What question did this study set out to answer?

This research aims to evaluate the effectiveness of an AI algorithm in diagnosing paroxysmal nocturnal hemoglobinuria (PNH) using electronic health records.

December 8, 2025Blood

Real-world application of AI in expediting paroxysmal nocturnal hemoglobinuria diagnosis

View Full Paper

Ask AI

Bookmark

This research aims to evaluate the effectiveness of an AI algorithm in diagnosing paroxysmal nocturnal hemoglobinuria (PNH) using electronic health records.
Developed an AI tool integrating machine learning and expert rules.
Screened 1,307,140 patients across 14 hospitals in Poland over 14 months.
Flagged individuals identified as high-risk for PNH for further testing.
356 patients were flagged as high-risk for PNH (0.03% of screened population).
13 patients were diagnosed with PNH, yielding a positive predictive value of 10.92%.
Symptoms of fatigue and anemia were significantly more prevalent in flagged patients compared to non-flagged patients.

Discussion

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

Implication

Prospective study demonstrates AI improves diagnostic accuracy for paroxysmal nocturnal hemoglobinuria, identifying 356 high-risk patients.

Cite This Study

Dąbrowski et al. (2025) studied this question.

synapsesocial.com/papers/693624dd4fa91c937236d21c https://doi.org/10.1182/blood-2025-1415

View Full Paper

Ask AI

Bookmark

Implication

Prospective study demonstrates AI improves diagnostic accuracy for paroxysmal nocturnal hemoglobinuria, identifying 356 high-risk patients.

Real-world application of AI in expediting paroxysmal nocturnal hemoglobinuria diagnosis

Key Points

Discussion

Implication

Cite This Study

Real-world application of AI in expediting paroxysmal nocturnal hemoglobinuria diagnosis

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider