A comparative study of large language model-based zero-shot inference and task-specific supervised classification of breast cancer pathology reports.

OBJECTIVE: Although supervised machine learning is popular for information extraction from clinical notes, creating large annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs could reduce the need for large-scale data annotations. MATERIALS AND METHODS: We curated a dataset of 769 breast cancer pathology reports, manually labeled with 12 categories, to compare zero-shot classification capability of the following LLMs: GPT-4, GPT-3.5, Starling, and ClinicalCamel, with task-specific supervised classification performance of 3 models: random forests, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model. RESULTS: Across all 12 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, LSTM-Att (average macro F1-score of 0.86 vs 0.75), with advantage on tasks with high label imbalance. Other LLMs demonstrated poor performance. Frequent GPT-4 error categories included incorrect inferences from multiple samples and from history, and complex task design, and several LSTM-Att errors were related to poor generalization to the test set. DISCUSSION: On tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of data labeling. However, if the use of LLMs is prohibitive, the use of simpler models with large annotated datasets can provide comparable results. CONCLUSIONS: GPT-4 demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for large annotated datasets. This may increase the utilization of NLP-based variables and outcomes in clinical studies.

Real-world effectiveness of ustekinumab and vedolizumab in TNF-exposed pediatric patients with ulcerative colitis.

OBJECTIVES: Vedolizumab (VDZ) and ustekinumab (UST) are second-line treatments in pediatric patients with ulcerative colitis (UC) refractory to antitumor necrosis factor (anti-TNF) therapy. Pediatric studies comparing the effectiveness of these medications are lacking. Using a registry from ImproveCareNow (ICN), a global research network in pediatric inflammatory bowel disease, we compared the effectiveness of UST and VDZ in anti-TNF refractory UC. METHODS: We performed a propensity-score weighted regression analysis to compare corticosteroid-free clinical remission (CFCR) at 6 months from starting second-line therapy. Sensitivity analyses tested the robustness of our findings to different ways of handling missing outcome data. Secondary analyses evaluated alternative proxies of response and infection risk. RESULTS: Our cohort included 262 patients on VDZ and 74 patients on UST. At baseline, the two groups differed on their mean pediatric UC activity index (PUCAI) (p = 0.03) but were otherwise similar. At Month 6, 28.3% of patients on VDZ and 25.8% of those on UST achieved CFCR (p = 0.76). Our primary model showed no difference in CFCR (odds ratio: 0.81; 95% confidence interval [CI]: 0.41-1.59) (p = 0.54). The time to biologic discontinuation was similar in both groups (hazard ratio: 1.26; 95% CI: 0.76-2.08) (p = 0.36), with the reference group being VDZ, and we found no differences in clinical response, growth parameters, hospitalizations, surgeries, infections, or malignancy risk. Sensitivity analyses supported these findings of similar effectiveness. CONCLUSIONS: UST and VDZ are similarly effective for inducing clinical remission in anti-TNF refractory UC in pediatric patients. Providers should consider safety, tolerability, cost, and comorbidities when deciding between these therapies.

Accurate, Robust, and Scalable Machine Abstraction of Mayo Endoscopic Subscores From Colonoscopy Reports.

BACKGROUND: The Mayo endoscopic subscore (MES) is an important quantitative measure of disease activity in ulcerative colitis. Colonoscopy reports in routine clinical care usually characterize ulcerative colitis disease activity using free text description, limiting their utility for clinical research and quality improvement. We sought to develop algorithms to classify colonoscopy reports according to their MES. METHODS: We annotated 500 colonoscopy reports from 2 health systems. We trained and evaluated 4 classes of algorithms. Our primary outcome was accuracy in identifying scorable reports (binary) and assigning an MES (ordinal). Secondary outcomes included learning efficiency, generalizability, and fairness. RESULTS: Automated machine learning models achieved 98% and 97% accuracy on the binary and ordinal prediction tasks, outperforming other models. Binary models trained on the University of California, San Francisco data alone maintained accuracy (96%) on validation data from Zuckerberg San Francisco General. When using 80% of the training data, models remained accurate for the binary task (97% [n = 320]) but lost accuracy on the ordinal task (67% [n = 194]). We found no evidence of bias by gender (P = .65) or area deprivation index (P = .80). CONCLUSIONS: We derived a highly accurate pair of models capable of classifying reports by their MES and recognizing when to abstain from prediction. Our models were generalizable on outside institution validation. There was no evidence of algorithmic bias. Our methods have the potential to enable retrospective studies of treatment effectiveness, prospective identification of patients meeting study criteria, and quality improvement efforts in inflammatory bowel diseases.

Our accurate pair of models automatically classify colonoscopy reports by Mayo endoscopic subscore and abstain from prediction appropriately. Our methods can enable large-scale electronic health record studies of treatment effectiveness, prospective identification of patients for clinical trials, and quality improvement efforts in ulcerative colitis.

A comparative study of zero-shot inference with large language models and supervised modeling in breast cancer pathology classification.

Although supervised machine learning is popular for information extraction from clinical notes, creating large, annotated datasets requires extensive domain expertise and is time-consuming. Meanwhile, large language models (LLMs) have demonstrated promising transfer learning capability. In this study, we explored whether recent LLMs can reduce the need for large-scale data annotations. We curated a manually labeled dataset of 769 breast cancer pathology reports, labeled with 13 categories, to compare zero-shot classification capability of the GPT-4 model and the GPT-3.5 model with supervised classification performance of three model architectures: random forests classifier, long short-term memory networks with attention (LSTM-Att), and the UCSF-BERT model. Across all 13 tasks, the GPT-4 model performed either significantly better than or as well as the best supervised model, the LSTM-Att model (average macro F1 score of 0.83 vs. 0.75). On tasks with a high imbalance between labels, the differences were more prominent. Frequent sources of GPT-4 errors included inferences from multiple samples and complex task design. On complex tasks where large annotated datasets cannot be easily collected, LLMs can reduce the burden of large-scale data labeling. However, if the use of LLMs is prohibitive, the use of simpler supervised models with large annotated datasets can provide comparable results. LLMs demonstrated the potential to speed up the execution of clinical NLP studies by reducing the need for curating large annotated datasets. This may increase the utilization of NLP-based variables and outcomes in observational clinical studies.

Sequential regression and simulation: a method for estimating causal effects from heterogeneous clinical trials without a common control group.

BACKGROUND: The advent of clinical trial data sharing platforms has created opportunities for making new discoveries and answering important questions using already collected data. However, existing methods for meta-analyzing these data require the presence of shared control groups across studies, significantly limiting the number of questions that can be confidently addressed. We sought to develop a method for meta-analyzing potentially heterogeneous clinical trials even in the absence of a common control group. METHODS: This work was conducted within the context of a broader effort to study comparative efficacy in Crohn's disease. Following a search of clnicaltrials.gov we obtained access to the individual participant data from nine trials of FDA-approved treatments in Crohn's Disease (N = 3392). We developed a method involving sequences of regression and simulation to separately model the placebo- and drug-attributable effects, and to simulate head-to-head trials against an appropriately normalized background. We validated this method by comparing the outcome of a simulated trial comparing the efficacies of adalimumab and ustekinumab against the recently published results of SEAVUE, an actual head-to-head trial of these drugs. This study was pre-registered on PROSPERO (#157,827) prior to the completion of SEAVUE. RESULTS: Using our method of sequential regression and simulation, we compared the week eight outcomes of two virtual cohorts subject to the same patient selection criteria as SEAVUE and treated with adalimumab or ustekinumab. Our primary analysis replicated the corresponding published results from SEAVUE (p = 0.9). This finding proved stable under multiple sensitivity analyses. CONCLUSIONS: This new method may help reduce the bias of individual participant data meta-analyses, expand the scope of what can be learned from these already-collected data, and reduce the costs of obtaining high-quality evidence to guide patient care.

ALK Inhibitor Treatment Patterns and Outcomes in Real-World Patients with ALK-Positive Non-Small-Cell Lung Cancer: A Retrospective Cohort Study.

BACKGROUND: Randomized trials have demonstrated that anaplastic lymphoma kinase (ALK) tyrosine kinase inhibitors (TKIs) can be safe and efficacious treatments for patients with ALK-positive advanced non-small-cell lung cancer (aNSCLC). However, their safety, tolerability, effectiveness, and patterns of use in real-world patients remain understudied. OBJECTIVE: We sought to assess the overall treatment pattern characteristics, safety, and effectiveness outcomes of real-world patients with ALK-positive aNSCLC receiving ALK TKIs. PATIENTS AND METHODS: This retrospective cohort study using electronic health record data included adult patients with ALK-positive aNSCLC receiving ALK TKIs between January 2012 and November 2021 at a large tertiary medical center, University of California, San Francisco (UCSF), with alectinib or crizotinib as the initial ALK TKI therapy. Our primary endpoints included the incidence of treatment changes (treatment dose adjustments, interruptions, and discontinuations) during the initial ALK TKI treatment, the count and type of subsequent treatments, rates of serious adverse events (sAEs), and major adverse events (mAEs) leading to any ALK TKI treatment changes. Secondary endpoints included the hazard ratios (HRs) for median mAE-free survival (mAEFS), real-world progression-free survival (rwPFS), and overall survival (OS) when comparing alectinib with crizotinib. RESULTS: The cohort consisted of 117 adult patients (70 alectinib and 47 crizotinib) with ALK-positive aNSCLC, with 24.8%, 17.9%, and 6.0% experiencing treatment dose adjustments, interruptions, and discontinuation, respectively. Of the 73 patients whose ALK TKI treatments were discontinued, 68 received subsequent treatments including newer generations of ALK TKIs, immune checkpoint inhibitors, and chemotherapies. The most common mAEs were rash (9.9%) and bradycardia (7.0%) for alectinib and liver toxicity (19.1%) for crizotinib. The most common sAEs were pericardial effusion (5.6%) and pleural effusion (5.6%) for alectinib and pulmonary embolism (6.4%) for crizotinib. Patients receiving alectinib versus crizotinib as their first ALK TKI treatment experienced significantly prolonged median rwPFS (29.3 versus 10.4 months) with an HR of 0.38 (95% CI 0.21-0.67), while prolonged median mAEFS (not reached versus 91.3 months) and OS (54.1 versus 45.8 months) were observed in patients receiving alectinib versus crizotinib but did not reach statistical significance. Yet, it is worth noting that there was a high degree of cross-over post-progression, which could significantly confound the overall survival measures. CONCLUSIONS: We found that ALK TKIs were highly tolerable, and alectinib was associated with favorable survival outcomes with longer time to adverse events (AE) requiring medical interventions, disease progression, and death, in the context of real-world use. Proactive monitoring for adverse events such as rash, bradycardia, and hepatotoxicity may help further promote the safe and optimal use of ALK TKIs in the treatment of patients with aNSCLC.

Assessment of valvular function in over 47,000 people using deep learning-based flow measurements.

Valvular heart disease is associated with a high global burden of disease. Even mild aortic stenosis confers increased morbidity and mortality, prompting interest in understanding normal variation in valvular function at scale. We developed a deep learning model to study velocity-encoded magnetic resonance imaging in 47,223 UK Biobank participants. We calculated eight traits, including peak velocity, mean gradient, aortic valve area, forward stroke volume, mitral and aortic regurgitant volume, greatest average velocity, and ascending aortic diameter. We then computed sex-stratified reference ranges for these phenotypes in up to 31,909 healthy individuals. In healthy individuals, we found an annual decrement of 0.03cm 2 in the aortic valve area. Participants with mitral valve prolapse had a 1 standard deviation [SD] higher mitral regurgitant volume (P=9.6 × 10 -12 ), and those with aortic stenosis had a 4.5 SD-higher mean gradient (P=1.5 × 10 -431 ), validating the derived phenotypes' associations with clinical disease. Greater levels of ApoB, triglycerides, and Lp(a) assayed nearly 10 years prior to imaging were associated with higher gradients across the aortic valve. Metabolomic profiles revealed that increased glycoprotein acetyls were also associated with an increased aortic valve mean gradient (0.92 SD, P=2.1 x 10 -22 ). Finally, velocity-derived phenotypes were risk markers for aortic and mitral valve surgery even at thresholds below what is considered relevant disease currently. Using machine learning to quantify the rich phenotypic data of the UK Biobank, we report the largest assessment of valvular function and cardiovascular disease in the general population.

DeepHeme: A generalizable, bone marrow classifier with hematopathologist-level performance.

Morphology-based classification of cells in the bone marrow aspirate (BMA) is a key step in the diagnosis and management of hematologic malignancies. However, it is time-intensive and must be performed by expert hematopathologists and laboratory professionals. We curated a large, high-quality dataset of 41,595 hematopathologist consensus-annotated single-cell images extracted from BMA whole slide images (WSIs) containing 23 morphologic classes from the clinical archives of the University of California, San Francisco. We trained a convolutional neural network, DeepHeme, to classify images in this dataset, achieving a mean area under the curve (AUC) of 0.99. DeepHeme was then externally validated on WSIs from Memorial Sloan Kettering Cancer Center, with a similar AUC of 0.98, demonstrating robust generalization. When compared to individual hematopathologists from three different top academic medical centers, the algorithm outperformed all three. Finally, DeepHeme reliably identified cell states such as mitosis, paving the way for image-based quantification of mitotic index in a cell-specific manner, which may have important clinical applications.

Creation of an ustekinumab external control arm for Crohn's disease using electronic health records data: A pilot study.

BACKGROUND: Randomized trials are the gold-standard for clinical evidence generation, but they can sometimes be limited by infeasibility and unclear generalizability to real-world practice. External control arm (ECA) studies may help address this evidence gaps by constructing retrospective cohorts that closely emulate prospective ones. Experience in constructing these outside the context of rare diseases or cancer is limited. We piloted an approach for developing an ECA in Crohn's disease using electronic health records (EHR) data. METHODS: We queried EHR databases and manually screened records at the University of California, San Francisco to identify patients meeting the eligibility criteria of TRIDENT, a recently completed interventional trial involving an ustekinumab reference arm. We defined timepoints to balance missing data and bias. We compared imputation models by their impacts on cohort membership and outcomes. We assessed the accuracy of algorithmic data curation against manual review. Lastly, we assessed disease activity following treatment with ustekinumab. RESULTS: Screening identified 183 patients. 30% of the cohort had missing baseline data. Nonetheless, cohort membership and outcomes were robust to the method of imputation. Algorithms for ascertaining non-symptom-based elements of disease activity using structured data were accurate against manual review. The cohort consisted of 56 patients, exceeding planned enrollment in TRIDENT. 34% of the cohort was in steroid-free remission at week 24. CONCLUSION: We piloted an approach for creating an ECA in Crohn's disease from EHR data by using a combination of informatics and manual methods. However, our study reveals significant missing data when standard-of-care clinical data are repurposed. More work will be needed to improve the alignment of trial design with typical patterns of clinical practice, and thereby enable a future of more robust ECAs in chronic diseases like Crohn's disease.

Predictive Models for Length of Stay and Discharge Disposition in Elective Spine Surgery: Development, Validation, and Comparison to the ACS NSQIP Risk Calculator.

STUDY DESIGN: A retrospective study at a single academic institution. OBJECTIVE: The purpose of this study is to utilize machine learning to predict hospital length of stay (LOS) and discharge disposition following adult elective spine surgery, and to compare performance metrics of machine learning models to the American College of Surgeon's National Surgical Quality Improvement Program's (ACS NSQIP) prediction calculator. SUMMARY OF BACKGROUND DATA: A total of 3678 adult patients undergoing elective spine surgery between 2014 and 2019, acquired from the electronic health record. METHODS: Patients were divided into three stratified cohorts: cervical degenerative, lumbar degenerative, and adult spinal deformity groups. Predictive variables included demographics, body mass index, surgical region, surgical invasiveness, surgical approach, and comorbidities. Regression, classification trees, and least absolute shrinkage and selection operator (LASSO) were used to build predictive models. Validation of the models was conducted on 16% of patients (N=587), using area under the receiver operator curve (AUROC), sensitivity, specificity, and correlation. Patient data were manually entered into the ACS NSQIP online risk calculator to compare performance. Outcome variables were discharge disposition (home vs. rehabilitation) and LOS (days). RESULTS: Of 3678 patients analyzed, 51.4% were male (n=1890) and 48.6% were female (n=1788). The average LOS was 3.66 days. In all, 78% were discharged home and 22% discharged to rehabilitation. Compared with NSQIP (Pearson R2 =0.16), the predictions of poisson regression ( R2 =0.29) and LASSO ( R2 =0.29) models were significantly more correlated with observed LOS ( P =0.025 and 0.004, respectively). Of the models generated to predict discharge location, logistic regression yielded an AUROC of 0.79, which was statistically equivalent to the AUROC of 0.75 for NSQIP ( P =0.135). CONCLUSION: The predictive models developed in this study can enable accurate preoperative estimation of LOS and risk of rehabilitation discharge for adult patients undergoing elective spine surgery. The demonstrated models exhibited better performance than NSQIP for prediction of LOS and equivalent performance to NSQIP for prediction of discharge location.

Trans-channel fluorescence learning improves high-content screening for Alzheimer's disease therapeutics.

In microscopy-based drug screens, fluorescent markers carry critical information on how compounds affect different biological processes. However, practical considerations, such as the labor and preparation formats needed to produce different image channels, hinders the use of certain fluorescent markers. Consequently, completed screens may lack biologically informative but experimentally impractical markers. Here, we present a deep learning method for overcoming these limitations. We accurately generated predicted fluorescent signals from other related markers and validated this new machine learning (ML) method on two biologically distinct datasets. We used the ML method to improve the selection of biologically active compounds for Alzheimer's disease (AD) from a completed high-content high-throughput screen (HCS) that had only contained the original markers. The ML method identified novel compounds that effectively blocked tau aggregation, which had been missed by traditional screening approaches unguided by ML. The method improved triaging efficiency of compound rankings over conventional rankings by raw image channels. We reproduced this ML pipeline on a biologically independent cancer-based dataset, demonstrating its generalizability. The approach is disease-agnostic and applicable across diverse fluorescence microscopy datasets.

Postoperative delirium prediction using machine learning models and preoperative electronic health record data.

BACKGROUND: Accurate, pragmatic risk stratification for postoperative delirium (POD) is necessary to target preventative resources toward high-risk patients. Machine learning (ML) offers a novel approach to leveraging electronic health record (EHR) data for POD prediction. We sought to develop and internally validate a ML-derived POD risk prediction model using preoperative risk features, and to compare its performance to models developed with traditional logistic regression. METHODS: This was a retrospective analysis of preoperative EHR data from 24,885 adults undergoing a procedure requiring anesthesia care, recovering in the main post-anesthesia care unit, and staying in the hospital at least overnight between December 2016 and December 2019 at either of two hospitals in a tertiary care health system. One hundred fifteen preoperative risk features including demographics, comorbidities, nursing assessments, surgery type, and other preoperative EHR data were used to predict postoperative delirium (POD), defined as any instance of Nursing Delirium Screening Scale ≥2 or positive Confusion Assessment Method for the Intensive Care Unit within the first 7 postoperative days. Two ML models (Neural Network and XGBoost), two traditional logistic regression models ("clinician-guided" and "ML hybrid"), and a previously described delirium risk stratification tool (AWOL-S) were evaluated using the area under the receiver operating characteristic curve (AUC-ROC), sensitivity, specificity, positive likelihood ratio, and positive predictive value. Model calibration was assessed with a calibration curve. Patients with no POD assessments charted or at least 20% of input variables missing were excluded. RESULTS: POD incidence was 5.3%. The AUC-ROC for Neural Net was 0.841 [95% CI 0. 816-0.863] and for XGBoost was 0.851 [95% CI 0.827-0.874], which was significantly better than the clinician-guided (AUC-ROC 0.763 [0.734-0.793], p < 0.001) and ML hybrid (AUC-ROC 0.824 [0.800-0.849], p < 0.001) regression models and AWOL-S (AUC-ROC 0.762 [95% CI 0.713-0.812], p < 0.001). Neural Net, XGBoost, and ML hybrid models demonstrated excellent calibration, while calibration of the clinician-guided and AWOL-S models was moderate; they tended to overestimate delirium risk in those already at highest risk. CONCLUSION: Using pragmatically collected EHR data, two ML models predicted POD in a broad perioperative population with high discrimination. Optimal application of the models would provide automated, real-time delirium risk stratification to improve perioperative management of surgical patients at risk for POD.

Case-control study of the association of chronic acid suppression and social determinants of health with COVID-19 infection.

Acid suppressants are widely-used classes of medications linked to increased risks of aerodigestive infections. Prior studies of these medications as potentially reversible risk factors for COVID-19 have been conflicting. We aimed to determine the impact of chronic acid suppression use on COVID-19 infection risk while simultaneously evaluating the influence of social determinants of health to validate known and discover novel risk factors. We assessed the association of chronic acid suppression with incident COVID-19 in a 1:1 case-control study of 900 patients tested across three academic medical centers in California, USA. Medical comorbidities and history of chronic acid suppression use were manually extracted from health records by physicians following a pre-specified protocol. Socio-behavioral factors by geomapping publicly-available data to patient zip codes were incorporated. We identified no evidence to support an association between chronic acid suppression and COVID-19 (adjusted odds ratio 1.04, 95% CI 0.92-1.17, P = 0.515). However, several medical and social features were positive (Latinx ethnicity, BMI ≥ 30, dementia, public transportation use, month of the pandemic) and negative (female sex, concurrent solid tumor, alcohol use disorder) predictors of new infection. These findings demonstrate the value of integrating publicly-available databases with medical data to identify critical features of communicable diseases.

Opportunities and Challenges in Democratizing Immunology Datasets.

The field of immunology is rapidly progressing toward a systems-level understanding of immunity to tackle complex infectious diseases, autoimmune conditions, cancer, and beyond. In the last couple of decades, advancements in data acquisition techniques have presented opportunities to explore untapped areas of immunological research. Broad initiatives are launched to disseminate the datasets siloed in the global, federated, or private repositories, facilitating interoperability across various research domains. Concurrently, the application of computational methods, such as network analysis, meta-analysis, and machine learning have propelled the field forward by providing insight into salient features that influence the immunological response, which was otherwise left unexplored. Here, we review the opportunities and challenges in democratizing datasets, repositories, and community-wide knowledge sharing tools. We present use cases for repurposing open-access immunology datasets with advanced machine learning applications and more.

Explanatory Model of Dry Eye Disease Using Health and Nutrition Examinations: Machine Learning and Network-Based Factor Analysis From a National Survey.

BACKGROUND: Dry eye disease (DED) is a complex disease of the ocular surface, and its associated factors are important for understanding and effectively treating DED. OBJECTIVE: This study aimed to provide an integrative and personalized model of DED by making an explanatory model of DED using as many factors as possible from the Korea National Health and Nutrition Examination Survey (KNHANES) data. METHODS: Using KNHANES data for 2012 (4391 sample cases), a point-based scoring system was created for ranking factors associated with DED and assessing patient-specific DED risk. First, decision trees and lasso were used to classify continuous factors and to select important factors, respectively. Next, a survey-weighted multiple logistic regression was trained using these factors, and points were assigned using the regression coefficients. Finally, network graphs of partial correlations between factors were utilized to study the interrelatedness of DED-associated factors. RESULTS: The point-based model achieved an area under the curve of 0.70 (95% CI 0.61-0.78), and 13 of 78 factors considered were chosen. Important factors included sex (+9 points for women), corneal refractive surgery (+9 points), current depression (+7 points), cataract surgery (+7 points), stress (+6 points), age (54-66 years; +4 points), rhinitis (+4 points), lipid-lowering medication (+4 points), and intake of omega-3 (0.43%-0.65% kcal/day; -4 points). Among these, the age group 54 to 66 years had high centrality in the network, whereas omega-3 had low centrality. CONCLUSIONS: Integrative understanding of DED was possible using the machine learning-based model and network-based factor analysis. This method for finding important risk factors and identifying patient-specific risk could be applied to other multifactorial diseases.

Accuracy of medical billing data against the electronic health record in the measurement of colorectal cancer screening rates.

OBJECTIVE: Medical billing data are an attractive source of secondary analysis because of their ease of use and potential to answer population-health questions with statistical power. Although these datasets have known susceptibilities to biases, the degree to which they can distort the assessment of quality measures such as colorectal cancer screening rates are not widely appreciated, nor are their causes and possible solutions. METHODS: Using a billing code database derived from our institution's electronic health records, we estimated the colorectal cancer screening rate of average-risk patients aged 50-74 years seen in primary care or gastroenterology clinic in 2016-2017. 200 records (150 unscreened, 50 screened) were sampled to quantify the accuracy against manual review. RESULTS: Out of 4611 patients, an analysis of billing data suggested a 61% screening rate, an estimate that matches the estimate by the Centers for Disease Control. Manual review revealed a positive predictive value of 96% (86%-100%), negative predictive value of 21% (15%-29%) and a corrected screening rate of 85% (81%-90%). Most false negatives occurred due to examinations performed outside the scope of the database-both within and outside of our institution-but 21% of false negatives fell within the database's scope. False positives occurred due to incomplete examinations and inadequate bowel preparation. Reasons for screening failure include ordered but incomplete examinations (48%), lack of or incorrect documentation by primary care (29%) including incorrect screening intervals (13%) and patients declining screening (13%). CONCLUSIONS: Billing databases are prone to substantial bias that may go undetected even in the presence of confirmatory external estimates. Caution is recommended when performing population-level inference from these data. We propose several solutions to improve the use of these data for the assessment of healthcare quality.

Corticosteroid use is not associated with improved outcomes in acute exacerbation of IPF.

BACKGROUND AND OBJECTIVE: AE-IPF has profound prognostic implications, preceding approximately half of all IPF-related deaths. Despite this clinical significance, there are limited data to guide management decisions. Corticosteroids remain the mainstay of treatment despite a lack of strong supporting evidence and mounting concern that they may be harmful. We assessed the impact of corticosteroid therapy on in-hospital mortality in AE-IPF patients. METHODS: AE-IPF subjects were retrospectively identified in the UCSF medical centre's electronic health records from 1 January 2010 to 1 August 2018 using a code-based algorithm followed by case validation. The relationship between corticosteroid treatment and in-hospital mortality was assessed using a Cox model and a propensity score to control for confounding by indication. Secondary outcomes included hospital readmissions and overall survival. RESULTS: In total, 82 AE-IPF subjects were identified, of whom 37 patients (45%) received corticosteroids. AE-IPF subjects treated with corticosteroids were more likely to require ICU level care and mechanical ventilation. There was no statistically significant association between corticosteroid treatment and in-hospital mortality (propensity score weighted, adjusted HR: 1.31; 95% CI: 0.26-6.55; P = 0.74). Overall survival was reduced in AE-IPF subjects receiving corticosteroids (HR: 6.17; 95% CI: 1.35-28.14; P = 0.019). CONCLUSION: Our study found no evidence that corticosteroid use improves outcomes in IPF patients admitted to the hospital with acute exacerbation. Furthermore, corticosteroid use may contribute to reduced overall survival following an exacerbation. Observational cohort studies using larger real-world cohorts can more definitively assess the relationship between corticosteroid treatment and short-term outcomes in AE-IPF.

A longitudinal big data approach for precision health.

Precision health relies on the ability to assess disease risk at an individual level, detect early preclinical conditions and initiate preventive strategies. Recent technological advances in omics and wearable monitoring enable deep molecular and physiological profiling and may provide important tools for precision health. We explored the ability of deep longitudinal profiling to make health-related discoveries, identify clinically relevant molecular pathways and affect behavior in a prospective longitudinal cohort (n = 109) enriched for risk of type 2 diabetes mellitus. The cohort underwent integrative personalized omics profiling from samples collected quarterly for up to 8 years (median, 2.8 years) using clinical measures and emerging technologies including genome, immunome, transcriptome, proteome, metabolome, microbiome and wearable monitoring. We discovered more than 67 clinically actionable health discoveries and identified multiple molecular pathways associated with metabolic, cardiovascular and oncologic pathophysiology. We developed prediction models for insulin resistance by using omics measurements, illustrating their potential to replace burdensome tests. Finally, study participation led the majority of participants to implement diet and exercise changes. Altogether, we conclude that deep longitudinal profiling can lead to actionable health discoveries and provide relevant information for precision health.

Reference-based analysis of lung single-cell sequencing reveals a transitional profibrotic macrophage.

Tissue fibrosis is a major cause of mortality that results from the deposition of matrix proteins by an activated mesenchyme. Macrophages accumulate in fibrosis, but the role of specific subgroups in supporting fibrogenesis has not been investigated in vivo. Here, we used single-cell RNA sequencing (scRNA-seq) to characterize the heterogeneity of macrophages in bleomycin-induced lung fibrosis in mice. A novel computational framework for the annotation of scRNA-seq by reference to bulk transcriptomes (SingleR) enabled the subclustering of macrophages and revealed a disease-associated subgroup with a transitional gene expression profile intermediate between monocyte-derived and alveolar macrophages. These CX3CR1+SiglecF+ transitional macrophages localized to the fibrotic niche and had a profibrotic effect in vivo. Human orthologs of genes expressed by the transitional macrophages were upregulated in samples from patients with idiopathic pulmonary fibrosis. Thus, we have identified a pathological subgroup of transitional macrophages that are required for the fibrotic response to injury.