Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Recurso digital |
| Language: | |
| Published: |
Zenodo
2026
|
| Subjects: | |
| Online Access: | https://doi.org/10.5281/zenodo.20230084 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866901876727873536 |
|---|---|
| author | Harsh Kumar Karan Himanshu Jaiswal Vansh Tomar Gunjan Agarwal |
| author_facet | Harsh Kumar Karan Himanshu Jaiswal Vansh Tomar Gunjan Agarwal |
| contents | Heart-related conditions and diseases remain to have a required special expertise which might not be instantly available in emergency conditions.[2]. Recent progress in artificial intelligence (AI) and data-driven health services have helped using machine learning (ML) techniques in the procedure of medical diagnosis process. ML models are constructed to capture complex non-linear patterns in clinical data which can support early risk assessment and decision making for treating physicians [3,4]. Research have found that they have shown enhancements over older techniques against noisy and mixed data, even beating Random Forest, Gradient-Boosted Trees and other ensemble-based classifiers [5]. For working with medical reports, we used a report-processing feature supported by an external language model. This part of the system reads reports in PDF, TXT, and DOCX formats and then extracts relevant values required for generating results. Sometimes the report contains extra details, so only the required values are taken. The system also gives probability-based results and shows the difference between models using charts and graphs. These figures help users to know the results more easily, mainly for users who are not very known with technical terms. Overall, this study makes easier by minimizing a lot of hand work and maintains the setup easy to use. Even individuals who do not have significant technical knowledge can still work with it without dealing with several challenges. Even though this system is not designed to take the place of a doctor, it clearly explains how machine learning and AI can be utilised as an effective tool for early awareness of heart disease likelihood. |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_20230084 |
| institution | Zenodo |
| language | |
| publishDate | 2026 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | Heart Disease Prediction using Machine Learning and AI-Based Medical Report Understanding Harsh Kumar Karan Himanshu Jaiswal Vansh Tomar Gunjan Agarwal cardiac risk analysis learning-based classifiers tree model regression approach neighbor method clinical report processing Heart-related conditions and diseases remain to have a required special expertise which might not be instantly available in emergency conditions.[2]. Recent progress in artificial intelligence (AI) and data-driven health services have helped using machine learning (ML) techniques in the procedure of medical diagnosis process. ML models are constructed to capture complex non-linear patterns in clinical data which can support early risk assessment and decision making for treating physicians [3,4]. Research have found that they have shown enhancements over older techniques against noisy and mixed data, even beating Random Forest, Gradient-Boosted Trees and other ensemble-based classifiers [5]. For working with medical reports, we used a report-processing feature supported by an external language model. This part of the system reads reports in PDF, TXT, and DOCX formats and then extracts relevant values required for generating results. Sometimes the report contains extra details, so only the required values are taken. The system also gives probability-based results and shows the difference between models using charts and graphs. These figures help users to know the results more easily, mainly for users who are not very known with technical terms. Overall, this study makes easier by minimizing a lot of hand work and maintains the setup easy to use. Even individuals who do not have significant technical knowledge can still work with it without dealing with several challenges. Even though this system is not designed to take the place of a doctor, it clearly explains how machine learning and AI can be utilised as an effective tool for early awareness of heart disease likelihood. |
| title | Heart Disease Prediction using Machine Learning and AI-Based Medical Report Understanding |
| topic | cardiac risk analysis learning-based classifiers tree model regression approach neighbor method clinical report processing |
| url | https://doi.org/10.5281/zenodo.20230084 |