheartfailuredecompensationsusingartificialintelligenceandmachinelearningtechniques AT jonkerexeta predictionofheartfailuredecompensationsusingartificialintelligenceandmachinelearningtechniques AT robertoalvarez predictionofheartfailuredecompensationsusingartificialintelligenceandmachinelearningtechniques AT amaiaechebarria predictionofheartfailuredecompensationsusingartificialintelligenceandmachinelearningtechniques AT albertoazcona predictionofheartfailuredecompensationsusingartificialintelligenceandmachinelearningtechniques |