Chatsum: An Intelligent Medical Chat Summarization Tool
Bibliographic record
Abstract
During the recent pandemic, online meetings, voice, and chat-based services have become extremely popular and the only way to provide remote services. Medical advising is one such mandatory service where patients use text to chat with medical professionals over the internet or mobile media and optionally upload sensitive information such as images. With a view to improving the quality of service of the remote medical advising system of our industry partner, we propose Chatsum, a chat summarization system, which creates a summary of chats from the previous encounters for each patient. Chatsum can assist the doctors to serve better by significantly reducing the cognitive load and highlighting important information. We applied a variety of natural language processing techniques including a medical domain-specific annotation and information extraction tool cTAKES, to identify key information in conversations and trained a classification model to identify sentences to be included in the final summary. The usability and the quality of chat summaries generated by our tool have been validated by real doctors serving patients online using the current platform. We also investigated the importance of each feature type in our method and assigned an importance score to each sentence in a chat to create a visualization to reduce the cognitive load.
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 | 0.002 | 0.010 |
| Meta-epidemiology (narrow) | 0.002 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.004 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.011 | 0.004 |
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".