A new approach to identifying patients with elevated risk for Fabry disease using a machine learning algorithm.

BACKGROUND: Fabry disease (FD) is a rare genetic disorder characterized by glycosphingolipid accumulation and progressive damage across multiple organ systems. Due to its heterogeneous presentation, the condition is likely significantly underdiagnosed. Several approaches, including provider education efforts and newborn screening, have attempted to address underdiagnosis of FD across the age spectrum, with limited success. Artificial intelligence (AI) methods present another option for improving diagnosis. These methods isolate common health history patterns among patients using longitudinal real-world data, and can be particularly useful when patients experience nonspecific, heterogeneous symptoms over time. In this study, the performance of an AI tool in identifying patients with FD was analyzed. The tool was calibrated using de-identified health record data from a large cohort of nearly 5000 FD patients, and extracted phenotypic patterns from these records. The tool then used this FD pattern information to make individual-level estimates of FD in a testing dataset. Patterns were reviewed and confirmed with medical experts. RESULTS: The AI tool demonstrated strong analytic performance in identifying FD patients. In out-of-sample testing, it achieved an area under the receiver operating characteristic curve (AUROC) of 0.82. Strong performance was maintained when testing on male-only and female-only cohorts, with AUROCs of 0.83 and 0.82 respectively. The tool identified small segments of the population with greatly increased prevalence of FD: in the 1% of the population identified by the tool as at highest risk, FD was 23.9 times more prevalent than in the population overall. The AI algorithm used hundreds of phenotypic signals to make predictions and included both familiar symptoms associated with FD (e.g. renal manifestations) as well as less well-studied characteristics. CONCLUSIONS: The AI tool analyzed in this study performed very well in identifying Fabry disease patients using structured medical history data. Performance was maintained in all-male and all-female cohorts, and the phenotypic manifestations of FD highlighted by the tool were reviewed and confirmed by clinical experts in the condition. The platform's analytic performance, transparency, and ability to generate predictions based on existing real-world health data may allow it to contribute to reducing persistent underdiagnosis of Fabry disease.

Risperidone, quetiapine, and fluphenazine in the treatment of patients with therapy-refractory schizophrenia.

This 12-week, double-blind study evaluated the effectiveness of risperidone (4 mg/day), quetiapine (400 mg/day), or fluphenazine (12.5 mg/day) in a stringently defined treatment-resistant population of people with schizophrenia. No differences were noted in total Brief Psychiatric Rating Scale (BPRS) or Clinical Global Impression scores among the drug groups (n = 38). More subjects tended to complete the study on risperidone (69%) or quetiapine (58%) than those treated with fluphenazine (31%; P value not significant). Eighty-nine percent of those who discontinued on fluphenazine (8 of 9) were due to lack of efficacy. Discontinuation due to adverse effects was low, with only 2 subjects (both on quetiapine) stopping due to side effects. Three of 13 risperidone-treated subjects (23%) and 3 of 12 quetiapine-treated subjects (25%) met response criteria (decrease of 20% of total BPRS score), whereas 2 of 13 subjects (15%) responded to fluphenazine. Side effect occurrence was similar among drug groups and EPS ratings on the Simpson Angus Scale improved in all drug groups (quetiapine, 1.64; risperidone, 1.30; fluphenazine, 0.69; P value not significant). Despite the newer class of second-generation antipsychotic medications, this treatment-resistant population remains difficult to treat. Many people have only minimal to modest improvements with antipsychotic treatment and most continue to have residual psychotic symptoms. Treatment with first- and second-generation antipsychotics may demonstrate similar efficacy; however, patients treated with second-generation antipsychotics may be more likely to adhere to treatment.

Adjunctive quetiapine decreases symptoms of tardive dyskinesia in a patient taking risperidone.

Tardive dyskinesia is a potentially permanent and disfiguring side effect associated with the use of conventional, or first generation, antipsychotics. Quetiapine is a second generation antipsychotic with transient dopamine receptor occupancy, a property shared with clozapine. Quetiapine was administered to a patient who had persistent choreoathetoid movements that developed during treatment with conventional antipsychotics and remained unimproved during longterm treatment with risperidone. During 10 weeks of monotherapy with quetiapine, his Abnormal Involuntary Movement Scale score fell from 11 to 3. He was subsequently switched back to risperidone and his movements returned. The addition of quetiapine to his risperidone regimen once again resulted in a decrease of his tardive dyskinesia symptoms. The mechanism by which quetiapine improved tardive dyskinesia symptoms in this patient is not known, but differential treatment effects between the novel antipsychotics may exist. Controlled trials of quetiapine in the treatment of tardive dyskinesia should be pursued.