Classifying Sickle Cell Disease Subtypes from Clinical Reports: Algorithm Validation and ICD-10 Accuracy Assessment in Five French Hospitals.

چکیده اصلی

INTRODUCTION: Research on rare diseases using large hospital and medico-administrative databases is expanding, yet precise patient characterization remains challenging. Sickle cell disease (SCD), given its different subtypes and the presence of sickle cell trait (SCT), illustrates these difficulties. METHODS: We developed and validated an algorithm using regular expressions to classify SCD subtypes and SCT from unstructured clinical reports. We included all documents issued between 2013 and 2025 of adult patients with at least one ICD-10 code for SCD in five French expert centers of the Greater Paris University Hospitals. Manual review of a stratified random sample of 1510 patients served as the reference standard. We also evaluated the accuracy of various ICD-10-based selection strategies commonly used in medico-administrative studies to confirm SCD status. RESULTS: Among the 10 868 included patients, 561 924 clinical reports were processed in five minutes using the algorithm. No sickle-related term was found for 1259 patients. Of the remaining 9 609 patients, 1 802 (18.8%) had non-specific sickle mentions, 1 502 (15.6%) were classified as SCT, 6 234 (64.9%) as SCD, of whom 4 443 (71.3%) were SS, 1 431 (23.0%) SC, 263 (4.2%) Sβ⁺ and 97 (1.6%) Sβ⁰. Finally, 71 (0.7%) were unresolved. The overall positive predictive value (PPV) of the algorithm was 94.0% (95% CI 92.6-95.4), ranging from 91.4% to 100% across subtypes. PPV of ICD-10 code-only strategies ranged from 58.1% to 88.3%, depending on the number of codes required and assumptions on unclassified patients. CONCLUSION: This simple algorithm effectively classifies SCD subtypes and SCT from clinical reports. Despite the large multicenter sample, performance may reflect the specific subtype demographics, expertise, and documentation practices of the study setting. This work highlights the risk of misclassification when relying solely on ICD-10 coding and the importance of high-quality clinical documentation for retrospective research.

ترجمه فارسی چکیده

مطالعه‌ای برای توسعه و اعتبارسنجی الگوریتمی با استفاده از عبارات منظم برای طبقه‌بندی زیرگروه‌های بیماری سل گلبول‌قرمز تخت و ویژگی سل گلبول‌قرمز (SCT) از گزارش‌های بالینی غیرسازمان‌یافته انجام شد. الگوریتم بر روی ۱۰۸۶۸ بیمار بالغ شامل در بازه ۲۰۱۳ تا ۲۰۲۵ اعمال شد. الگوریتم در پنج دقیقه توانست ۵۶۱۹۲۴ گزارش بالینی را پردازش کند. دقت الگوریتم در طبقه‌بندی‌ها بین ۹۱.۴٪ تا ۱۰۰٪ متغیر بود. الگوریتم دقت بالاتری نسبت به روش‌های مبتنی بر کد ICD-10 نشان داد.

متن کامل اصلی