MétaCan
Menu
Back to cohort

Revolutioning Healthcare: A Superficial Learning Approach to Predict Heart Diseases by Using Artificial Intelligence (AI) Logic

2024· article· en· W4408358245 on OpenAlexaff
S Rohini, B. Thiyaneswaran, S. Durgadevi, K. Revathi, Jayant Giri, Mohammad Omar Sabri

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldHealth Professions
TopicArtificial Intelligence in Healthcare
Canadian institutionsArtificial Intelligence in Medicine (Canada)
Fundersnot available
KeywordsComputer scienceArtificial intelligenceHealth careMachine learning

Abstract

fetched live from OpenAlex

The prevalence of cardiovascular illnesses is on the rise, making early disease prediction all the more crucial and worrisome. Making this diagnosis is no easy feat; it requires speed and accuracy. The primary objective of the study article is to identify the patient subset most at risk for cardiovascular disease using a battery of medical diagnostic criteria. By analyzing the patient's medical history, we developed a technique to forecast the likelihood of a heart disease diagnosis. Clinical decision support systems have made extensive use of AI approaches for the accurate prediction and diagnosis of a wide range of disorders. Here, we present Superficial Neural Health Learning (SNHL), an AI-based method for accurate heart disease prediction, and we cross-validate it with K-Nearest Neighbor (KNN), a traditional learning method, to see how well it works. Many of the observable risk factors are shared by heart disease patients and can be utilized to make a good diagnosis. A system that takes these risk factors into account might be useful for both doctors and patients; it could alert them to the possibility of heart disease before they incur the expenses associated with unnecessary hospital visits or expensive checkups. In order to diagnose and categorize the patient with cardiac illness, we employed various deep learning algorithms, including KNN and SNHL. In order to control the model's applicability and enhance the accuracy of heart attack prediction in any person, a very helpful technique was applied. When compared to earlier classifiers like naïve bayes, etc., the suggested model's strength in predicting if a person has heart disease using KNN and SNHL was rather satisfying. Applying the provided model to determine the classifier's likelihood of correctly and precisely identifying the heart condition has thus relieved a considerable amount of strain. Both the quality and affordability of medical treatment are improved by the given heart disease prediction system and it is easy to learn a lot about which people are likely to have heart disease from this method.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.005
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.004
Threshold uncertainty score0.009

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0020.005
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0000.002
Scholarly communication0.0020.002
Open science0.0010.002
Research integrity0.0010.002
Insufficient payload (model declined to judge)0.0020.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.210
GPT teacher head0.476
Teacher spread0.266 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2024
Admission routes1
Has abstractyes

Explore more

Same topicArtificial Intelligence in HealthcareFrench-language works237,207