Artificial Neural Network for Predicting Abscess Disease Based on Patient Data Using the Backpropagation Method
Bibliographic record
Abstract
The development of information technology, particularly Artificial Intelligence (AI), has had a significant impact on the healthcare sector, including its application in supporting disease diagnosis. One of the common diseases encountered is abscess, a pyogenic bacterial infection characterized by the accumulation of pus in body tissues. At Bidadari General Hospital Binjai, abscess cases have shown fluctuations from 2023 to 2025, highlighting the need for faster, more accurate, and more efficient prediction methods to assist medical personnel in decision-making. This study aims to develop an abscess disease prediction model using an Artificial Neural Network (ANN) with the backpropagation algorithm based on patient data, analyze the model’s accuracy, and provide an alternative decision-support system for early diagnosis. The research method applied is quantitative-experimental, involving several stages: problem identification, collection of patient clinical data, data normalization, ANN architecture design, model training using backpropagation, and evaluation using accuracy metrics, Mean Squared Error (MSE), and Confusion Matrix. The prediction results indicate that the average number of abscess patients per month is projected to increase by 14.33% from historical records to the next 12 months. The historical monthly average was 14.9 patients, while the predicted average for the following year reached 17.0%. The model demonstrated good performance with a Mean Absolute Percentage Error (MAPE) of 244.25%. Therefore, the application of backpropagation-based ANN has the potential to serve as an effective solution in assisting medical personnel to perform early diagnosis of abscess disease in a faster, more accurate, and efficient manner.
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 | 0.004 |
| 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 | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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".