Analyses of GWAS signal using GRIN identify additional genes contributing to suicidal behavior.

Genome-wide association studies (GWAS) identify genetic variants underlying complex traits but are limited by stringent genome-wide significance thresholds. We present GRIN (Gene set Refinement through Interacting Networks), which increases confidence in the expanded gene set by retaining genes strongly connected by biological networks when GWAS thresholds are relaxed. GRIN was validated on both simulated interrelated gene sets as well as multiple GWAS traits. From multiple GWAS summary statistics of suicide attempt, a complex phenotype, GRIN identified additional genes that replicated across independent cohorts and retained biologically interrelated genes despite a relaxed significance threshold. We present a conceptual model of how these retained genes interact through neurobiological pathways that may influence suicidal behavior, and identify existing drugs associated with these pathways that would not have been identified under traditional GWAS thresholds. We demonstrate GRIN's utility in boosting GWAS results by increasing the number of true positive genes identified from GWAS results.

Early Identification of Candidates for Epilepsy Surgery: A Multicenter, Machine Learning, Prospective Validation Study.

BACKGROUND AND OBJECTIVES: Epilepsy surgery is often delayed. We previously developed machine learning (ML) models to identify candidates for resective epilepsy surgery earlier in the disease course. In this study, we report the prospective validation. METHODS: In this multicenter, prospective, longitudinal cohort study, random forest models were validated at a pediatric epilepsy center consisting of 2 hospitals and 14 outpatient neurology clinic sites and an adult epilepsy center with 2 hospitals and 27 outpatient neurology clinic sites. The models used neurology visit notes, EEG and MRI reports, visit patterns, hospitalizations, and medication, laboratory, and procedure orders to identify candidates for surgery. The models were trained on historical data up to May 10, 2019. Patients with an ICD-10 diagnosis of epilepsy who visited from May 11, 2019, to May 10, 2020, were screened by the algorithm and assigned surgical candidacy scores. The primary outcome was area under the curve (AUC), which was calculated by comparing scores from patients who underwent epilepsy surgery before November 10, 2020, against scores from nonsurgical patients. Nonsurgical patients' charts were reviewed to determine whether patients with high scores were more likely to be missed surgical candidates. Delay to surgery was defined as the time between the first visit that a surgical candidate was identified by the algorithm and the date of the surgery. RESULTS: A total of 5,285 pediatric and 5,782 adult patients were included to train the ML algorithms. During the study period, 41 children and 23 adults underwent resective epilepsy surgery. In the pediatric cohort, AUC was 0.91 (95% CI 0.87-0.94), positive predictive value (PPV) was 0.08 (0.05-0.10), and negative predictive value (NPV) was 1.00 (0.99-1.00). In the adult cohort, AUC was 0.91 (0.86-0.97), PPV was 0.07 (0.04-0.11), and NPV was 1.00 (0.99-1.00). The models first identified patients at a median of 2.1 years (interquartile range [IQR]: 1.2-4.9 years, maximum: 11.1 years) before their surgery and 1.3 years (IQR: 0.3-4.0 years, maximum: 10.1 years) before their presurgical evaluations. DISCUSSION: ML algorithms can identify surgical candidates earlier in the disease course. Even at specialized epilepsy centers, there is room to shorten the time to surgery. CLASSIFICATION OF EVIDENCE: 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.

High dimensional predictions of suicide risk in 4.2 million US Veterans using ensemble transfer learning.

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 attempt, and overdose diagnoses with varying choices of study design and prediction methodology. Each model used twenty cross-sectional and 190 longitudinal variables observed in eight time intervals covering 7.5 years prior to the time of prediction. Ensembles of seven base models were created and fine-tuned with ten variables expected to change with study design and outcome definition in order to predict suicide and combined outcome in a prospective cohort. The ensemble models achieved c-statistics of 0.73 on 2-year suicide risk and 0.83 on the combined outcome when predicting on a prospective cohort of [Formula: see text] 4.2 M veterans. The ensembles rely on nonlinear base models trained using a matched retrospective nested case-control (Rcc) study cohort and show good calibration across a diversity of subgroups, including risk strata, age, sex, race, and level of healthcare utilization. In addition, a linear Rcc base model provided a rich set of biological predictors, including indicators of suicide, substance use disorder, mental health diagnoses and treatments, hypoxia and vascular damage, and demographics.

Using iterative random forest to find geospatial environmental and Sociodemographic predictors of suicide attempts.

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. In this study, we aim to identify potential risk factors of suicide attempt using geospatial features in an Artificial intelligence framework. Methods: We use iterative Random Forest, an explainable artificial intelligence method, to predict suicide attempts using data from the Million Veteran Program. This cohort incorporated 405,540 patients with 391,409 controls and 14,131 attempts. Our predictive model incorporates multiple climatic features at ZIP-code-level geospatial resolution. We additionally consider demographic features from the American Community Survey as well as the number of firearms and alcohol vendors per 10,000 people to assess the contributions of proximal environment, access to means, and restraint decrease to suicide attempts. In total 1,784 features were included in the predictive model. Results: Our results show that geographic areas with higher concentrations of married males living with spouses are predictive of lower rates of suicide attempts, whereas geographic areas where males are more likely to live alone and to rent housing are predictive of higher rates of suicide attempts. We also identified climatic features that were associated with suicide attempt risk by age group. Additionally, we observed that firearms and alcohol vendors were associated with increased risk for suicide attempts irrespective of the age group examined, but that their effects were small in comparison to the top features. Discussion: Taken together, our findings highlight the importance of social determinants and environmental factors in understanding suicide risk among veterans.

Developmental Epidemiology of Pediatric Anxiety Disorders.

This review summarizes the developmental epidemiology of childhood and adolescent anxiety disorders. It discusses the coronavirus disease of 2019 (COVID-19) pandemic, sex differences, longitudinal course, and stability of anxiety disorders in addition to recurrence and remission. The trajectory of anxiety disorders-whether homotypic (ie, the same anxiety disorder persists over time) or heterotypic (ie, an anxiety disorder shifts to a different diagnosis over time) is discussed with regard to social, generalized, and separation anxiety disorders as well as specific phobia, and panic disorder. Finally, strategies for early recognition, prevention, and treatment of disorders are discussed.

Automated, machine learning-based alerts increase epilepsy surgery referrals: A randomized controlled trial.

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 embedded in the electronic health record (EHR) at 14 pediatric neurology outpatient clinic sites. Children with epilepsy and at least two prior neurology visits were screened by the system prior to their scheduled visit. Patients classified as a potential surgical candidate were randomized 2:1 for their provider to receive an alert or standard of care (no alert). The primary outcome was referral for a neurosurgical evaluation. The likelihood of referral was estimated using a Cox proportional hazards regression model. RESULTS: Between April 2017 and April 2019, at total of 4858 children were screened by the system, and 284 (5.8%) were identified as potential surgical candidates. Two hundred four patients received an alert, and 96 patients received standard care. Median follow-up time was 24 months (range: 12-36 months). Compared to the control group, patients whose provider received an alert were more likely to be referred for a presurgical evaluation (3.1% vs 9.8%; adjusted hazard ratio [HR] = 3.21, 95% confidence interval [CI]: 0.95-10.8; one-sided p = .03). Nine patients (4.4%) in the alert group underwent epilepsy surgery, compared to none (0%) in the control group (one-sided p = .03). SIGNIFICANCE: Machine learning-based automated alerts may improve the utilization of referrals for epilepsy surgery evaluations.

Implementation of Machine Learning Pipelines for Clinical Practice: Development and Validation Study.

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 experimental studies to direct clinical care implementation. OBJECTIVE: We aimed to describe the key components for successful development and integration of two AI technology-based research pipelines for clinical practice. METHODS: We summarized the approach, results, and key learnings from the implementation of the following two systems implemented at a large, tertiary care children's hospital: (1) epilepsy surgical candidate identification (or epilepsy ID) in an ambulatory neurology clinic; and (2) an automated clinical trial eligibility screener (ACTES) for the real-time identification of patients for research studies in a pediatric emergency department. RESULTS: The epilepsy ID system performed as well as board-certified neurologists in identifying surgical candidates (with a sensitivity of 71% and positive predictive value of 77%). The ACTES system decreased coordinator screening time by 12.9%. The success of each project was largely dependent upon the collaboration between machine learning experts, research and operational information technology professionals, longitudinal support from clinical providers, and institutional leadership. CONCLUSIONS: These projects showcase novel interactions between machine learning recommendations and providers during clinical care. Our deployment provides seamless, real-time integration of AI technology to provide decision support and improve patient care.

Early identification of epilepsy surgery candidates: A multicenter, machine learning study.

OBJECTIVES: Epilepsy surgery is underutilized. Automating the identification of potential surgical candidates may facilitate earlier intervention. Our objective was to develop site-specific machine learning (ML) algorithms to identify candidates before they undergo surgery. MATERIALS & METHODS: In this multicenter, retrospective, longitudinal cohort study, ML algorithms were trained on n-grams extracted from free-text neurology notes, EEG and MRI reports, visit codes, medications, procedures, laboratories, and demographic information. Site-specific algorithms were developed at two epilepsy centers: one pediatric and one adult. Cases were defined as patients who underwent resective epilepsy surgery, and controls were patients with epilepsy with no history of surgery. The output of the ML algorithms was the estimated likelihood of candidacy for resective epilepsy surgery. Model performance was assessed using 10-fold cross-validation. RESULTS: There were 5880 children (n = 137 had surgery [2.3%]) and 7604 adults with epilepsy (n = 56 had surgery [0.7%]) included in the study. Pediatric surgical patients could be identified 2.0 years (range: 0-8.6 years) before beginning their presurgical evaluation with AUC =0.76 (95% CI: 0.70-0.82) and PR-AUC =0.13 (95% CI: 0.07-0.18). Adult surgical patients could be identified 1.0 year (range: 0-5.4 years) before beginning their presurgical evaluation with AUC =0.85 (95% CI: 0.78-0.93) and PR-AUC =0.31 (95% CI: 0.14-0.48). By the time patients began their presurgical evaluation, the ML algorithms identified pediatric and adult surgical patients with AUC =0.93 and 0.95, respectively. The mean squared error of the predicted probability of surgical candidacy (Brier scores) was 0.018 in pediatrics and 0.006 in adults. CONCLUSIONS: Site-specific machine learning algorithms can identify candidates for epilepsy surgery early in the disease course in diverse practice settings.

Cystic Fibrosis Point of Personalized Detection (CFPOPD): An Interactive Web Application.

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-care tools for accurate and timely information regarding the risk of rapid decline is essential for clinical decision support. OBJECTIVE: This study aims to translate a novel algorithm for earlier, more accurate prediction of rapid lung function decline in patients with CF into an interactive web-based application that can be integrated within electronic health record systems, via collaborative development with clinicians. METHODS: Longitudinal clinical history, lung function measurements, and time-invariant characteristics were obtained for 30,879 patients with CF who were followed in the US Cystic Fibrosis Foundation Patient Registry (2003-2015). We iteratively developed the application using the R Shiny framework and by conducting a qualitative study with care provider focus groups (N=17). RESULTS: A clinical conceptual model and 4 themes were identified through coded feedback from application users: (1) ambiguity in rapid decline, (2) clinical utility, (3) clinical significance, and (4) specific suggested revisions. These themes were used to revise our application to the currently released version, available online for exploration. This study has advanced the application's potential prognostic utility for monitoring individuals with CF lung disease. Further application development will incorporate additional clinical characteristics requested by the users and also a more modular layout that can be useful for care provider and family interactions. CONCLUSIONS: Our framework for creating an interactive and visual analytics platform enables generalized development of applications to synthesize, model, and translate electronic health data, thereby enhancing clinical decision support and improving care and health outcomes for chronic diseases and disorders. A prospective implementation study is necessary to evaluate this tool's effectiveness regarding increased communication, enhanced shared decision-making, and improved clinical outcomes for patients with CF.

A Feasibility Study Using a Machine Learning Suicide Risk Prediction Model Based on Open-Ended Interview Language in Adolescent Therapy Sessions.

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 this technology's use in adolescent therapy sessions and assess machine learning model performance. METHOD: Natural language processing machine learning models to identify level of suicide risk using a smartphone app were tested in outpatient therapy sessions. Data collection included language samples, depression and suicidality standardized scale scores, and therapist impression of the client's mental state. Previously developed models were used to predict suicidal risk. RESULTS: 267 interviews were collected from 60 students in eight schools by ten therapists, with 29 students indicating suicide or self-harm risk. During external validation, models were trained on suicidal speech samples collected from two separate studies. We found that support vector machines (AUC: 0.75; 95% CI: 0.69-0.81) and logistic regression (AUC: 0.76; 95% CI: 0.70-0.82) lead to good discriminative ability, with an extreme gradient boosting model performing the best (AUC: 0.78; 95% CI: 0.72-0.84). CONCLUSION: Voice collection technology and associated procedures can be integrated into mental health therapists' workflow. Collected language samples could be classified with good discrimination using machine learning methods.

A Machine Learning Approach to Identifying Changes in Suicidal Language.

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 language up to 30 days after discharge from care. METHOD: In a multi-center study, 253 subjects were enrolled into either suicidal or control cohorts. Their responses to standardized instruments and interviews were analyzed using machine learning algorithms. Subjects were re-interviewed approximately 30 days later, and their language was compared to the original language to determine the presence of suicidal ideation. RESULTS: The results show that language characteristics used to classify suicidality at the initial encounter are still present in the speech 30 days later (AUC = 89% (95% CI: 85-95%), p < .0001) and that algorithms trained on the second interviews could also identify the subjects that produced the first interviews (AUC = 85% (95% CI: 81-90%), p < .0001). CONCLUSIONS: This approach explores the stability of suicidal language. When using advanced computational methods, the results show that a patient's language is similar 30 days after first captured, while responses to standard measures change. This can be useful when developing methods that identify the data-based phenotype of a subject.

Identifying epilepsy psychiatric comorbidities with machine learning.

OBJECTIVE: People with epilepsy are at increased risk for mental health comorbidities. Machine-learning methods based on spoken language can detect suicidality in adults. This study's purpose was to use spoken words to create machine-learning classifiers that identify current or lifetime history of comorbid psychiatric conditions in teenagers and young adults with epilepsy. MATERIALS AND METHODS: Eligible participants were >12 years old with epilepsy. All participants were interviewed using the Mini International Neuropsychiatric Interview (MINI) or the MINI Kid Tracking and asked five open-ended conversational questions. N-grams and Linguistic Inquiry and Word Count (LIWC) word categories were used to construct machine learning classification models from language harvested from interviews. Data were analyzed for four individual MINI identified disorders and for three mutually exclusive groups: participants with no psychiatric disorders, participants with non-suicidal psychiatric disorders, and participants with any degree of suicidality. Performance was measured using areas under the receiver operating characteristic curve (AROCs). RESULTS: Classifiers were constructed from 227 interviews with 122 participants (7.5 ± 3.1 minutes and 454 ± 299 words). AROCs for models differentiating the non-overlapping groups and individual disorders ranged 57%-78% (many with P < .02). DISCUSSION AND CONCLUSION: 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 larger data sets. Machine-learning analysis of spoken language can be promising as a useful screening alternative when traditional approaches are unwieldy (eg, telephone calls, primary care offices, school health clinics).

Dynamic predictive probabilities to monitor rapid cystic fibrosis disease progression.

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 intervention. Determining whether an individual is experiencing a period of rapid decline is complicated due to its heterogeneous timing and extent, and error component of the measured lung function. We construct individualized predictive probabilities for "nowcasting" rapid decline. We assume each patient's true longitudinal lung function, S(t), follows a nonlinear, nonstationary stochastic process, and accommodate between-patient heterogeneity through random effects. Corresponding lung-function decline at time t is defined as the rate of change, S'(t). We predict S'(t) conditional on observed covariate and measurement history by modeling a measured lung function as a noisy version of S(t). The method is applied to data on 30 879 US CF Registry patients. Results are contrasted with a currently employed decision rule using single-center data on 212 individuals. Rapid decline is identified earlier using predictive probabilities than the center's currently employed decision rule (mean difference: 0.65 years; 95% confidence interval (CI): 0.41, 0.89). We constructed a bootstrapping algorithm to obtain CIs for predictive probabilities. We illustrate real-time implementation with R Shiny. Predictive accuracy is investigated using empirical simulations, which suggest this approach more accurately detects peak decline, compared with a uniform threshold of rapid decline. Median area under the ROC curve estimates (Q1-Q3) were 0.817 (0.814-0.822) and 0.745 (0.741-0.747), respectively, implying reasonable accuracy for both. This article demonstrates how individualized rate of change estimates can be coupled with probabilistic predictive inference and implementation for a useful medical-monitoring approach.

Prospective validation of a machine learning model that uses provider notes to identify candidates for resective epilepsy surgery.

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 assign epilepsy surgery candidacy scores. METHODS: The application was trained on notes from (1) patients with a diagnosis of epilepsy and a history of resective epilepsy surgery and (2) patients who were seizure-free without surgery. The testing set included all patients with unknown surgical candidacy status and an upcoming neurology visit. Training and testing sets were updated weekly for 1 year. One- to three-word phrases contained in patients' notes were used as features. Patients prospectively identified by the application as candidates for surgery were manually reviewed by two epileptologists. Performance metrics were defined by comparing NLP-derived surgical candidacy scores with surgical candidacy status from expert chart review. RESULTS: The training set was updated weekly and included notes from a mean of 519 ± 67 patients. The area under the receiver operating characteristic curve (AUC) from 10-fold cross-validation was 0.90 ± 0.04 (range = 0.83-0.96) and improved by 0.002 per week (P < .001) as new patients were added to the training set. Of the 6395 patients who visited the neurology clinic, 4211 (67%) were evaluated by the model. The prospective AUC on this test set was 0.79 (95% confidence interval [CI] = 0.62-0.96). Using the optimal surgical candidacy score threshold, sensitivity was 0.80 (95% CI = 0.29-0.99), specificity was 0.77 (95% CI = 0.64-0.88), positive predictive value was 0.25 (95% CI = 0.07-0.52), and negative predictive value was 0.98 (95% CI = 0.87-1.00). The number needed to screen was 5.6. SIGNIFICANCE: An electronic health record-integrated NLP application can accurately assign surgical candidacy scores to patients in a clinical setting.

Investigation of bias in an epilepsy machine learning algorithm trained on physician notes.

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 presurgical evaluations. To assess this, an NLP algorithm was trained to identify potential surgical candidates using 1097 notes from 175 epilepsy patients with a history of resective epilepsy surgery and 268 patients who achieved seizure freedom without surgery (total N = 443 patients). The model was tested on 8340 notes from 3776 patients with epilepsy whose surgical candidacy status was unknown (2029 male, 1747 female, median age = 9 years; age range = 0-60 years). Multiple linear regression using demographic variables as covariates was used to test for correlations between patient race and surgical candidacy scores. After accounting for other demographic and socioeconomic variables, patient race, gender, and primary language did not influence surgical candidacy scores (P > .35 for all). Higher scores were given to patients >18 years old who traveled farther to receive care, and those who had a higher family income and public insurance (P < .001, .001, .001, and .01, respectively). Demographic effects on surgical candidacy scores appeared to reflect patterns in patient referrals.

Improving Detection of Rapid Cystic Fibrosis Disease Progression-Early Translation of a Predictive Algorithm Into a Point-of-Care Tool.

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 of measurements over the lifespan of an individual patient. Point-of-care technologies aimed at improving detection of rapid decline have been limited. Our aim in this early translational study is to develop and translate a predictive algorithm into a prototype prognostic tool for improved detection of rapid decline. The predictive algorithm was developed, validated and checked for 6-month, 1-year, and 2-year forecast accuracies using data on demographic and clinical characteristics from 30 879 patients aged 6 years and older who were followed in the U.S. Cystic Fibrosis Foundation Patient Registry from 2003 to 2015. Predictions of rapid decline based on the algorithm were compared to a detection algorithm currently being used at a CF center with 212 patients who received care between 2012-2017. The algorithm was translated into a prototype web application using RShiny, which resulted from an iterative development and refinement based on clinician feedback. The study showed that the algorithm had excellent predictive accuracy and earlier detection of rapid decline, compared to the current approach, and yielded a prototype platform with the potential to serve as a viable point-of-care tool. Future work includes implementation of this clinical prototype, which will be evaluated prospectively under real-world settings, with the aim of improving the pre-visit planning process for CF point of care. Likely extensions to other point-of-care settings are discussed.

A nonparametric Bayesian method of translating machine learning scores to probabilities in clinical decision support.

BACKGROUND: Probabilistic assessments of clinical care are essential for quality care. Yet, machine learning, which supports this care process has been limited to categorical results. To maximize its usefulness, it is important to find novel approaches that calibrate the ML output with a likelihood scale. Current state-of-the-art calibration methods are generally accurate and applicable to many ML models, but improved granularity and accuracy of such methods would increase the information available for clinical decision making. This novel non-parametric Bayesian approach is demonstrated on a variety of data sets, including simulated classifier outputs, biomedical data sets from the University of California, Irvine (UCI) Machine Learning Repository, and a clinical data set built to determine suicide risk from the language of emergency department patients. RESULTS: The method is first demonstrated on support-vector machine (SVM) models, which generally produce well-behaved, well understood scores. The method produces calibrations that are comparable to the state-of-the-art Bayesian Binning in Quantiles (BBQ) method when the SVM models are able to effectively separate cases and controls. However, as the SVM models' ability to discriminate classes decreases, our approach yields more granular and dynamic calibrated probabilities comparing to the BBQ method. Improvements in granularity and range are even more dramatic when the discrimination between the classes is artificially degraded by replacing the SVM model with an ad hoc k-means classifier. CONCLUSIONS: The method allows both clinicians and patients to have a more nuanced view of the output of an ML model, allowing better decision making. The method is demonstrated on simulated data, various biomedical data sets and a clinical data set, to which diverse ML methods are applied. Trivially extending the method to (non-ML) clinical scores is also discussed.

Phenotypes of Rapid Cystic Fibrosis Lung Disease Progression during Adolescence and Young Adulthood.

RATIONALE: Individuals with cystic fibrosis are at risk for prolonged drops in lung function, clinically termed rapid decline, during discreet periods of the disease. OBJECTIVES: To identify phenotypes of rapid pulmonary decline and determine how these phenotypes are related to patient characteristics. METHODS: A longitudinal cohort study of patients with cystic fibrosis aged 6-21 years was conducted using the Cystic Fibrosis Foundation Patient Registry. A statistical approach for clustering longitudinal profiles, sparse functional principal components analysis, was used to classify patients into distinct phenotypes by evaluating trajectories of FEV1 decline. Phenotypes were compared with respect to baseline and mortality characteristics. MEASUREMENTS AND MAIN RESULTS: Three distinct phenotypes of rapid decline were identified, corresponding to early, middle, and late timing of maximal FEV1 loss, in the overall cohort (n = 18,387). The majority of variation (first functional principal component, 94%) among patient profiles was characterized by differences in mean longitudinal FEV1 trajectories. Average degree of rapid decline was similar among phenotypes (roughly -3% predicted/yr); however, average timing differed, with early, middle, and late phenotypes experiencing rapid decline at 12.9, 16.3, and 18.5 years of age, respectively. Individuals with the late phenotype had the highest initial FEV1 but experienced the greatest loss of lung function. The early phenotype was more likely to have respiratory infections and acute exacerbations at baseline or to develop them subsequently, compared with other phenotypes. CONCLUSIONS: By identifying phenotypes and associated risk factors, timing of interventions may be more precisely targeted for subgroups at highest risk of lung function loss.