Back

Development of a Clinical Severity Score for Indian Sickle Cell Anaemia Patients

NONGMAITHEM, S. S.; BISWAS, A.; IYER, S.; VAISHNAVI, J.; WATH, A.; CHANDAK, G. R.; JAIN, D.

2025-10-09 pediatrics
10.1101/2025.10.07.25337518 medRxiv
Show abstract

BackgroundSickle cell anemia (SCA) is a common monogenic disorder but phenotypic heterogeneity is common among patients, especially in Indians. Scores to label them as per severity have mostly included non-Indians. We investigated the utility of existing pediatric severity score (PSS) in Indian patients and attempted to develop a severity score to facilitate informed management decisions. Materials and MethodsA total of 171 SCA patients were recruited and two clinical experts categorized them into mild, moderate and severe groups based on clinical and biochemical parameters. We generated PSS and two other modified scores viz. Indian Severity Score 1 (ISS1) by including additional four clinical parameters, and Indian Severity Score 2 (ISS2) by replacing four biochemical measures with related clinical parameters. The patients were randomized and using the training set (N=86), severity scores cutoff values were decided and severity status was established in the testing set (N=85). Overall concordance between severity score-based and clinical expert categorization was calculated in three randomized sets. ResultsUsing PSS, only 2/3rd (66.7%) of Indian patients matched with the clinical assessment; the modified scores significantly improved the concordance; ISS1 (82.8%) and ISS2 (85.1%). Results were similar in all three random sets (80.0%-84.71% and 80.0%-88.2% for ISS1 and ISS2 respectively), suggesting robustness of modified scores in Indian patients. The highest concordance was observed in mild (81-100%) followed by severe (57-85%) groups in all three severity score models. The lowest concordance was observed in the moderate group (10-48%). ConclusionsWe have developed a robust population-specific score for identification of severity status in young Indian SCA patients. Inclusion of specific clinical symptoms in Indian patients underlines the importance of population-specific features to correctly categorize SCA patients. Further exploration of its utility in other populations is needed.

Published in eJHaem · not in our set (fewer than 10 published preprints to learn from) · training set

Matching journals

The top 4 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.