Machine learning-based immune cell predictive model for cytokine-induced killer cell therapeutic efficacy in gastrointestinal cancer* 3340
Bibliographic record
Abstract
Abstract Description Cancer remains the leading cause of death worldwide, driving a substantial global demand for effective cancer cell therapies. Despite advancements, physicians face challenges in identifying the most suitable treatment for individual patients due to the lack of standardized methodologies. In this study, peripheral blood mononuclear cells from cancer patients were collected prior to cytokine-induced killer (CIK) immunotherapy and analyzed using flow cytometry with a multi-antibody panel to identify immune cell populations. Post-therapy, patient responses were evaluated based on the Response Evaluation Criteria in Solid Tumors (RECIST) to assess therapeutic efficacy. The objective was to develop machine learning prototypes—such as principal component analysis (PCA), support vector machines (SVM), K-nearest neighbor (KNN), and Decision Tree (DT) models—to classify immune cell data into distinct RECIST groups and predict therapeutic outcomes. Among these, PCA and DT models demonstrated accuracy rates exceeding 85%. Integrating immune monitoring with AI technologies has the potential to enhance preventive medicine and therapeutic diagnostics, paving the way for advancements in precision medicine. Keywords Immune monitoring, CIK, AI, Machine learning, Precision medicine Funding Sources *This work is supported by a grant from the National Science and Technology Council (113-2314-B-038-137), Taipei, Taiwan. Topic Categories Tumor Immunology: Checkpoints, Prevention, and Treatment (TIPT)
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".