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

BACKGROUND: Early diagnosis of Gaucher disease (GD) allows for disease-specific treatment before significant symptoms arise, preventing/delaying onset of complications. Yet, many endure years-long diagnostic odysseys. We report the development of a machine learning algorithm to identify patients with GD from electronic health records. METHODS: We utilized Optum's de-identified Integrated Claims-Clinical dataset (2007-2019) for feature engineering and algorithm training/testing, based on clinical characteristics of GD. Two algorithms were selected: one based on age of feature occurrence (age-based), and one based on occurrence of features (prevalence-based). Performance was compared with an adaptation of the available clinical diagnostic algorithm for identifying patients with diagnosed GD. Undiagnosed patients highly-ranked by the algorithms were compared with diagnosed GD patients. RESULTS: Splenomegaly was the most important predictor for diagnosed GD with both algorithms, followed by geographical location (northeast USA), thrombocytopenia, osteonecrosis, bone density disorders, and bone pain. Overall, 1204 and 2862 patients, respectively, would need to be assessed with the age- and prevalence-based algorithms, compared with 20,743 with the clinical diagnostic algorithm, to identify 28 patients with diagnosed GD in the integrated dataset. Undiagnosed patients highly-ranked by the algorithms had similar clinical manifestations as diagnosed GD patients. CONCLUSIONS: The age-based algorithm identified younger patients, while the prevalence-based identified patients with advanced clinical manifestations. Their combined use better captures GD heterogeneity. The two algorithms were about 10-20-fold more efficient at identifying GD patients than the clinical diagnostic algorithm. Application of these algorithms could shorten diagnostic delay by identifying undiagnosed GD patients.

Estimating the pertussis burden in adolescents and adults in the United States between 2007 and 2019.

We developed a machine learning algorithm to identify undiagnosed pertussis episodes in adolescent and adult patients with reported acute respiratory disease (ARD) using clinician notes in an electronic healthcare record (EHR) database. Here, we utilized the algorithm to better estimate the overall pertussis incidence within the Optum Humedica clinical repository from 1 January 2007 through 31 December 2019. The incidence of diagnosed pertussis episodes was 1-5 per 100,000 annually, consistent with data registered by the US Centers for Disease Control and Prevention (CDC) over the same time period. Among 18,573,496 ARD episodes assessed, 1,053,946 were identified (i.e. algorithm-identified) as likely undiagnosed pertussis episodes. Accounting for these undiagnosed pertussis episodes increased the estimated pertussis incidence by 110-fold on average (34-474 per 100,000 annually). Risk factors for pertussis episodes (diagnosed and algorithm-identified) included asthma (Odds ratio [OR] 2.14; 2.12-2.16), immunodeficiency (OR 1.85; 1.78-1.91), chronic obstructive pulmonary disease (OR 1.63; 1.61-1.65), obesity (OR 1.44; 1.43-1.45), Crohn's disease (OR 1.39; 1.33-1.45), diabetes type 1 (OR 1.21; 1.17-1.24) and type 2 (OR 1.12; 1.1-1.13). Of note, all these risk factors, except Crohn's disease, increased the likelihood of severe pertussis. In conclusion, the incidence of pertussis in the adolescent and adult population in the USA is likely substantial, but considerably under-recognized, highlighting the need for improved clinical awareness of the disease and for improved control strategies in this population. These results will help better inform public health vaccination and booster programs, particularly in those with underlying comorbidities.

Development of an algorithm for finding pertussis episodes in a population-based electronic health record database.

While tetanus-diphtheria-acellular pertussis (Tdap) vaccines for adolescents and adults were licensed in 2005 and immunization strategies proposed, the burden of pertussis in this population remains under-recognized mainly due to atypical disease presentation, undermining efforts to optimize protection through vaccination. We developed a machine learning algorithm to identify undiagnosed/misdiagnosed pertussis episodes in patients diagnosed with acute respiratory disease (ARD) using signs, diseases and symptoms from clinician notes and demographic information within electronic health-care records (Optum Humedica repository [2007-2019]). We used two patient cohorts aged ≥11 years to develop the model: a positive pertussis cohort (4,515 episodes in 4,316 patients) and a negative pertussis (ARD) cohort (4,573,445 episodes and patients), defined using ICD 9/10 codes. To improve contrast between positive pertussis and negative pertussis (ARD) episodes, only episodes with ≥7 symptoms were selected. LightGBM was used as the machine learning model for pertussis episode identification. Model validity was determined using laboratory-confirmed pertussis positive and negative cohorts. Model explainability was obtained using the Shapley additive explanations method. The predictive performance was as follows: area under the precision-recall curve, 0.24 (SD, 7 × 10-3); recall, 0.72 (SD, 4 × 10-3); precision, 0.012 (SD, 1 × 10-3); and specificity, 0.94 (SD, 7 × 10-3). The model applied to laboratory-confirmed positive and negative pertussis episodes had a specificity of 0.846. Predictive probability for pertussis increased with presence of whooping cough, whoop, and post-tussive vomiting in clinician notes, but decreased with gastrointestinal bleeding, sepsis, pulmonary symptoms, and fever. In conclusion, machine learning can help identify pertussis episodes among those diagnosed with ARD.

Cluster analysis of kidney function decline among males with Fabry disease in a large United States electronic health records database.

BACKGROUND: Fabry disease (FD) is an X-linked lysosomal storage disorder caused by deficient α-galactosidase A activity. The spectrum of disease includes phenotypes ranging from "classic" to "later-onset," with varying kidney disease progression. Identifying patterns of declining kidney function and involvement of other major organs in patients with FD is important to guide therapy decisions. METHODS: Clusters of patients with FD and similar estimated glomerular filtration rate (eGFR) decline and age were created using agglomerative clustering of data captured between 2007 and 2020 in the United States Optum Market Clarity database. Male patients with a diagnosis of FD and two or more eGFR values ≥6 months apart were included. Disease progression was compared with a control cohort of patients without an FD diagnosis. RESULTS: eGFR values from 234 male patients with FD were analysed, yielding seven clusters. Five clusters demonstrated disease progression from "natural" eGFR decline, with a slight decrease in kidney function and eGFR usually within the normal range, to rapid, early decline in eGFR and cardiac complications. When compared with the control cohort, a more rapid decline and a higher percentage of cardiac hypertrophy, heart failure, arrhythmias and stroke were noted in the study group. An inflection point was observed in each cluster when deterioration of kidney function accelerated. CONCLUSIONS: Clustering of male patients with FD by decline in kidney function, organ involvement and phenotype through analysis of real-world data provides a reference that could help determine the optimal time for initiation of FD-specific treatment and facilitate management decisions made by healthcare professionals.

Visual-area-specific tonic modulation of GABA release by endocannabinoids sets the activity and coordination of neocortical principal neurons.

Perisomatic inhibition of pyramidal neurons (PNs) coordinates cortical network activity during sensory processing, and this role is mainly attributed to parvalbumin-expressing basket cells (BCs). However, cannabinoid receptor type 1 (CB1)-expressing interneurons are also BCs, but the connectivity and function of these elusive but prominent neocortical inhibitory neurons are unclear. We find that their connectivity pattern is visual area specific. Persistently active CB1 signaling suppresses GABA release from CB1 BCs in the medial secondary visual cortex (V2M), but not in the primary visual cortex (V1). Accordingly, in vivo, tonic CB1 signaling is responsible for higher but less coordinated PN activity in the V2M than in the V1. These differential firing dynamics in the V1 and V2M can be captured by a computational network model that incorporates visual-area-specific properties. Our results indicate a differential CB1-mediated mechanism controlling PN activity, suggesting an alternative connectivity scheme of a specific GABAergic circuit in different cortical areas.