Pediatric blood & cancer · 2026
Development and Validation of an Automated Pediatric Cancer Staging Calculator Using the Toronto Pediatric Cancer Stage Guidelines.
СтатьяВалидационное исследованиеНазвание и аннотация: Перевод пока не подготовлен
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Sultan Iyad, Al-Nassan Anwar, Alomari Laith, Altalla Bayan, Bazzeh Faiha, Halalsheh Hadeel, Zandaki Dua'a, Al-Omari Amal, Mansour Asem H
Аннотация
BACKGROUND: Pediatric cancer stage at diagnosis is critical for prognosis and research comparisons. The Toronto Pediatric Cancer Stage Guidelines standardize staging across childhood malignancies. We developed a framework for automated staging of pediatric cancers using electronic health records.
METHODS: An extraction pipeline was implemented to orchestrate agents. The system ingests notes from the first 3 months after diagnosis. Agents select the most appropriate staging schema based on diagnosis, calculate the stage, and then validate its accuracy. We tested the tool on 500 pediatric patients from our institutional registry. Cases outside the Toronto schema were excluded, yielding 433 evaluable cases. Each case was processed independently in two runs. The outputs were compared to an expert consensus reference stage (ground truth) established by four pediatric oncologists.
RESULTS: The automated system matched the reference stage in 91.2% of cases overall. Per-run accuracy (compared to ground truth) was 93.8% for the first run and 88.7% for the second run. The two runs agreed on 89.8% of cases (Cohen's κ = 0.785, p < 0.001). Accuracy dropped significantly when the validation agent failed the first attempt and requested a recalculation. For stages obtained from the first attempt, accuracy was 97%; while for stages achieved on subsequent attempts, accuracy was 77%.
CONCLUSION: We demonstrate the first automated staging system for pediatric cancers using standardized Toronto criteria. The tool showed high accuracy comparable to human experts and excellent consistency between independent runs. We propose a hybrid workflow that flags uncertain cases for human review, yielding approximately 97% accuracy with approximately 30% human adjudication.
METHODS: An extraction pipeline was implemented to orchestrate agents. The system ingests notes from the first 3 months after diagnosis. Agents select the most appropriate staging schema based on diagnosis, calculate the stage, and then validate its accuracy. We tested the tool on 500 pediatric patients from our institutional registry. Cases outside the Toronto schema were excluded, yielding 433 evaluable cases. Each case was processed independently in two runs. The outputs were compared to an expert consensus reference stage (ground truth) established by four pediatric oncologists.
RESULTS: The automated system matched the reference stage in 91.2% of cases overall. Per-run accuracy (compared to ground truth) was 93.8% for the first run and 88.7% for the second run. The two runs agreed on 89.8% of cases (Cohen's κ = 0.785, p < 0.001). Accuracy dropped significantly when the validation agent failed the first attempt and requested a recalculation. For stages obtained from the first attempt, accuracy was 97%; while for stages achieved on subsequent attempts, accuracy was 77%.
CONCLUSION: We demonstrate the first automated staging system for pediatric cancers using standardized Toronto criteria. The tool showed high accuracy comparable to human experts and excellent consistency between independent runs. We propose a hybrid workflow that flags uncertain cases for human review, yielding approximately 97% accuracy with approximately 30% human adjudication.