Assessment of Predictive Factors That Shorten Duration of Treatment in Patients With Multiple Myeloma Using AI: Real-World Longitudinal Study Using Data From Medical Data Vision Claims Database
Bibliographic record
Abstract
BACKGROUND: With the availability of newer therapies, the duration of therapy (DoT) shortens with each increasing line of treatment in Japanese patients with multiple myeloma (MM). OBJECTIVE: This study aimed to identify factors that shorten DoT in patients with MM using a machine learning (ML) procedure from the Medical Data Vision (MDV) database. METHODS: This nationwide, retrospective observational real-world study was conducted using anonymized patient data from the MDV claims database from 2003 to 2022. Patients (≥18 y) with transplant-ineligible newly diagnosed MM (continued first line therapy), or relapsed or refractory MM (continued second or third line therapies) were included. To identify important predictive factors, an explainable deep learning model was created using 647 extracted variables (continuous, binary, and nominal categorical) from the MDV database, and the extracted data were used to train ML algorithms to build point-wise linear (PWL) models for predicting DoT. Predictive performance of the PWL model was compared with the elastic net (regularized logistic regression) and the extreme gradient boosting models, and calculated by area under the curve and evaluated by 10-fold double cross-validation. A clustering analysis (k-means method) of 4848 individual samples assessed the relationship between each sample and DoT (3, 6, and 12 months). The characteristics of clusters and sample features belonging to each cluster during and after treatment were studied. RESULTS: Overall, 2762 (4848 individual samples) patients were evaluated (mean age 69.6, SD 11.8 years; 1450/2762, 52.5% male). The area under the curve score of the PWL model to predict DoT at 3, 6, and 12 months was 0.61, 0.64, and 0.66, respectively. Based on the similarity of coefficients of regression models, samples were categorized into 2 clusters (clusters A and B) at DoT of 3 months, 3 clusters (clusters A, B, and C) at 6 months, and 12 months (clusters A, B, and C). Cluster B versus cluster A (at 3 months) and cluster C versus cluster A and B (at 6 and 12 months) had a significantly (P<.01) higher pretreatment Charlson Comorbidity Index. They also showed a lower median of prediction probability. At 3 months in cluster B and at 6 and 12 months in cluster C, the use of immunomodulatory drugs for MM treatment was significantly higher in patients who met predicted DoT at each threshold versus those who did not. Additionally, the use of aspirin was significantly higher in cluster B and cluster C at 3 and 6 months, respectively. CONCLUSIONS: Applying ML techniques using the PWL model yielded efficient results to understand trends associated with treatment and characteristics of Japanese patients with MM whose DoT were shortened. The study demonstrated that patients' disease status and management-related factors, including use of immunomodulatory drugs and management of thromboprophylaxis, may be associated with DoT length.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".