Development of machine learning models for the prediction of complications after colorectal and small intestine surgery in psychiatric and non-psychiatric patient collectives (P-Study)
Bibliographic record
Abstract
Abstract Introduction Psychiatric and psychosomatic diseases are an increasingly cumbersome burden for the medical system. Indeed, hospital costs associated with mental health conditions have been constantly on the rise in recent years. Moreover, psychiatric conditions are likely to have a negative effect on the treatment of other medical conditions and surgical outcomes, in addition to their direct effects on the overall quality of life. Our study aims to investigate the impact of preoperative risk factors, psychiatric and psychosomatic diseases, and non-psychiatric and non-psychosomatic diseases on the outcomes of small and large bowel surgery and length of hospital stay via predictive modeling techniques. Methods and Analysis Patient data will be collected from several participating national and international surgical centers. The machine learning models will be calculated and coded, but also published in respect to the TRIPOD guidelines (transparent reporting of a multivariable prediction model for individual prognosis or diagnosis). Expected Results It is conceivable to arrive at generalizable models predicting the above-mentioned endpoints through large amounts of data from several centers. The models will be subsequently deployed as a free-to-use web-based prediction tool. Ethics and Dissemination The ethical is approved by Cantonal Ethics Committee Zurich, Switzerland BASEC Nr. 2021-02105.
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 | 0.007 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| 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".