Leveraging ChatGPT and Long Short-Term Memory in Recommender Algorithm for Self-Management of Cardiovascular Risk Factors
Abstract
:1. Introduction
- (1)
- The user profile, in addition to the risk factors outlined in the 2021 European guidelines for CVD prevention [1], includes angina symptoms and two predictive assessments. The first predictive assessment estimates the possibility of the presence of CVD in adults with risk factors based on a pre-trained LSTM model. The second one assesses the total risk of CVDs over a 10-year period using SCORE models [7].
- (2)
- Based on user profiles, we propose and study the CaRiFaM algorithm to support the management of CVD risk factors in adults at home. Our proposed algorithm, CaRiFaM, integrates several key enhancements, including an extended user profile and a modified structure of recommendation, leveraging LLM and deep ML models.
- (3)
- The individual recommendations created have a three-dimensional structure and contain recommendation items of different types of meanings, namely targeted, informational, and explanatory. We leveraged the power of ChatGPT to generate explainable recommendations for managing CVD risk factors.
2. Literature Review
3. Model of Multidimensional Recommendation
- Usefulness: The recommendations should help adults to manage CVD risk factors more effectively.
- Safety: The recommendations should be based on the principles of evidence-based medicine and, at the same time, without drug interventions. The recommendations should not lead to an adverse event for users.
- Completeness: The recommendations should be based on most of the CVD risk factors and their assessment, as set out in the current clinical guidelines for the prevention of CVDs. At the same time, the symptoms of angina pectoris as the main predictor of coronary heart disease should be included in the complex of CVD risk factors.
- Accuracy: The recommendation items must be correct and free of errors. The text of recommendations should provide information about a person’s CVD risk factors only if they are identified. For the persons without CVD risk factors, the text of recommendations should present general information supporting their healthy lifestyle.
- Explainability: The recommendation items should not only inform about identified CVD risk factors but also explain their impact on the person’s CV health.
- Timeliness: The recommendations should include information about the need and degree of urgency to seek medical help, depending on the assessment of the person’s risk of CVD.
4. Multifactorial User CVD Risk Model
5. Recommender Algorithm to Support Self-Management of CVD Risk Factors
- Creating the user profile Factor using multifactorial CVD risk model Z:
- 2.
- Generating the recommendations:
5.1. Creating User Profile Factor
5.2. Generating Individual Recommendations
6. Preliminary Analysis of ChatGPT Explanations for CVD Risk Factors
7. Experimental Results
7.1. Evaluation of CVD Prediction Using ML Models
7.2. Exploring the Effectiveness of ChatGPT for the Explanation of CVD Risk Factors
7.3. Study of the Effectiveness of a Recommendation Algorithm
7.4. Assessment of the Potential Benefit of Using the Proposed Algorithm
8. Discussion
9. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Visseren, F.L.J.; Mach, F. 2021 ESC Guidelines on cardiovascular disease prevention in clinical practice. Eur. Heart J. 2021, 42, 3227–3337. [Google Scholar] [CrossRef] [PubMed]
- Global Strategy on Digital Health 2020–2025; World Health Organization: Geneva, Switzerland; Available online: https://www.who.int/publications/i/item/9789240020924 (accessed on 15 July 2024).
- Cai, Y.; Yu, F. Health Recommender Systems Development, Usage, and Evaluation from 2010 to 2022: A Scoping Review. Int. J. Environ. Res. Public Health 2022, 19, 15115. [Google Scholar] [CrossRef]
- Uta, M.; Felfernig, A.; Le, V.-M.; Burgstaller, T. Knowledge-based recommender systems: Overview and research directions. Front. Big Data 2024, 7, 1304439. [Google Scholar] [CrossRef]
- Burke, R. Knowledge-based recommender systems. In Encyclopedia of Library and Information Science; CRC Press: Boca Raton, FL, USA, 2000; Volume 69, pp. 180–200. [Google Scholar]
- Aggarwal, C.C. Recommender Systems: The Textbook; Springer International Publishing: Cham, Switzerland, 2016. [Google Scholar]
- SCORE2 working group and ESC Cardiovascular risk collaboration. SCORE2 risk prediction algorithms: New models to estimate 10-year risk of cardiovascular disease in Europe. Eur. Heart J. 2021, 42, 2439–2454. [Google Scholar] [CrossRef]
- Tran, T.N.T.; Felfernig, A.; Trattner, C.; Holzinger, A. Recommender systems in the healthcare domain: State-of-the-art and research issues. J. Intell. Inf. Syst. 2020, 57, 171–201. [Google Scholar] [CrossRef]
- Etemadi, M.; Abkenar, S. A systematic review of healthcare recommender systems: Open issues, challenges, and techniques. Expert Syst. Appl. 2023, 213, 118823. [Google Scholar] [CrossRef]
- De Croon, R.; Van Houdt, L. Health Recommender Systems: Systematic Review. J. Med. Internet Res. 2021, 23, e18035. [Google Scholar] [CrossRef] [PubMed]
- Wang, Z.; Huang, H.; Cui, L.; Chen, J.; An, J.; Duan, H.; Ge, H.; Deng, N. Using Natural Language Processing Techniques to Provide Personalized Educational Materials for Chronic Disease Patients in China: Development and Assessment of a Knowledge-Based Health Recommender System. Med. Inf. J. 2020, 8, e17642. [Google Scholar] [CrossRef]
- Lopez-Barreiro, J.; Garcia-Soidan, J.L.; Alvarez-Sabucedo, L.; Santos-Gago, J.M. Practical Approach to Designing and Implementing a Recommendation System for Healthy Challenges. Appl. Sci. J. 2023, 13, 9782. [Google Scholar] [CrossRef]
- Dogan, A.; Li, Y.; Odo, C.P.; Sonawane, K.; Lin, Y.; Liu, C. A utility-based machine learning-driven personalized lifestyle recommendation for cardiovascular disease prevention. J. Biomed. Inform. 2023, 141, 104342. [Google Scholar] [CrossRef]
- Honka, A.M.; Nieminen, H.; Similä, H.; Kaartinen, J.; Gils, M.J. A Comprehensive User Modeling Framework and a Recommender System for Personalizing Well-Being Related Behavior Change Interventions: Development and Evaluation. IEEE Access J. 2022, 10, 116766–116783. [Google Scholar] [CrossRef]
- Kobrinskii, B.A.; Grigoriev, O.G.; Molodchenkov, A.I.; Smirnov, I.V.; Blagosklonov, N.A. Artificial Intelligence Technologies Application for Personal Health Management. IFAC-Pap. 2019, 52, 70–74. [Google Scholar] [CrossRef]
- Kung, T.H.; Cheatham, M.; Medenilla, A.; Sillos, C.; De Leon, L.; Elepaño, C.; Madriaga, M.; Aggabao, R.; Diaz-Candido, G.; Maningo, J.; et al. Performance of ChatGPT on USMLE: Potential for AI-assisted medical education using large language models. PLoS Digit. Health 2023, 2, e0000198. [Google Scholar] [CrossRef]
- Tran, T.N.T.; Felfernig, A.; Man Le, V.; Chau, T.M.N.; Mai, T.G. User Needs for Explanations of Recommendations: In-depth Analyses of the Role of Item Domain and Personal Characteristics. In Proceedings of the 31st ACM Conference on User Modeling, Adaptation and Personalization (UMAP ’23), Limassol, Cyprus, 26–29 June 2023; Association for Computing Machinery: New York, NY, USA, 2023; pp. 54–65. [Google Scholar] [CrossRef]
- Li, Z.; Chen, Y.; Zhang, X.; Liang, X. BookGPT: A General Framework for Book Recommendation Empowered by Large Language Model. Electronics 2023, 12, 4654. [Google Scholar] [CrossRef]
- Ray, P.P. ChatGPT: A comprehensive review on background, applications, key challenges, bias, ethics, limitations and future scope. Internet Things Cyber-Phys. Syst. 2023, 3, 121–154. [Google Scholar] [CrossRef]
- Shahab, O.; El Kurdi, B.; Shaukat, A.; Nadkarni, G.; Soroush, A. Large language models: A primer and gastroenterology applications. Ther. Adv. Gastroenterol. 2024, 17, 1–15. [Google Scholar] [CrossRef]
- Gala, D.; Makaryus, A.N. The Utility of Language Models in Cardiology: A Narrative Review of the Benefits and Concerns of ChatGPT-4. Int. J. Environ. Res. Public Health 2023, 20, 6438. [Google Scholar] [CrossRef]
- Rao, A.; Pang, M.; Kim, J.; Kamineni, M.; Lie, W.; Prasad, A.K.; Landman, A.; Dreyer, K.; Succi, M.D. Assessing the Utility of ChatGPT Throughout the Entire Clinical Workflow: Development and Usability Study. J. Med. Internet Res. 2023, 25, e48659. [Google Scholar] [CrossRef]
- Dave, T.; Athaluri, S.A.; Singh, S. ChatGPT in medicine: An overview of its applications, advantages, limitations, future prospects, and ethical considerations. Front. Artif. Intell. 2023, 6, 1169595. [Google Scholar] [CrossRef]
- Groza, T.; Caufield, H.; Gration, D.; Baynam, G.; Haendel, M.A.; Robinson, P.N.; Mungall, C.J.; Reese, J.T. An evaluation of GPT models for phenotype concept recognition. BMC Med. Inform. Decis. Mak. 2024, 24, 30. [Google Scholar] [CrossRef]
- Sarraju, A.; Bruemmer, D.; Van Iterson, E.; Cho, L.; Rodriguez, F.; Laffin, L. Appropriateness of cardiovascular disease prevention recommendations obtained from a popular online chat-based artificial intelligence model. JAMA 2023, 329, 842–844. [Google Scholar] [CrossRef] [PubMed]
- Valery, L.; Feigin; Krishnamurthi, R. Digital solutions for primary stroke and cardiovascular disease prevention: A mass individual and public health approach. Lancet Reg. Health West. Pac. 2022, 29, 100511. [Google Scholar] [CrossRef]
- Rose, G.A. The diagnosis of ischemic heart pain and intermittent claudication in field surveys. Bull. World Health Organ. 1962, 27, 645–658. [Google Scholar] [PubMed]
- ChatGPT: Optimizing Language Models for Dialogue. Open AI. Available online: https://openai.com/blog/chatgpt (accessed on 15 July 2024).
- Baktash, A.J.; Dawodi, M.; Chat GPT. GPT-4: A Review on Advancements and Opportunities in Natural Language Processing. J. Electr. Electron. Eng. 2023, 2, 548–549. [Google Scholar] [CrossRef]
- Erickson, N.; Mueller, J.; Shirkov, A.; Zhang, H.; Larroy, P.; Li, M.; Smola, A. AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data. arXiv 2020, arXiv:2003.06505v1. [Google Scholar]
- Cardiovascular Disease Dataset. Kaggle. Available online: https://www.kaggle.com/datasets/sulianova/cardiovascular-disease-dataset (accessed on 15 July 2024).
- Naseer, Z.A.N.; Nazeer, H. Cardiovascular Disease Detection Using Multiple Machine Learning Algorithms and their Performance Analysis. In Proceedings of the 2022 International Conference on Emerging Trends in Electrical, Control, and Telecommunication Engineering (ETECTE), Lahore, Pakistan, 2–4 December 2022; pp. 1–7. [Google Scholar] [CrossRef]
- Fayez, M.; Kurnaz, S. Novel method for diagnosis diseases using advanced high-performance machine learning system. Appl. Nanosci. 2021, 13, 1787. [Google Scholar] [CrossRef]
- Maiga, J.; Hungilo, G.G.; Pranowo, P. Comparison of Machine Learning Models in Prediction of Cardiovascular Disease Using Health Record Data. In Proceedings of the 2019 International Conference on Informatics, Multimedia, Cyber and Information System (ICIMCIS), Jakarta, Indonesia, 24–25 October 2019; pp. 45–48. [Google Scholar] [CrossRef]
- Zero-Shot Prompting. Prompt Engineering Guide. Available online: https://www.promptingguide.ai/techniques/zeroshot (accessed on 15 July 2024).
- Singhal, A. Modern Information Retrieval: A Brief Overview. IEEE Data Eng. Bull. 2001, 24, 35–43. [Google Scholar]
- Wu, S.; Liu, F.; Zhang, K. Short text similarity calculation based on jaccard and semantic mixture in Bio-Inspired Computing: Theories and Applications. In Bio-Inspired Computing: Theories and Applications; Springer: Singapore, 2021; pp. 37–45. [Google Scholar]
- Duda-Sikuła, M.; Kurpas, D. Barriers and Facilitators in the Implementation of Prevention Strategies for Chronic Disease Patients-Best Practice GuideLines and Policies’ Systematic Review. J. Pers. Med. 2023, 13, 288. [Google Scholar] [CrossRef]
- Timmis, A.; Vardas, P.; Townsend, N.; Torbica, A.; Katus, H.; De Smedt, D.; Gale, C.P.; Maggioni, A.P.; Petersen, S.E.; Huculeci, R.; et al. European Society of Cardiology: Cardiovascular disease statistics 2021. Eur. Heart J. 2022, 43, 716–799. [Google Scholar] [CrossRef]
- Shalnova, S.A.; Maksimov, S.A.; Balanova, Y.A.; Evstifeeva, S.E.; Imaeva, A.E.; Kapustina, A.V.; Karamnova, N.S.; Muromtseva, G.A.; Viktorova, I.A.; Prishchepa, N.N.; et al. Adherence to a healthy lifestyle of the Russian population depending on the socio-demographics. Cardiovasc. Ther. Prev. 2020, 19, 2452. (In Russian) [Google Scholar] [CrossRef]
- Da Costa, F.A.; Pedro, A.R.; Teixeira, I.; Bragança, F.; da Silva, J.A.; Cabrita, J. Primary non-adherence in Portugal: Findings and implications. Int. J. Clin. Pharm. 2015, 37, 626–635. [Google Scholar] [CrossRef] [PubMed]
- Andualem, A.; Gelaye, H.; Damtie, Y. Adherence to Lifestyle Modifications and Associated Factors Among Adult Hypertensive Patients Attending Chronic Follow-Up Units of Dessie Referral Hospital, North East Ethiopia, 2020. Integr. Blood Press. Control 2020, 13, 145–156. [Google Scholar] [CrossRef] [PubMed] [PubMed Central]
- Cleveland Clinic Heart Disease Dataset. Kaggle. Available online: https://www.kaggle.com/datasets/aavigan/cleveland-clinic-heart-disease-dataset (accessed on 15 July 2024).
- Marateb, H.R.; Goudarzi, S. A noninvasive method for coronary artery diseases diagnosis using a clinically-interpretable fuzzy rule-based system. J. Res. Med. Sci. 2015, 20, 214–223. [Google Scholar] [PubMed] [PubMed Central]
- Spoladore, D.; Colombo, V.; Arlati, S.; Mahroo, A.; Trombetta, A.; Sacco, M. An Ontology-Based Framework for a Telehealthcare System to Foster Healthy Nutrition and Active Life-style in Older Adults. Electronics 2021, 10, 2129. [Google Scholar] [CrossRef]
Factor No. | CVD Risk Factor Designation and Description |
---|---|
Type 1: Symptoms (S) | |
1 | —a sign of symptoms of angina pectoris with a significant deterioration in health |
Type 2: Non-modifiable factors ( | |
2 | —a sign that the person has documented one of the CVDs |
3 | a sign of chronic kidney disease |
4 | a sign of type 2 diabetes |
5 | a sign of family history of early CV diseases in close relatives: in men under the age of 55 years and in women under 65 years |
Type 3: Modifiable biological factors () | |
6 | a sign of obesity if the body mass index is more than 30 kg/m |
7 | a sign of high cholesterol; the threshold is 5 mmol/L |
8 | a sign of high levels of non-high-density lipoprotein cholesterol; the threshold is 4 mmol/L |
9 | a sign of raised systolic blood pressure; the threshold is 130/90 mmHg |
10 | a sign of raised glucose levels in the blood serum; the threshold is 7 mmol/L |
Type 4: Modifiable behavioral factors of lifestyle () | |
11 | —a sign of tobacco smoking |
12 | a sign of insufficient physical activity, no more than 2 h of household activity or moderate-intensity aerobic physical activity per week |
13 | a sign of unhealthy food abuse |
Type 5: Predictive estimates of CVD risk (Predict) | |
14 | Totala sign of moderate and higher total CVD risk in 10-year perspective, based on clinical model |
15 | Pre-CVDa sign of the possibility of existing CVD, based on machine learning |
X | Indicator | X | Indicator |
---|---|---|---|
X(1) | Gender: male (1)/female (0) | X(10) | Total cholesterol (mmol/L) |
X(2) | Age (years) | X(11) | Non-high-density lipoprotein cholesterol (mmol/L) |
X(3) | Height (cm) | X(12) | Systolic blood pressure (mmHg) |
X(4) | Weight (kg) | X(13) | Glucose level (mmol/L) |
X(5) | Family history of CVD (1/0) | X(14) | Physical inactivity (1/0) |
X(6) | Presence of CVD (1/0) | X(15) | Smoking (1/0) |
X(7) | Chronic kidney disease (1/0) | X(16) | Unhealthy diet (1/0)) |
X(8) | History of CV events (1/0) | X(17) | Symptoms of angina pectoris, with a significant deterioration in health (1/0) |
X(9) | Type 2 diabetes mellitus (1/0) |
Level | Constraint-Based Rules | |
---|---|---|
1 | CVD risk factors have not been identified. Continue to follow a healthy lifestyle | |
2 | Behavioral risk factors for CVD have been identified. Follow healthy lifestyle and regularly control these factors. | |
3 | You have reported having CVD, which is a high-level risk factor. To prevent cardiovascular events, it is recommended that you consult your doctor regularly and adhere to his recommendations. | |
4 | You are recommended to plan consultation with a primary care physician this year as some CVD risk factors have been identified. | |
5 | You are advised to consult with a primary care physician within six months because some of your risk factors for heart disease need professional help. | |
6 | You have reported a health status that is a specific risk factor for CVD, moreover some additional CVD risk factors have been identified. Therefore, it is recommended to consult with a physician within next month. | |
7 | Based on your CVD risk level, you are strongly advised to consult with physician or cardiologist. Do it within a month—a good decision. | |
8 | You have reported the presence of CVD and some indicators are out of the norm. To clarify your treatment plan, you strongly advised to consult with your doctor this month. | |
9 | Symptoms of angina pectoris have been identified. To prevent CV events, it is extremely important for you to consult a primary care physician or cardiologist as soon as possible without delay. |
Prompts | ChatGPT Responses |
---|---|
Explain, please, why human with diagnosed CVD should manage cholesterol? The explanation must be understandable to the person, include only person CVD risk factors and contain no more 4 propositions. | ChatGPT-4 response: Managing cholesterol is crucial for individuals diagnosed with cardiovascular disease (CVD) because cholesterol plays a significant role in the development of atherosclerosis, which is a common underlying cause of CVD. Plaque Formation. High levels of low-density lipoprotein (LDL) cholesterol can lead to the buildup of plaque in the arteries. This plaque narrows the arteries and can reduce or block blood flow to the heart and other organs. Risk of Heart Attack and Stroke. Plaque buildup increases the risk of heart attacks and strokes. If a plaque ruptures, it can form a clot that blocks the flow of blood. Reducing Inflammation. High cholesterol can contribute to inflammation, which is associated with a higher risk of heart disease. Managing cholesterol levels can help reduce this inflammation. Improving Heart Health. Lowering high cholesterol, especially LDL cholesterol, can slow, reduce, or even stop the buildup of plaque. This helps maintain healthy blood vessels and improves overall heart health. |
Explain, please, why it is recommender to manage CVD risk factors? Use analogy of a garden. The explanation must be understandable to the person, include only person CVD risk factors and contain no more 4 propositions. | ChatGPT-3.5 response: Think of your heart as a garden that you want to keep flourishing with vibrant flowers and plants. The risk factors for CVD—like high blood pressure, high cholesterol, smoking, obesity, and diabetes—are akin to weeds, pests, and harsh weather conditions that can harm your garden. Just as you would pull out weeds, protect your plants from pests, and prepare for changes in weather, managing your CVD risk factors involves adopting a healthy diet, exercising regularly, and following medical advice to keep your heart healthy. Neglecting these risk factors is like letting weeds grow wild, which can choke out the healthy plants. Over time, this can lead to a garden—or in this case, a heart—that isn’t as healthy or vibrant as it could be. Managing these risks is like nurturing your garden, ensuring that it remains a beautiful and serene place to enjoy for years to come. |
Explain, please, why human need to control her/his CVD risk factors such as high blood pressure—160/90 mmHg, physical inactivity, smoking, unhealthy diet. Use analogy of a car. The explanation must be understandable to the person, include only person CV risk factors and contain no more 4 propositions. | ChatGPT-4.o response: High Blood Pressure is like putting too much air in a balloon—it strains the walls and can cause them to burst. In the body, this can lead to damage in the arteries, heart, and other organs. It’s often called the “silent killer” because it doesn’t have symptoms but can lead to serious problems like heart attacks and stroke. Keeping blood pressure lower reduces the strain on your heart and the risk of heart disease. Physical Inactivity. Being inactive is like leaving a car unused for a long time; eventually, it won’t run as well. Regular physical activity keeps your heart and body running smoothly and can help lower high blood pressure, manage weight, and reduce stress on your heart. It can also improve your mood and energy levels. Smoking damages your blood vessels and can make them narrow, making it harder for blood to get around your body. Think of it as a traffic jam in your arteries. Stopping smoking can help to clear the traffic and reduce your risk of heart disease, as well as improve your overall health. Unhealthy Diet. Eating foods high in fat, salt, and sugar is like using low-quality fuel in a car—it won’t run properly and will break down sooner. A healthy diet is like high-quality fuel; it makes sure everything runs smoothly and reduces the risk of blockages in your arteries. It’s good for your whole body, including your heart. |
Answer Semantic Similarity (ASS)% | Accuracy (ACC)% | Diversity (DIV)% | |
---|---|---|---|
GPT-3.5 | 67.2 | 86 | 57 |
GPT-4 | 66.6 | 71 | 50 |
GPT-4o | 66.9 | 86 | 57 |
Safety % | E_Accuracy % | Coherence % | Mean % | |
---|---|---|---|---|
GPT-4 | 99 | 91 | 92 | 94 |
GPT-4o | 99 | 85 | 90 | 92 |
GPT-3.5 | 99 | 75 | 84 | 86 |
No. | Feature of the Individual Recommendations | Mean | SD | DUS% |
---|---|---|---|---|
1 | Completeness. The resulting recommendations comprehensively cover your cardiovascular health concerns and inform you about cardiovascular risk factors | 4.4 | 0.40 | 88 |
2 | Explainability. Recommendations explain the impact of risk factors on cardiovascular health | 4.4 | 0.40 | 88 |
3 | Timeliness. The recommendations received are relevant for seeking medical help | 4.3 | 0.52 | 87 |
4 | Personalization. The recommendations received are specific to you and presented in understandable language | 4.2 | 0.46 | 84 |
5 | Planning. A recommended plan of steps you need to take to help you achieve your cardiovascular disease prevention goals | 4.6 | 0.40 | 92 |
6 | Motivation. The recommendations you receive will motivate you to manage your CV health | 4.2 | 0.31 | 84 |
7 | Usefulness. The recommendations received are useful for you | 4.6 | 0.40 | 92 |
Mean | 4.4 | 0.44 | 88 | |
Cronbach’s alpha = 0.86 |
Criteria of Comparison | Spoladore [45] | Lopez-Barreiro [12] | Wang [11] | Proposed | |
---|---|---|---|---|---|
Perspective of Comparison | Indicator of Comparison | ||||
Number of risk factors in user profile corresponding to CVD risk factors | Lifestyle | 2 | 9 | 4 | 3 |
Biological | - | - | 4 | 5 | |
Non-modifiable factors | - | - | 4 | 5 | |
Descriptive estimates | 2 | 9 | 12 | 13 | |
Predictive estimates | - | - | - | 2 | |
Recommendation associated with self-management of CVD risk factors | User focus | One class: older adults with chronic pathologies | One class: persons without medical conditions | One class: chronic disease patients, including CVD | Adults with or without any CVD risk factors as well symptoms of angina |
Goal | Support healthy diet and physical activity | Support physical, mental, and nutritional health | Support selection of educational materials | Support self-management of CVD risk factors | |
Results | 32 dishes, with diet plan for each day | Ranked list of challenges, selected from 30 health challenges | Ranked list of educational materials | Goal, information, and explanation for each person’s risk factor | |
Knowledge models and algorithms | Ontology and expert knowledge | Expert ranking model | Rules, ontology, and natural language processing | Rules, ChatGPT, and LSTM | |
Guidelines or other official materials used in clinic practice | ACSM guideline and clinical literature | SF-36, sHEI-15, and OSC questionnaires | Corpus of educational materials | 2021 ESC Guidelines on CVD prevention in clinical practice, SCORE algorithms | |
Evaluation | Two use cases | Four experts, 30 uses | MAE on key words for corpus of educational materials, marked by two experts | Testing on open dataset, ASS, ACC, DIV, Safety, E_accuracy, and Coherence; four physicians, 15 users, and potential benefit assessment |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Afanasieva, T.V.; Platov, P.V.; Komolov, A.V.; Kuzlyakin, A.V. Leveraging ChatGPT and Long Short-Term Memory in Recommender Algorithm for Self-Management of Cardiovascular Risk Factors. Mathematics 2024, 12, 2582. https://doi.org/10.3390/math12162582
Afanasieva TV, Platov PV, Komolov AV, Kuzlyakin AV. Leveraging ChatGPT and Long Short-Term Memory in Recommender Algorithm for Self-Management of Cardiovascular Risk Factors. Mathematics. 2024; 12(16):2582. https://doi.org/10.3390/math12162582
Chicago/Turabian StyleAfanasieva, Tatiana V., Pavel V. Platov, Andrey V. Komolov, and Andrey V. Kuzlyakin. 2024. "Leveraging ChatGPT and Long Short-Term Memory in Recommender Algorithm for Self-Management of Cardiovascular Risk Factors" Mathematics 12, no. 16: 2582. https://doi.org/10.3390/math12162582
APA StyleAfanasieva, T. V., Platov, P. V., Komolov, A. V., & Kuzlyakin, A. V. (2024). Leveraging ChatGPT and Long Short-Term Memory in Recommender Algorithm for Self-Management of Cardiovascular Risk Factors. Mathematics, 12(16), 2582. https://doi.org/10.3390/math12162582