Incidence Measures for Schizophrenia among Commercial Health Insurance and Medicaid Enrollees
Bibliographic record
Abstract
ABSTRACT Objective To examine and compare the prevalence, incidence, and specificity and positive predictive value of incidence measures in a national commercial insurance database and a state Medicaid database, for different age groups over the life span. Methods This cross-sectional study examined the annual prevalence of schizophrenia in 2019 in two databases: a) MarketScan, a United States national commercial insurance database ( N = 16,365,997), and b) New York State Medicaid program ( N = 4,414,153). A subset of these individuals with 10 years of continuous insurance prior to 2019 (2009-2018) was used to assess incidence and to create a reference standard for incidence measure testing, including positive predictive value and specificity, by age group. Continuous enrollment was required for all years of study (45-day gap allowance per year, and one or more health care services annually to ensure opportunity to be diagnosed). Results The prevalence of schizophrenia in 2019 was 0.13% in MarketScan, and 2.13% in Medicaid. Prevalence was highest in MarketScan among individuals aged 21-25 years. In contrast, prevalence in Medicaid increased over the lifespan, with the peak among those 56-60 years of age. The incidence of new-onset schizophrenia in 2019 was 0.07% in MarketScan and 0.19% in Medicaid and peaked in young adulthood (26-30 years of age) in both databases (0.16% and 0.40%, respectively). Positive predictive value (PPV) for the incidence measures was higher for women than men and increased with longer lookback periods prior to the first schizophrenia diagnosis in 2019. Using a one-year lookback period, the PPV for those ≤35 years of age was 79% in MarketScan and 51% in Medicaid; a ≥95% PPV was achieved with a two-year lookback in MarketScan, and a seven-year lookback period in Medicaid. PPVs were also higher in younger age groups; in Medicaid a two-year lookback period yielded a PPV of 68% for those ≤35 years, but was 94% for those ≤20 years. Specificity was high even for the total population with one year of observation prior to the first schizophrenia diagnosis in 2019, and was higher in Medicaid (92%) than in MarketScan (80%), increasing further with longer lookback periods in both databases. Conclusions The prevalence of schizophrenia is over 10-fold higher, and the incidence two-fold higher, in the New York State Medicaid population compared to the MarketScan national commercial insurance database. Within each database, prevalence and incidence varied by sex, age, and duration of insurance. Yet despite these differences, accurate measures of incidence of new-onset schizophrenia could be constructed with high specificity and positive predictive values.
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 | 0.013 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".