Genetic Discovery Enabled by A Large Language Model.

Artificial intelligence (AI) has been used in many areas of medicine, and recently large language models (LLMs) have shown potential utility for clinical applications. However, since we do not know if the use of LLMs can accelerate the pace of genetic discovery, we used data generated from mouse genetic models to investigate this possibility. We examined whether a recently developed specialized LLM (Med-PaLM 2) could analyze sets of candidate genes generated from analysis of murine models of biomedical traits. In response to free-text input, Med-PaLM 2 correctly identified the murine genes that contained experimentally verified causative genetic factors for six biomedical traits, which included susceptibility to diabetes and cataracts. Med-PaLM 2 was also able to analyze a list of genes with high impact alleles, which were identified by comparative analysis of murine genomic sequence data, and it identified a causative murine genetic factor for spontaneous hearing loss. Based upon this Med-PaLM 2 finding, a novel bigenic model for susceptibility to spontaneous hearing loss was developed. These results demonstrate Med-PaLM 2 can analyze gene-phenotype relationships and generate novel hypotheses, which can facilitate genetic discovery.

Artificial Intelligence Based on Machine Learning in Pharmacovigilance: A Scoping Review.

INTRODUCTION: Artificial intelligence based on machine learning has made large advancements in many fields of science and medicine but its impact on pharmacovigilance is yet unclear. OBJECTIVE: The present study conducted a scoping review of the use of artificial intelligence based on machine learning to understand how it is used for pharmacovigilance tasks, characterize differences with other fields, and identify opportunities to improve pharmacovigilance through the use of machine learning. DESIGN: The PubMed, Embase, Web of Science, and IEEE Xplore databases were searched to identify articles pertaining to the use of machine learning in pharmacovigilance published from the year 2000 to September 2021. After manual screening of 7744 abstracts, a total of 393 papers met the inclusion criteria for further analysis. Extraction of key data on study design, data sources, sample size, and machine learning methodology was performed. Studies with the characteristics of good machine learning practice were defined and manual review focused on identifying studies that fulfilled these criteria and results that showed promise. RESULTS: The majority of studies (53%) were focused on detecting safety signals using traditional statistical methods. Of the studies that used more recent machine learning methods, 61% used off-the-shelf techniques with minor modifications. Temporal analysis revealed that newer methods such as deep learning have shown increased use in recent years. We found only 42 studies (10%) that reflect current best practices and trends in machine learning. In the subset of 154 papers that focused on data intake and ingestion, 30 (19%) were found to incorporate the same best practices. CONCLUSION: Advances from artificial intelligence have yet to fully penetrate pharmacovigilance, although recent studies show signs that this may be changing.

Digital signatures for early traumatic brain injury outcome prediction in the intensive care unit.

Traumatic brain injury (TBI) is a leading neurological cause of death and disability across the world. Early characterization of TBI severity could provide a window for therapeutic intervention and contribute to improved outcome. We hypothesized that granular electronic health record data available in the first 24 h following admission to the intensive care unit (ICU) can be used to differentiate outcomes at discharge. Working from two ICU datasets we focused on patients with a primary admission diagnosis of TBI whose length of stay in ICU was ≥ 24 h (N = 1689 and 127). Features derived from clinical, laboratory, medication, and physiological time series data in the first 24 h after ICU admission were used to train elastic-net regularized Generalized Linear Models for the prediction of mortality and neurological function at ICU discharge. Model discrimination, determined by area under the receiver operating characteristic curve (AUC) analysis, was 0.903 and 0.874 for mortality and neurological function, respectively. Model performance was successfully validated in an external dataset (AUC 0.958 and 0.878 for mortality and neurological function, respectively). These results demonstrate that computational analysis of data routinely collected in the first 24 h after admission accurately and reliably predict discharge outcomes in ICU stratum TBI patients.

Evaluating Invasive EEG Implantations with Structural Imaging Data and Functional Scalp EEG Recordings from Epilepsy Patients.

Seizures in patients with medically refractory epilepsy (MRE) cannot be controlled with drugs. For focal MRE, seizures originate in the epileptogenic zone (EZ), which is the minimum amount of cortex that must be treated to be seizure free. Localizing the EZ is often a laborious process wherein clinicians first inspect scalp EEG recordings during several seizure events, and then formulate an implantation plan for subsequent invasive monitoring. The goal of implantation is to place electrodes into the brain region covering the EZ. Then, during invasive monitoring, clinicians visually inspect intracranial EEG recordings to more precisely localize the EZ. Finally, the EZ is then surgically ablated, removed or treated with electrical stimulation. Unfortunately success rates average at 50%. Such grim outcomes call for analytical assistance in creating more accurate implantation plans from scalp EEG. In this paper, we introduce a method that combines imaging data (CT and MRI scans) with scalp EEG to derive an implantation distribution. Specifically, scalp EEG data recorded over a seizure event is converted into a time-gamma frequency map, which is then processed to derive a spectrally annotated implantation distribution (SAID). The SAID represents a distribution of gamma power in each of eight cortical lobe/hemisphere partitions. We applied this method to 4 MRE patients who underwent treatment, and found that the SAID distribution overlapped more with clinical implantations in success cases than in failed cases. These preliminary findings suggest that the SAID may help in improving EZ localization accuracy and surgical outcomes.