A Noninvasive Model to Detect Malaria Based on Symptoms Using Machine Learning
Bibliographic record
Abstract
The impact of Artificial Intelligence in the domain of Healthcare has been growing, day by day. These applications bring a drastic change in the healthcare system and affects our lives based in the change it brings to the Patientcare system, transforming the traditional way of handling sicknesses and diseases. Machine Learning algorithms that use data, have a big role in the AI based applications that are used in the Healthcare. Hence the Data source and the nature of Data holds an important role in developing effective AI based solutions for many health issues in the society. Data is available in all the hospitals and medical care facilities for many years now. However, without transforming them into a format where Machine Learning algorithms work, it is impossible to use them to develop an AI based application. In this research paper, we briefly discuss the process of developing an AI based application to predict Malaria, which is one of the most common vector borne diseases in the coastal districts of Karnataka. This pioneer work was done over the data collected from the clinical notes of a 1500 bed hospital situated in Mangalore. Few machine learning algorithms like Logistic regression, Support vector machine XGB Booster classifier, CAT Booster Classifier and Random forest classifier were used over the dataset. Our experimental study revealed that, Random Forest classifier works efficiently for this data set, compared with the other algorithms that we used. It gave the best accuracy of 90.92.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 0.001 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".