Publications by authors named "Michael Ripperger"
Purpose: The value of genetic information for improving the performance of clinical risk prediction models has yielded variable conclusions. Many methodological decisions have the potential to contribute to differential results. We performed multiple modeling experiments integrating clinical and demographic data from electronic health records (EHR) with genetic data to understand which decisions may affect performance.
View Article and Find Full Text PDFArticle Synopsis
- Post-marketing safety surveillance can be improved by detecting clinical events through spontaneous reporting, but it requires healthcare professionals to be well-informed and aware of the reporting process.
- The study introduces a new method for identifying incidents using unstructured clinical data and natural language processing, validated against traditional methods for two specific health concerns: suicide attempts and sleep-related behaviors.
- Results showed that while the new approach effectively identified suicide attempts with decent precision, it struggled more with sleep-related behaviors; additionally, performance varied by race, highlighting the need for careful monitoring and bias reduction in healthcare AI applications.
Article Synopsis
- This study focuses on treatment-resistant depression (TRD), which affects about one-third of major depressive disorder (MDD) patients, and aims to clarify its genetic basis since previous research hasn't pinpointed specific genetic markers.* -
- Researchers used electroconvulsive therapy (ECT) as an indicator of TRD and applied machine learning to analyze health records, performing a genome-wide association study involving over 154,000 patients in four large biobanks.* -
- The findings revealed low heritability estimates and identified two significant genetic loci associated with TRD, suggesting links to other traits like cognition and metabolism, which could have implications for future treatments.*
Post marketing safety surveillance depends in part on the ability to detect concerning clinical events at scale. Spontaneous reporting might be an effective component of safety surveillance, but it requires awareness and understanding among healthcare professionals to achieve its potential. Reliance on readily available structured data such as diagnostic codes risk under-coding and imprecision.
View Article and Find Full Text PDFThe value of genetic information for improving the performance of clinical risk prediction models has yielded variable conclusions. Many methodological decisions have the potential to contribute to differential results across studies. Here, we performed multiple modeling experiments integrating clinical and demographic data from electronic health records (EHR) and genetic data to understand which decision points may affect performance.
View Article and Find Full Text PDFArticle Synopsis
- The study aimed to evaluate how polygenic scores (PGS) related to psychiatric disorders affect healthcare usage and the burden of comorbid conditions among a large group of participants with linked health records.
- Using data from approximately 118,882 individuals, researchers found that higher PGS for major depressive disorder was significantly associated with increased visits to emergency departments, inpatient services, and outpatient services, especially after a depression diagnosis.
- The results indicate that individuals with a higher genetic predisposition to depression tend to use more healthcare resources and experience greater comorbidity, although similar patterns were not observed for bipolar disorder and schizophrenia.
Objective: To develop and validate algorithms for predicting 30-day fatal and nonfatal opioid-related overdose using statewide data sources including prescription drug monitoring program data, Hospital Discharge Data System data, and Tennessee (TN) vital records. Current overdose prevention efforts in TN rely on descriptive and retrospective analyses without prognostication.
Materials And Methods: Study data included 3 041 668 TN patients with 71 479 191 controlled substance prescriptions from 2012 to 2017.
Background: NCBI's Gene Expression Omnibus (GEO) is a rich community resource containing millions of gene expression experiments from human, mouse, rat, and other model organisms. However, information about each experiment (metadata) is in the format of an open-ended, non-standardized textual description provided by the depositor. Thus, classification of experiments for meta-analysis by factors such as gender, age of the sample donor, and tissue of origin is not feasible without assigning labels to the experiments.
View Article and Find Full Text PDFPurposeThe Genomic Oligoarray and SNP Array Evaluation Tool 3.0 matches candidate genes within regions of homozygosity with a patient's phenotype, by mining OMIM for gene entries that contain a Clinical Synopsis. However, the tool cannot identify genes/disorders whose OMIM entries lack a descriptor of the mode of (Mendelian) inheritance.
View Article and Find Full Text PDF