Machine learning models in predicting health care costs in patients with a recent acute coronary syndrome : A prospective pilot study
Hautala, A. J., Shavazipour, B., Afsar, B., Tulppo, M. P., & Miettinen, K. (2023). Machine learning models in predicting health care costs in patients with a recent acute coronary syndrome : A prospective pilot study. Cardiovascular Digital Health Journal, 4(4), 137-142. https://doi.org/10.1016/j.cvdhj.2023.05.001
Published in
Cardiovascular Digital Health JournalAuthors
Date
2023Discipline
Laskennallinen tiedeHyvinvoinnin tutkimuksen yhteisöMultiobjective Optimization GroupPäätöksen teko monitavoitteisestiComputational ScienceSchool of WellbeingMultiobjective Optimization GroupDecision analytics utilizing causal models and multiobjective optimizationCopyright
© 2023 Heart Rhythm Society
Background
Health care budgets are limited requiring the optimal use of resources. Machine learning (ML) methods may have an enormous potential for effective use of health care resources.
Objective
We assessed the applicability of selected ML tools to evaluate the contribution of known risk markers for prognosis of coronary artery disease to predict health care costs for all reasons in patients with a recent acute coronary syndrome (n = 65, aged 65 ± 9 years) for one-year follow-up.
Methods
Risk markers were assessed at baseline, and health care costs were collected from electronic health registries. The Cross-decomposition algorithms were used to rank the considered risk markers based on their impacts on variances. Then regression analysis was performed to predict costs by entering the first top-ranking risk marker and adding the next best markers, one-by-one, to built-up altogether 13 predictive models.
Results
The average annual health care costs were €2601±5378 per patient. The Depression Scale showed the highest predictive value (r = 0.395), accounting for 16% of the costs (p=0.001). When the next two ranked markers (LDL cholesterol; r = 0.230 and left ventricular ejection fraction; r= - 0.227, respectively) were added to the model, the predictive value was 24 % for the costs (p=0.001).
Conclusion
Higher depression score is the primary variable forecasting health care costs in one-year follow-up among acute coronary syndrome patients. The ML tools may help decision-making when planning optimal utilization of treatment strategies.
...
Publisher
ElsevierISSN Search the Publication Forum
2666-6936Keywords
Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/183230136
Metadata
Show full item recordCollections
Related funder(s)
Research Council of FinlandFunding program(s)
Academy Project, AoFAdditional information about funding
This study was partly funded by the Academy of Finland (grant no. 322221).License
Related items
Showing items with similar title or keywords.
-
Machine learning models for assessing risk factors affecting health care costs : 12-month exercise-based cardiac rehabilitation
Hautala, Arto J.; Shavazipour, Babooshka; Afsar, Bekir; Tulppo, Mikko P.; Miettinen, Kaisa (Frontiers Media SA, 2024)Introduction: Exercise-based cardiac rehabilitation (ECR) has proven to be effective and cost-effective dominant treatment option in health care. However, the contribution of well-known risk factors for prognosis of coronary ... -
Exercise and brain health in patients with coronary artery disease : study protocol for the HEART-BRAIN randomized controlled trial
Toval, Angel; Solis-Urra, Patricio; Bakker, Esmée A.; Sánchez-Aranda, Lucía; Fernández-Ortega, Javier; Prieto, Carlos; Alonso-Cuenca, Rosa María; González-García, Alberto; Martín-Fuentes, Isabel; Fernandez-Gamez, Beatriz; Olvera-Rojas, Marcos; Coca-Pulido, Andrea; Bellón, Darío; Sclafani, Alessandro; Sanchez-Martinez, Javier; Rivera-López, Ricardo; Herrera-Gómez, Norberto; Peñafiel-Burkhardt, Rafael; López-Espinosa, Víctor; Corpas-Pérez, Sara; García-Ortega, María Belén; Vega-Cordoba, Alejandro; Barranco-Moreno, Emilio J.; Morales-Navarro, Francisco J.; Nieves, Raúl; Caro-Rus, Alfredo; Amaro-Gahete, Francisco J.; Mora-Gonzalez, Jose; Vidal-Almela, Sol; Carlén, Anna; Migueles, Jairo H.; Erickson, Kirk I.; Moreno-Escobar, Eduardo; García-Orta, Rocío; Esteban-Cornejo, Irene; Ortega, Francisco B. (Frontiers Media, 2024)Introduction: Patients with coronary artery disease (CAD) have a higher risk of developing cognitive impairment and mental health disorders compared to the general population. Physical exercise might improve their brain ... -
Nurse-led counseling for coronary artery disease patients : A 1-year follow-up study
Nurmeksela, Anu; Pihlainen, Vuokko; Kettunen, Tarja; Laukkanen, Jari; Peltokoski, Jaana (Wiley-Blackwell, 2021)Nurse‐led counseling and systematic follow‐up has been shown to reduce cardiovascular risk factor levels. The study aim was to investigate if cardiovascular risk factor levels could be reduced in patients with coronary ... -
Baroreflex sensitivity following acute upper-body exercise in the cold among stable coronary artery disease patients
Pikkarainen, Kalle; Valtonen, Rasmus I. P.; Hintsala, Heidi E.; Kiviniemi, Antti; Crandall, Craig G.; Perkiömäki, Juha; Hautala, Arto J.; Tulppo, Mikko P.; Jaakkola, Jouni J. K.; Ikäheimo, Tiina M. (Frontiers Media, 2023)Background: A cold environment and exercise separately affect the autonomic nervous system (ANS), baroreflex sensitivity (BRS), and blood pressure variability (BPV) but their combined effects on post-exercise recovery are ... -
The Effects of Combined Same Session Aerobic and Resistance Training on Physical Performance in Coronary Artery Disease Patients : Protocol Comparison
Clavario, P.; Barbara, C.; Porcile, A.; Russo, C.; Zappulla, T.; Capurroa, E.; Cornero, T.; Ferrari, Aggradi, C.; Mäkikallio, T.; Hautala A., J. (Austin Publishing Group, 2021)Aerobic training is included to cardiac rehabilitation programs together with resistance training. The effects of combined aerobic and resistance training performed in a same session with different protocols on peak aerobic ...