John Pestian
YOU?
Author Swipe
View article: Comparing Machine and Deep Learning Models for Pediatric Anxiety Classification using Structured EHRs and Area-based Measures of Health Data
Comparing Machine and Deep Learning Models for Pediatric Anxiety Classification using Structured EHRs and Area-based Measures of Health Data Open
Objective This study investigates the performance of various machine learning (ML) and deep learning (DL) models to classify pediatric patients at risk of anxiety disorders using electronic health records (EHRs). By leveraging EHR data and…
View article: Temporal Drift in the Semantic Meaning of Pediatric Anxiety Terms in Electronic Healthcare Records
Temporal Drift in the Semantic Meaning of Pediatric Anxiety Terms in Electronic Healthcare Records Open
Objective To identify and measure semantic drift (i.e., the change in semantic meaning over time) in expert-provided anxiety-related (AR) terminology and compare it to other common electronic health record (EHR) vocabulary in longitudinal …
View article: LLM Assistance for Pediatric Depression
LLM Assistance for Pediatric Depression Open
Traditional depression screening methods, such as the PHQ-9, are particularly challenging for children in pediatric primary care due to practical limitations. AI has the potential to help, but the scarcity of annotated datasets in mental h…
View article: A Data-Centric Approach to Detecting and Mitigating Demographic Bias in Pediatric Mental Health Text: A Case Study in Anxiety Detection
A Data-Centric Approach to Detecting and Mitigating Demographic Bias in Pediatric Mental Health Text: A Case Study in Anxiety Detection Open
Introduction: Healthcare AI models often inherit biases from their training data. While efforts have primarily targeted bias in structured data, mental health heavily depends on unstructured data. This study aims to detect and mitigate lin…
View article: Analyses of GWAS signal using GRIN identify additional genes contributing to suicidal behavior
Analyses of GWAS signal using GRIN identify additional genes contributing to suicidal behavior Open
View article: Early Identification of Candidates for Epilepsy Surgery
Early Identification of Candidates for Epilepsy Surgery Open
This study provides Class II evidence that a machine learning algorithm can accurately distinguish patients with epilepsy who require resective surgery from those who do not.
View article: High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning
High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning Open
We present an ensemble transfer learning method to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverse set of base models was trained to predict a binary outcome constructed from reported suicide, suicide…
View article: High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning
High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning Open
We present an ensemble transfer learning model to predict suicide from Veterans Affairs (VA) electronic medical records (EMR). A diverseset of base models was trained to predict a binary outcome constructed from reported suicide, suicide a…
View article: Using iterative random forest to find geospatial environmental and Sociodemographic predictors of suicide attempts
Using iterative random forest to find geospatial environmental and Sociodemographic predictors of suicide attempts Open
Introduction Despite a recent global decrease in suicide rates, death by suicide has increased in the United States. It is therefore imperative to identify the risk factors associated with suicide attempts to combat this growing epidemic. …
View article: Addressing the Pediatric Mental Health Crisis: Moving from a Reactive to a Proactive System of Care
Addressing the Pediatric Mental Health Crisis: Moving from a Reactive to a Proactive System of Care Open
View article: Automated, machine learning–based alerts increase epilepsy surgery referrals: A randomized controlled trial
Automated, machine learning–based alerts increase epilepsy surgery referrals: A randomized controlled trial Open
Objective To determine whether automated, electronic alerts increased referrals for epilepsy surgery. Methods We conducted a prospective, randomized controlled trial of a natural language processing–based clinical decision support system e…
View article: Identification of Novel, Replicable Genetic Risk Loci for Suicidal Thoughts and Behaviors Among US Military Veterans
Identification of Novel, Replicable Genetic Risk Loci for Suicidal Thoughts and Behaviors Among US Military Veterans Open
Importance Suicide is a leading cause of death; however, the molecular genetic basis of suicidal thoughts and behaviors (SITB) remains unknown. Objective To identify novel, replicable genomic risk loci for SITB. Design, Setting, and Partic…
View article: Implementation of Machine Learning Pipelines for Clinical Practice: Development and Validation Study
Implementation of Machine Learning Pipelines for Clinical Practice: Development and Validation Study Open
Background Artificial intelligence (AI) technologies, such as machine learning and natural language processing, have the potential to provide new insights into complex health data. Although powerful, these algorithms rarely move from exper…
View article: Using Explainable-AI to Find Geospatial Environmental and Sociodemographic Predictors of Suicide Attempts
Using Explainable-AI to Find Geospatial Environmental and Sociodemographic Predictors of Suicide Attempts Open
Despite a global decrease in suicide rates in recent years, death by suicide has increased in the United States. It is therefore imperative to identify the risk factors associated with suicide attempts in order to combat this growing epide…
View article: Digging deeper into GWAS signal using GRIN implicates additional genes contributing to suicidal behavior
Digging deeper into GWAS signal using GRIN implicates additional genes contributing to suicidal behavior Open
Genome-wide association studies (GWAS) identify genetic variants underlying complex traits but are limited by stringent genome-wide significance thresholds. Here we dramatically relax GWAS stringency by orders of magnitude and apply GRIN (…
View article: Implementation of Machine Learning Pipelines for Clinical Practice (Preprint)
Implementation of Machine Learning Pipelines for Clinical Practice (Preprint) Open
UNSTRUCTURED Artificial Intelligence (AI) technologies, such as machine learning and natural language processing, have the potential to provide new insights into complex health data. While powerful, these algorithms rarely move from exper…
View article: Early identification of epilepsy surgery candidates: A multicenter, machine learning study
Early identification of epilepsy surgery candidates: A multicenter, machine learning study Open
Site-specific machine learning algorithms can identify candidates for epilepsy surgery early in the disease course in diverse practice settings.
View article: Cystic Fibrosis Point of Personalized Detection (CFPOPD): An Interactive Web Application
Cystic Fibrosis Point of Personalized Detection (CFPOPD): An Interactive Web Application Open
Background Despite steady gains in life expectancy, individuals with cystic fibrosis (CF) lung disease still experience rapid pulmonary decline throughout their clinical course, which can ultimately end in respiratory failure. Point-of-car…
View article: A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions
A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions Open
Background: As adolescent suicide rates continue to rise, innovation in risk identification is warranted. Machine learning can identify suicidal individuals based on their language samples. This feasibility pilot was conducted to explore t…
View article: Cystic Fibrosis Point of Personalized Detection (CFPOPD): An Interactive Web Application (Preprint)
Cystic Fibrosis Point of Personalized Detection (CFPOPD): An Interactive Web Application (Preprint) Open
BACKGROUND Despite steady gains in life expectancy, individuals with cystic fibrosis (CF) lung disease still experience rapid pulmonary decline throughout their clinical course, which can ultimately end in respiratory failure. Point-of-ca…
View article: A Machine Learning Approach to Identifying Changes in Suicidal Language
A Machine Learning Approach to Identifying Changes in Suicidal Language Open
Objective With early identification and intervention, many suicidal deaths are preventable. Tools that include machine learning methods have been able to identify suicidal language. This paper examines the persistence of this suicidal lang…
View article: Identifying epilepsy psychiatric comorbidities with machine learning
Identifying epilepsy psychiatric comorbidities with machine learning Open
Machine-learning classifiers of spoken language can reliably identify current or lifetime history of suicidality and depression in people with epilepsy. Data suggest identification of anxiety and bipolar disorders may be achieved with larg…
View article: Dynamic predictive probabilities to monitor rapid cystic fibrosis disease progression
Dynamic predictive probabilities to monitor rapid cystic fibrosis disease progression Open
Cystic fibrosis (CF) is a progressive, genetic disease characterized by frequent, prolonged drops in lung function. Accurately predicting rapid underlying lung‐function decline is essential for clinical decision support and timely interven…
View article: Prospective validation of a machine learning model that uses provider notes to identify candidates for resective epilepsy surgery
Prospective validation of a machine learning model that uses provider notes to identify candidates for resective epilepsy surgery Open
Objective Delay to resective epilepsy surgery results in avoidable disease burden and increased risk of mortality. The objective was to prospectively validate a natural language processing (NLP) application that uses provider notes to assi…
View article: Investigation of bias in an epilepsy machine learning algorithm trained on physician notes
Investigation of bias in an epilepsy machine learning algorithm trained on physician notes Open
Racial disparities in the utilization of epilepsy surgery are well documented, but it is unknown whether a natural language processing ( NLP ) algorithm trained on physician notes would produce biased recommendations for epilepsy presurgic…
View article: Improving Detection of Rapid Cystic Fibrosis Disease Progression–Early Translation of a Predictive Algorithm Into a Point-of-Care Tool
Improving Detection of Rapid Cystic Fibrosis Disease Progression–Early Translation of a Predictive Algorithm Into a Point-of-Care Tool Open
The clinical course of cystic fibrosis (CF) lung disease is marked by acute drops of lung function, defined clinically as rapid decline. As such, lung function is monitored routinely through pulmonary function testing, producing hundreds o…
View article: A Machine Learning Approach to Identifying Future Suicide Risk
A Machine Learning Approach to Identifying Future Suicide Risk Open
View article: Early detection of rapid cystic fibrosis disease progression tailored to point of care: A proof-of-principle study
Early detection of rapid cystic fibrosis disease progression tailored to point of care: A proof-of-principle study Open
Slowing cystic fibrosis (CF) lung disease progression is crucial to survival, but point-of-care technologies aimed at early detection-and possibly prevention-of rapid lung function decline are limited. This proof-of-principle study leverag…
View article: A nonparametric Bayesian method of translating machine learning scores to probabilities in clinical decision support
A nonparametric Bayesian method of translating machine learning scores to probabilities in clinical decision support Open
View article: Phenotypes of Rapid Cystic Fibrosis Lung Disease Progression during Adolescence and Young Adulthood
Phenotypes of Rapid Cystic Fibrosis Lung Disease Progression during Adolescence and Young Adulthood Open
By identifying phenotypes and associated risk factors, timing of interventions may be more precisely targeted for subgroups at highest risk of lung function loss.