Polygenic risk score portability for common diseases across genetically diverse populations.

BACKGROUND: Polygenic risk scores (PRS) derived from European individuals have reduced portability across global populations, limiting their clinical implementation at worldwide scale. Here, we investigate the performance of a wide range of PRS models across four ancestry groups (Africans, Europeans, East Asians, and South Asians) for 14 conditions of high-medical interest. METHODS: To select the best-performing model per trait, we first compared PRS performances for publicly available scores, and constructed new models using different methods (LDpred2, PRS-CSx and SNPnet). We used 285 K European individuals from the UK Biobank (UKBB) for training and 18 K, including diverse ancestries, for testing. We then evaluated PRS portability for the best models in Europeans and compared their accuracies with respect to the best PRS per ancestry. Finally, we validated the selected PRS models using an independent set of 8,417 individuals from Biobank of the Americas-Genomelink (BbofA-GL); and performed a PRS-Phewas. RESULTS: We confirmed a decay in PRS performances relative to Europeans when the evaluation was conducted using the best-PRS model for Europeans (51.3% for South Asians, 46.6% for East Asians and 39.4% for Africans). We observed an improvement in the PRS performances when specifically selecting ancestry specific PRS models (phenotype variance increase: 1.62 for Africans, 1.40 for South Asians and 0.96 for East Asians). Additionally, when we selected the optimal model conditional on ancestry for CAD, HDL-C and LDL-C, hypertension, hypothyroidism and T2D, PRS performance for studied populations was more comparable to what was observed in Europeans. Finally, we were able to independently validate tested models for Europeans, and conducted a PRS-Phewas, identifying cross-trait interplay between cardiometabolic conditions, and between immune-mediated components. CONCLUSION: Our work comprehensively evaluated PRS accuracy across a wide range of phenotypes, reducing the uncertainty with respect to which PRS model to choose and in which ancestry group. This evaluation has let us identify specific conditions where implementing risk-prioritization strategies could have practical utility across diverse ancestral groups, contributing to democratizing the implementation of PRS.

Validating and automating learning of cardiometabolic polygenic risk scores from direct-to-consumer genetic and phenotypic data: implications for scaling precision health research.

INTRODUCTION: A major challenge to enabling precision health at a global scale is the bias between those who enroll in state sponsored genomic research and those suffering from chronic disease. More than 30 million people have been genotyped by direct-to-consumer (DTC) companies such as 23andMe, Ancestry DNA, and MyHeritage, providing a potential mechanism for democratizing access to medical interventions and thus catalyzing improvements in patient outcomes as the cost of data acquisition drops. However, much of these data are sequestered in the initial provider network, without the ability for the scientific community to either access or validate. Here, we present a novel geno-pheno platform that integrates heterogeneous data sources and applies learnings to common chronic disease conditions including Type 2 diabetes (T2D) and hypertension. METHODS: We collected genotyped data from a novel DTC platform where participants upload their genotype data files and were invited to answer general health questionnaires regarding cardiometabolic traits over a period of 6 months. Quality control, imputation, and genome-wide association studies were performed on this dataset, and polygenic risk scores were built in a case-control setting using the BASIL algorithm. RESULTS: We collected data on N = 4,550 (389 cases / 4,161 controls) who reported being affected or previously affected for T2D and N = 4,528 (1,027 cases / 3,501 controls) for hypertension. We identified 164 out of 272 variants showing identical effect direction to previously reported genome-significant findings in Europeans. Performance metric of the PRS models was AUC = 0.68, which is comparable to previously published PRS models obtained with larger datasets including clinical biomarkers. DISCUSSION: DTC platforms have the potential of inverting research models of genome sequencing and phenotypic data acquisition. Quality control (QC) mechanisms proved to successfully enable traditional GWAS and PRS analyses. The direct participation of individuals has shown the potential to generate rich datasets enabling the creation of PRS cardiometabolic models. More importantly, federated learning of PRS from reuse of DTC data provides a mechanism for scaling precision health care delivery beyond the small number of countries who can afford to finance these efforts directly. CONCLUSIONS: The genetics of T2D and hypertension have been studied extensively in controlled datasets, and various polygenic risk scores (PRS) have been developed. We developed predictive tools for both phenotypes trained with heterogeneous genotypic and phenotypic data generated outside of the clinical environment and show that our methods can recapitulate prior findings with fidelity. From these observations, we conclude that it is possible to leverage DTC genetic repositories to identify individuals at risk of debilitating diseases based on their unique genetic landscape so that informed, timely clinical interventions can be incorporated.

Discovering prescription patterns in pediatric acute-onset neuropsychiatric syndrome patients.

OBJECTIVE: Pediatric acute-onset neuropsychiatric syndrome (PANS) is a complex neuropsychiatric syndrome characterized by an abrupt onset of obsessive-compulsive symptoms and/or severe eating restrictions, along with at least two concomitant debilitating cognitive, behavioral, or neurological symptoms. A wide range of pharmacological interventions along with behavioral and environmental modifications, and psychotherapies have been adopted to treat symptoms and underlying etiologies. Our goal was to develop a data-driven approach to identify treatment patterns in this cohort. MATERIALS AND METHODS: In this cohort study, we extracted medical prescription histories from electronic health records. We developed a modified dynamic programming approach to perform global alignment of those medication histories. Our approach is unique since it considers time gaps in prescription patterns as part of the similarity strategy. RESULTS: This study included 43 consecutive new-onset pre-pubertal patients who had at least 3 clinic visits. Our algorithm identified six clusters with distinct medication usage history which may represent clinician's practice of treating PANS of different severities and etiologies i.e., two most severe groups requiring high dose intravenous steroids; two arthritic or inflammatory groups requiring prolonged nonsteroidal anti-inflammatory drug (NSAID); and two mild relapsing/remitting group treated with a short course of NSAID. The psychometric scores as outcomes in each cluster generally improved within the first two years. DISCUSSION AND CONCLUSION: Our algorithm shows potential to improve our knowledge of treatment patterns in the PANS cohort, while helping clinicians understand how patients respond to a combination of drugs.

Data mining of digitized health records in a resource-constrained setting reveals that timely immunophenotyping is associated with improved breast cancer outcomes.

BACKGROUND: Organizations that issue guidance on breast cancer recommend the use of immunohistochemistry (IHC) for providing appropriate and precise care. However, little focus has been directed to the identification of maximum allowable turnaround times for IHC, which is necessary given the diversity of hospital settings in the world. Much less effort has been committed to the development of digital tools that allow hospital administrators to monitor service utilization histories of their patients. METHODS: In this retrospective cohort study, we reviewed electronic and paper medical records of all suspected breast cancer patients treated at one secondary-care hospital of the Mexican Institute of Social Security (IMSS), located in western Mexico. We then followed three years of medical history of those patients with IHC testing. RESULTS: In 2014, there were 402 breast cancer patients, of which 30 (7.4% of total) were tested for some IHC biomarker (ER, PR, HER2). The subtyping allowed doctors to adjust (56.7%) or confirm (43.3%) the initial therapeutic regimen. The average turnaround time was 56 days. Opportune IHC testing was found to be beneficial when it was available before or during the first rounds of chemotherapy. CONCLUSIONS: The use of data mining tools applied to health record data revealed that there is an association between timely immunohistochemistry and improved outcomes in breast cancer patients. Based on this finding, inclusion of turnaround time in clinical guidelines is recommended. As much of the health data in the country becomes digitized, our visualization tools allow a digital dashboard of the hospital service utilization histories.

Comparison of machine learning classifiers for influenza detection from emergency department free-text reports.

Influenza is a yearly recurrent disease that has the potential to become a pandemic. An effective biosurveillance system is required for early detection of the disease. In our previous studies, we have shown that electronic Emergency Department (ED) free-text reports can be of value to improve influenza detection in real time. This paper studies seven machine learning (ML) classifiers for influenza detection, compares their diagnostic capabilities against an expert-built influenza Bayesian classifier, and evaluates different ways of handling missing clinical information from the free-text reports. We identified 31,268 ED reports from 4 hospitals between 2008 and 2011 to form two different datasets: training (468 cases, 29,004 controls), and test (176 cases and 1620 controls). We employed Topaz, a natural language processing (NLP) tool, to extract influenza-related findings and to encode them into one of three values: Acute, Non-acute, and Missing. Results show that all ML classifiers had areas under ROCs (AUC) ranging from 0.88 to 0.93, and performed significantly better than the expert-built Bayesian model. Missing clinical information marked as a value of missing (not missing at random) had a consistently improved performance among 3 (out of 4) ML classifiers when it was compared with the configuration of not assigning a value of missing (missing completely at random). The case/control ratios did not affect the classification performance given the large number of training cases. Our study demonstrates ED reports in conjunction with the use of ML and NLP with the handling of missing value information have a great potential for the detection of infectious diseases.

Prevalence and metabolic risk factors of chronic kidney disease among a Mexican adult population: a cross-sectional study in primary healthcare medical units.

Introduction: The intricate relationship between obesity and chronic kidney disease (CKD) progression underscores a significant public health challenge. Obesity is strongly linked to the onset of several health conditions, including arterial hypertension (AHTN), metabolic syndrome, diabetes, dyslipidemia, and hyperuricemia. Understanding the connection between CKD and obesity is crucial for addressing their complex interplay in public health strategies. Objective: This research aimed to determine the prevalence of CKD in a population with high obesity rates and evaluate the associated metabolic risk factors. Material and Methods: In this cross-sectional study conducted from January 2017 to December 2019 we included 3,901 participants of both sexes aged ≥20 years who were selected from primary healthcare medical units of the Mexican Social Security Institute (IMSS) in Michoacan, Mexico. We measured the participants' weight, height, systolic and diastolic blood pressure, glucose, creatinine, total cholesterol, triglycerides, HDL-c, LDL-c, and uric acid. We estimated the glomerular filtration rate using the Collaborative Chronic Kidney Disease Epidemiology (CKD-EPI) equation. Results: Among the population studied, 50.6% were women and 49.4% were men, with a mean age of 49 years (range: 23-90). The prevalence of CKD was 21.9%. Factors significantly associated with an increased risk of CKD included age ≥60 years (OR = 11.70, 95% CI [9.83-15.93]), overweight (OR = 4.19, 95% CI [2.88-6.11]), obesity (OR = 13.31, 95% CI [11.12-15.93]), abdominal obesity (OR = 9.25, 95% CI [7.13-11.99]), AHTN (OR = 20.63, 95% CI [17.02-25.02]), impaired fasting glucose (IFG) (OR = 2.73, 95% CI [2.31-3.23]), type 2 diabetes (T2D) (OR = 14.30, 95% CI [11.14-18.37]), total cholesterol (TC) ≥200 mg/dL (OR = 6.04, 95% CI [5.11-7.14]), triglycerides (TG) ≥150 mg/dL (OR = 5.63, 95% CI 4.76-6.66), HDL-c <40 mg/dL (OR = 4.458, 95% CI [3.74-5.31]), LDL-c ≥130 mg/dL (OR = 6.06, 95% CI [5.12-7.18]), and serum uric acid levels ≥6 mg/dL in women and ≥7 mg/dL in men (OR = 8.18, 95% CI [6.92-9.68]), (p < 0.0001). These factors independently contribute to the development of CKD. Conclusions: This study underscores the intricate relationship between obesity and CKD, revealing a high prevalence of CKD. Obesity, including overweight, abdominal obesity, AHTN, IFG, T2D, dyslipidemia, and hyperuricemia emerged as significant metabolic risk factors for CKD. Early identification of these risk factors is crucial for effective intervention strategies. Public health policies should integrate both pharmacological and non-pharmacological approaches to address obesity-related conditions and prevent kidney damage directly.

A genetic counseling needs assessment of Mexico.

BACKGROUND: While genetic counseling has expanded globally, Mexico has not adopted it as a separate profession. Given the rapid expansion of genetic and genomic services, understanding the current genetic counseling landscape in Mexico is crucial to improving healthcare outcomes. METHODS: Our needs assessment strategy has two components. First, we gathered quantitative data about genetics education and medical geneticists' geographic distribution through an exhaustive compilation of available information across several medical schools and public databases. Second, we conducted semi-structured interviews of 19 key-informants from 10 Mexican states remotely with digital recording and transcription. RESULTS: Across 32 states, ~54% of enrolled medical students receive no medical genetics training, and only Mexico City averages at least one medical geneticist per 100,000 people. Barriers to genetic counseling services include: geographic distribution of medical geneticists, lack of access to diagnostic tools, patient health literacy and cultural beliefs, and education in medical genetics/genetic counseling. Participants reported generally positive attitudes towards a genetic counseling profession; concerns regarding a current shortage of available jobs for medical geneticists persisted. CONCLUSION: To create a foundation that can support a genetic counseling profession in Mexico, the clinical significance of medical genetics must be promoted nationwide. Potential approaches include: requiring medical genetics coursework, developing community genetics services, and increasing jobs for medical geneticists.

A study of the transferability of influenza case detection systems between two large healthcare systems.

OBJECTIVES: This study evaluates the accuracy and transferability of Bayesian case detection systems (BCD) that use clinical notes from emergency department (ED) to detect influenza cases. METHODS: A BCD uses natural language processing (NLP) to infer the presence or absence of clinical findings from ED notes, which are fed into a Bayesain network classifier (BN) to infer patients' diagnoses. We developed BCDs at the University of Pittsburgh Medical Center (BCDUPMC) and Intermountain Healthcare in Utah (BCDIH). At each site, we manually built a rule-based NLP and trained a Bayesain network classifier from over 40,000 ED encounters between Jan. 2008 and May. 2010 using feature selection, machine learning, and expert debiasing approach. Transferability of a BCD in this study may be impacted by seven factors: development (source) institution, development parser, application (target) institution, application parser, NLP transfer, BN transfer, and classification task. We employed an ANOVA analysis to study their impacts on BCD performance. RESULTS: Both BCDs discriminated well between influenza and non-influenza on local test cases (AUCs > 0.92). When tested for transferability using the other institution's cases, BCDUPMC discriminations declined minimally (AUC decreased from 0.95 to 0.94, p<0.01), and BCDIH discriminations declined more (from 0.93 to 0.87, p<0.0001). We attributed the BCDIH decline to the lower recall of the IH parser on UPMC notes. The ANOVA analysis showed five significant factors: development parser, application institution, application parser, BN transfer, and classification task. CONCLUSION: We demonstrated high influenza case detection performance in two large healthcare systems in two geographically separated regions, providing evidentiary support for the use of automated case detection from routinely collected electronic clinical notes in national influenza surveillance. The transferability could be improved by training Bayesian network classifier locally and increasing the accuracy of the NLP parser.