The Use of Artificial Intelligence (AI) to Predict Heart Failure in Type II Diabetes Mellitus Patients: A Systematic Review
Abstract
Heart failure (HF) is a critical concern for individuals with Type II Diabetes Mellitus (T2DM), significantly increasing morbidity and mortality rates. Artificial Intelligence (AI) and machine learning hold promise in enhancing predictive capabilities and guiding personalised interventions. This systematic review evaluates existing AI models' effectiveness in predicting HF complications in T2DM patients. A comprehensive literature search identified 8 relevant studies, predominantly from European, North American, and Southeastern populations. These studies utilised multi-centered registries and electronic medical records to develop AI models predominantly focused on supervised learning algorithms. While the AI models had promising performance, these models lack external validation with diverse populations and reproducibility, hindering their clinical applicability. Moreover, variations in outcome definitions and input features underscore the need for standardised approaches. Despite these limitations, AI models offer valuable insights into HF risk assessment in T2DM, highlighting the importance of further validation and reproducibility for clinical integration.
Downloads
References
2. Abegaz TM, Baljoon A, Kilanko O, Sherbeny F, Ali AA. Machine learning algorithms to predict major adverse cardiovascular events in patients with diabetes. Comput Biol Med. 2023 Sep;164:107289.
3. Basu S, Sussman JB, Berkowitz SA, Hayward RA, Yudkin JS. Development and validation of Risk Equations for Complications Of type 2 Diabetes (RECODe) using individual participant data from randomised trials. Lancet Diabetes Endocrinol. 2017 Oct;5(10):788–98.
4. Gandin I, Saccani S, Coser A, Scagnetto A, Cappelletto C, Candido R, et al. Deep-learning-based prognostic modeling for incident heart failure in patients with diabetes using electronic health records: A retrospective cohort study. Cannatà A, editor. PLOS ONE. 2023 Feb 21;18(2):e0281878.
5. Kanda E, Suzuki A, Makino M, Tsubota H, Kanemata S, Shirakawa K, et al. Machine learning models for prediction of HF and CKD development in early-stage type 2 diabetes patients. Sci Rep. 2022 Nov 21;12(1):20012.
6. Mora T, Roche D, Rodríguez-Sánchez B. Predicting the onset of diabetes-related complications after a diabetes diagnosis with machine learning algorithms. Diabetes Res Clin Pract. 2023 Oct;204:110910.
7. Segar MW, Vaduganathan M, Patel KV, McGuire DK, Butler J, Fonarow GC, et al. Machine Learning to Predict the Risk of Incident Heart Failure Hospitalization Among Patients With Diabetes: The WATCH-DM Risk Score. Diabetes Care. 2019 Dec 1;42(12):2298–306.
8. Tee C, Xu H, Fu X, Cui D, Jafar TH, Bee YM. Longitudinal HbA1c trajectory modelling reveals the association of HbA1c and risk of hospitalization for heart failure for patients with type 2 diabetes mellitus. Lang CC, editor. PLOS ONE. 2023 Jan 20;18(1):e0275610.
9. Dworzynski P, Aasbrenn M, Rostgaard K, Melbye M, Gerds TA, Hjalgrim H, et al. Nationwide prediction of type 2 diabetes comorbidities. Sci Rep. 2020 Feb 4;10(1):1776.
Full Text (PDF) downloads: 266
Copyright (c) 2023 Indonesian Journal of Cardiology
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
