Development of a Clinical Prediction Model to Calculate Patient Life Expectancy: The Measure of Actuarial Life Expectancy (MALE)
Bibliographic record
Abstract
OBJECTIVES: To develop a clinical prediction model enabling the calculation of an individual patient's life expectancy (LE) and survival probability based on age, sex, and comorbidity for use in the joint decision-making process regarding medical treatment. METHODS: A computer software program was developed with a team of 3 clinicians, 2 professional actuaries, and 2 professional computer programmers. This incorporated statistical spreadsheet and database access design methods. Data sources included life insurance industry actuarial rating factor tables (public and private domain), Government Actuary Department UK life tables, professional actuarial sources, and evidence-based medical literature. The main outcome measures were numerical and graphical display of comorbidity-adjusted LE; 5-, 10-, and 15-year survival probability; in addition to generic UK population LE. RESULTS: Nineteen medical conditions, which impacted significantly on LE in actuarial terms and were commonly encountered in clinical practice, were incorporated in the final model. Numerical and graphical representations of statistical predictions of LE and survival probability were successfully generated for patients with either no comorbidity or a combination of the 19 medical conditions included. Validation and testing, including actuarial peer review, confirmed consistency with the data sources utilized. CONCLUSIONS: The evidence-based actuarial data utilized in this computer program design represent a valuable resource for use in the clinical decision-making process, where an accurate objective assessment of patient LE can so often make the difference between patients being offered or denied medical and surgical treatment. Ongoing development to incorporate additional comorbidities and enable Web-based access will enhance its use further.
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 | 0.003 | 0.017 |
| 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 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 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".