Development of a rare disease algorithm to identify persons at risk of Gaucher disease using electronic health records in the United States

A machine learning model for early diagnosis of type 1 Gaucher disease using real-life data

OBJECTIVE

The diagnosis of Gaucher disease (GD) presents a major challenge due to the high variability and low specificity of its clinical characteristics, along with limited physician awareness of the disease's early symptoms. Early and accurate diagnosis is important to enable effective treatment decisions, prevent unnecessary testing, and facilitate genetic counseling. This study aimed to develop a machine learning (ML) model for GD screening and GD early diagnosis based on real-world clinical data using the Maccabi Healthcare Services electronic database, which contains 20 years of longitudinal data on approximately 2.6 million patients.

STUDY DESIGN AND SETTING

We screened the Maccabi Healthcare Services database for patients with GD between January 1998 and May 2022. Eligible controls were matched by year of birth, sex, and socioeconomic status in a 1:13 ratio. The data were partitioned into 75% training and 25% test sets and trained to predict GD using features obtained from medical and laboratory records. Model performances were evaluated using the area under the receiver operating characteristic curve and the area under the precision-recall curve.

RESULTS

We detected 264 confirmed patients with GD to which we matched 3,429 controls. The best model performance (which included known GD signs and symptoms, previously unknown clinical features, and administrative codes) on the test set had an area under the receiver operating characteristic curve = 0.95 ± 0.03 and area under the precision-recall curve = 0.80 ± 0.08, which yielded a median GD identification of 2.78 years earlier than the clinical diagnosis (25th-75th percentile: 1.29-4.53).

CONCLUSION

Using an ML approach on real-world data led to excellent discrimination between GD patients and controls, with the ability to detect GD significantly earlier than the time of actual diagnosis. Hence, this approach might be useful as a screening tool for GD and lead to earlier diagnosis and treatment. Furthermore, advanced ML analytics may highlight previously unrecognized features associated with GD, including clinical diagnoses and health-seeking behaviors.

PLAIN LANGUAGE SUMMARY

Diagnosing Gaucher disease is difficult, which often leads to late or incorrect diagnoses. As a result, patients may undergo unnecessary tests and treatments and experience health deterioration despite medications availability for Gaucher disease. In this study, we used electronic health data to develop machine learning models for early diagnosis of Gaucher disease type 1. Our models, which included known Gaucher disease signs and symptoms, previously unknown clinical features, and administrative codes, were able to significantly outperform other models and expert opinions, detecting type 1 Gaucher disease 3 years on average before actual diagnosis. Our models also revealed new features linked to type 1 Gaucher disease, including specific diagnoses and patterns in patients' healthcare-seeking behaviors. We believe that the tool of machine learning can be valuable for patients with rare diseases.

Assessing the diagnostic utility of the Gaucher Earlier Diagnosis Consensus (GED-C) scoring system using real-world data

BACKGROUND

Gaucher disease (GD) is a rare autosomal recessive condition associated with clinical features such as splenomegaly, hepatomegaly, anemia, thrombocytopenia, and bone abnormalities. Three clinical forms of GD have been defined based on the absence (type 1, GD1) or presence (types 2 and 3) of neurological signs. Early diagnosis can reduce the likelihood of severe, often irreversible complications. The aim of this study was to validate the ability of factors from the Gaucher Earlier Diagnosis Consensus (GED-C) scoring system to discriminate between patients with GD1 and controls using real-world data from electronic patient medical records from Maccabi Healthcare Services, Israel's second-largest state-mandated healthcare provider.

METHODS

We applied the GED-C scoring system to 265 confirmed cases of GD and 3445 non-GD controls matched for year of birth, sex, and socioeconomic status identified from 1998 to 2022. The analyses were based on two databases: (1) all available data and (2) all data except free-text notes. Features from the GED-C scoring system applicable to GD1 were extracted for each individual. Patients and controls were compared for the proportion of the specific features and overall GED-C scores. Decision tree and random forest models were trained to identify the main features distinguishing GD from non-GD controls.

RESULTS

The GED-C scoring distinguished individuals with GD from controls using both databases. Decision tree models for the databases showed good accuracy (0.96 [95% CI 0.95-0.97] for Database 1; 0.95 [95% CI 0.94-0.96] for Database 2), high specificity (0.99 [95% CI 0.99-1]) for Database 1; 1.0 [95% CI 0.99-1] for Database 2), but relatively low sensitivity (0.53 [95% CI 0.46-0.59] for Database 1; 0.32 [95% CI 0.25-0.38]) for Database 2). The clinical features of splenomegaly, thrombocytopenia (< 50 × 109/L), and hyperferritinemia (300-1000 ng/mL) were found to be the three most accurate classifiers of GD in both databases.

CONCLUSION

In this analysis of real-world patient data, certain individual features of the GED-C score discriminate more successfully between patients with GD and controls than the overall score. An enhanced diagnostic model may lead to earlier, reliable diagnoses of Gaucher disease, aiming to minimize the severe complications associated with this disease.