Limitations of Binary Classification for Long-Horizon Diagnosis Prediction and Advantages of a Discrete-Time Time-to-Event Approach: Empirical Analysis
Abstract BackgroundA major challenge in using electronic health records (EHR) is the inconsistency of patient follow-up, resulting in right-censored outcomes. This becomes particularly problematic in long-horizon event predictions, such as autism and attention-deficit/hyperact...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
JMIR Publications
2025-03-01
|
| Series: | JMIR AI |
| Online Access: | https://ai.jmir.org/2025/1/e62985 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract
BackgroundA major challenge in using electronic health records (EHR) is the inconsistency of patient follow-up, resulting in right-censored outcomes. This becomes particularly problematic in long-horizon event predictions, such as autism and attention-deficit/hyperactivity disorder (ADHD) diagnoses, where a significant number of patients are lost to follow-up before the outcome can be observed. Consequently, fully supervised methods such as binary classification (BC), which are trained to predict observed diagnoses, are substantially affected by the probability of sufficient follow-up, leading to biased results.
ObjectiveThis empirical analysis aims to characterize BC’s inherent limitations for long-horizon diagnosis prediction from EHR; and quantify the benefits of a specific time-to-event (TTE) approach, the discrete-time neural network (DTNN).
MethodsRecords within the Duke University Health System EHR were analyzed, extracting features such as ICD-10International Classification of Diseases, Tenth Revisiontt
ResultsTTE models consistently had comparable or higher ttYOB≤2020YOB≤2020ttttYOB≤2020
ConclusionsBC models substantially underpredicted diagnosis likelihood and inappropriately assigned lower probability scores to individuals with earlier censoring. Common filtering strategies did not adequately address this limitation. TTE approaches, particularly DTNN, effectively mitigated bias from the censoring distribution, resulting in superior discrimination and calibration performance and more accurate prediction of clinical prevalence. Machine learning practitioners should recognize the limitations of BC for long-horizon diagnosis prediction and adopt TTE approaches. The DTNN in particular is well-suited to mitigate the effects of right-censoring and maximize prediction performance in this setting. |
|---|---|
| ISSN: | 2817-1705 |