December 8, 2025BloodOpen Access

Early identification of patients likely to benefit from paroxysmal nocturnal hemoglobinuria workup using machine learning on large-scale real-world data.

View Full Paper

Ask AI

Bookmark

Mortality improves with early diagnosis of paroxysmal nocturnal hemoglobinuria through machine learning.
AUPRC of 0.09 and AUROC of 0.77 were achieved with a predictive model based on 375 features.
The study utilized a dataset of 416K patients to enhance diagnostic processes for PNH.
Implementing this predictive model may reduce diagnostic delays for patients with PNH, requiring local validation.

Discussion

No takes yet. Share an insight, caveat, or question.

Analysis shows predictive model identifies PNH patients 3-12 months after initial diagnosis, indicating potential for improved disease burden.

W. T. Pike (2025) studied this question.

View Full Paper

Ask AI

Bookmark

Analysis shows predictive model identifies PNH patients 3-12 months after initial diagnosis, indicating potential for improved disease burden.