Search

There is a growing focus on making clinical trials more inclusive but the design of trial eligibility criteria remains challenging1-3. Here we systematically evaluate the effect of different eligibility criteria on cancer trial populations and outcomes with real-world data using the computational framework of Trial Pathfinder. We apply Trial Pathfinder to emulate completed trials of advanced non-small-cell lung cancer using data from a nationwide database of electronic health records comprising 61,094 patients with advanced non-small-cell lung cancer. Our analyses reveal that many common criteria, including exclusions based on several laboratory values, had a minimal effect on the trial hazard ratios. When we used a data-driven approach to broaden restrictive criteria, the pool of eligible patients more than doubled on average and the hazard ratio of the overall survival decreased by an average of 0.05. This suggests that many patients who were not eligible under the original trial criteria could potentially benefit from the treatments. We further support our findings through analyses of other types of cancer and patient-safety data from diverse clinical trials. Our data-driven methodology for evaluating eligibility criteria can facilitate the design of more-inclusive trials while maintaining safeguards for patient safety.

Background: Olfactory impairment is evident in Alzheimer’s disease (AD); however, its precise relationships with clinical biomarker measures of tau pathology and neuroinflammation are not well understood. Objective: To determine if odor identification performance measured with the University of Pennsylvania Smell Identification Test (UPSIT) is related to in vivo measures of tau pathology and neuroinflammation. Methods: Cognitively normal and cognitively impaired participants were selected from an established research cohort of adults aged 50 and older who underwent neuropsychological testing, brain MRI, and amyloid PET. Fifty-four participants were administered the UPSIT. Forty-one underwent 18F-MK-6240 PET (measuring tau pathology) and fifty-three underwent 11C-PBR28 PET (measuring TSPO, present in activated microglia). Twenty-three participants had lumbar puncture to measure CSF concentrations of total tau (t-tau), phosphorylated tau (p-tau), and amyloid-β (Aβ42). Results: Low UPSIT performance was associated with greater18F-MK-6240 binding in medial temporal cortex, hippocampus, middle/inferior temporal gyri, inferior parietal cortex, and posterior cingulate cortex (p

Background. Transparent and accessible reporting of COVID-19 data is critical for public health efforts. Each state and union territory (UT) of India has its own mechanism for reporting COVID-19 data, and the quality of their reporting has not been systematically evaluated. We present a comprehensive assessment of the quality of COVID-19 data reporting done by the Indian state and union territory governments. This assessment informs the public health efforts in India and serves as a guideline for pandemic data reporting by other governments. Methods. We designed a semi-quantitative framework to assess the quality of COVID-19 data reporting done by the states and union territories of India. This framework captures four key aspects of public health data reporting - availability, accessibility, granularity, and privacy. We then used this framework to calculate a COVID-19 Data Reporting Score (CDRS, ranging from 0 to 1) for 29 states based on the quality of COVID-19 data reporting done by the state during the two-week period from 19 May to 1 June, 2020. States that reported less than 10 total confirmed cases as of May 18 were excluded from the study. Findings. Our results indicate a strong disparity in the quality of COVID-19 data reporting done by the state governments in India. CDRS varies from 0.61 (good) in Karnataka to 0.0 (poor) in Bihar and Uttar Pradesh, with a median value of 0.26. Only ten states provide a visual representation of the trend in COVID-19 data. Ten states do not report any data stratified by age, gender, comorbidities or districts. In addition, we identify that Punjab and Chandigarh compromised the privacy of individuals under quarantine by releasing their personally identifiable information on the official websites. Across the states, the CDRS is positively associated with the state's sustainable development index for good health and well-being (Pearson correlation: r=0.630, p=0.0003). Interpretation. The disparity in CDRS across states highlights three important findings at the national, state, and individual level. At the national level, it shows the lack of a unified framework for reporting COVID-19 data in India, and highlights the need for a central agency to monitor or audit the quality of data reporting done by the states. Without a unified framework, it is difficult to aggregate the data from different states, gain insights from them, and coordinate an effective nationwide response to the pandemic. Moreover, it reflects the inadequacy in coordination or sharing of resources among the states in India. Coordination among states is particularly important as more people start moving across states in the coming months. The disparate reporting score also reflects inequality in individual access to public health information and privacy protection based on the state of residence. Funding. J.Z. is supported by NSF CCF 1763191, NIH R21 MD012867-01, NIH P30AG059307, NIH U01MH098953 and grants from the Silicon Valley Foundation and the Chan-Zuckerberg Initiative.

We sought to determine if upstream amyloid accumulation and downstream cognitive impairment have independent relationships with microglial activation and tau pathology. Fifty-eight older adults were stratified by amyloid and cognitive status based on (18)F-florbetaben PET, history, and neuropsychological testing. Of these, 57 had (11)C-PBR28 PET to measure microglial activation and 43 had (18)F-MK-6240 PET to measure tau pathology. Amyloid and cognitive status were associated with increased overall binding for both (11)C-PBR28 and (18)F-MK-6240 (p’s < 0.01). While there was no interaction between amyloid and cognitive status in their association with (11)C-PBR28 binding (p = 0.6722), there was an interaction in their association with (18)F-MK-6240 binding (p = 0.0115). Binding of both radioligands was greater in amyloid-positive controls than in amyloid-negative controls; however, this difference was seen in neocortical regions for (11)C-PBR28 and only in medial temporal cortex for (18)F-MK-6240. We conclude that, in the absence of cognitive symptoms, amyloid deposition has a greater association with microglial activation than with tau pathology.

Single-cell RNA sequencing (scRNA-seq) has the potential to provide powerful, high-resolution signatures to inform disease prognosis and precision medicine. This paper takes an important first step towards this goal by developing an interpretable machine learning algorithm, CloudPred, to predict individuals' disease phenotypes from their scRNA-seq data. Predicting phenotype from scRNA-seq is challenging for standard machine learning methods -- the number of cells measured can vary by orders of magnitude across individuals and the cell populations are also highly heterogeneous. Typical analysis creates pseudo-bulk samples which are biased toward prior annotations and also lose the single cell resolution. CloudPred addresses these challenges via a novel end-to-end differentiable learning algorithm which is coupled with a biologically informed mixture of cell types model. CloudPred automatically infers the cell subpopulation that are salient for the phenotype without prior annotations. We developed a systematic simulation platform to evaluate the performance of CloudPred and several alternative methods we propose, and find that CloudPred outperforms the alternative methods across several settings. We further validated CloudPred on a real scRNA-seq dataset of 142 lupus patients and controls. CloudPred achieves AUROC of 0.98 while identifying a specific subpopulation of CD4 T cells whose presence is highly indicative of lupus. CloudPred is a powerful new framework to predict clinical phenotypes from scRNA-seq data and to identify relevant cells., Preprint of an article published in Pacific Symposium on Biocomputing \copyright\ 2021 World Scientific Publishing Co., Singapore, http://psb.stanford.edu/

Gene expression at the individual cell-level resolution, as quantified by single-cell RNA-sequencing (scRNA-seq), can provide unique insights into the pathology and cellular origin of diseases and complex traits. Here, we introduce single-cell Disease Relevance Score (scDRS), an approach that links scRNA-seq with polygenic risk of disease at individual cell resolution; scDRS identifies individual cells that show excess expression levels for genes in a disease-specific gene set constructed from GWAS data. We determined via simulations that scDRS is well-calibrated and powerful in identifying individual cells associated to disease. We applied scDRS to GWAS data from 74 diseases and complex traits (average N=341K) in conjunction with 16 scRNA-seq data sets spanning 1.3 million cells from 31 tissues and organs. At the cell type level, scDRS broadly recapitulated known links between classical cell types and disease, and also produced novel biologically plausible findings. At the individual cell level, scDRS identified subpopulations of disease-associated cells that are not captured by existing cell type labels, including subpopulations of CD4+ T cells associated with inflammatory bowel disease, partially characterized by their effector-like states; subpopulations of hippocampal CA1 pyramidal neurons associated with schizophrenia, partially characterized by their spatial location at the proximal part of the hippocampal CA1 region; and subpopulations of hepatocytes associated with triglyceride levels, partially characterized by their higher ploidy levels. At the gene level, we determined that genes whose expression across individual cells was correlated with the scDRS score (thus reflecting co-expression with GWAS disease genes) were strongly enriched for gold-standard drug target and Mendelian disease genes.

Patient experience surveys (PES) are collected by healthcare systems as a surrogate marker of quality and published unedited online for the purpose of transparency, but these surveys may reflect gender biases directed toward healthcare providers. This retrospective study evaluated PES at a single university hospital between July 2016 and June 2018. Surveys were stratified by overall provider rating and self-identified provider gender. Adjectives from free-text survey comments were extracted using natural language processing techniques and applied to a statistical machine learning model to identify descriptors predictive of provider gender. 109,994 surveys were collected, 17,395 contained free-text comments describing 687 unique providers. The mean overall rating between male (8.84, n = 8558) and female (8.80, n = 8837) providers did not differ (p = 0.149). However, highly-rated male providers were more often described for their agentic qualities using adjectives such as “informative,” “forthright,” “superior,” and “utmost” (OR 1.48, p

Significance Simultaneous measurement of the DNA, RNA, and proteins of single cells can lead to important new insights but is experimentally challenging. This work introduces a deep learning algorithm that flexibly translates between chromatin, RNA, and protein profiles in single cells. This makes it possible to computationally synthesize matched multiomic measurements when only one modality is experimentally available. This algorithm complements experimental advances to efficiently achieve single-cell multiomic insight., Simultaneous profiling of multiomic modalities within a single cell is a grand challenge for single-cell biology. While there have been impressive technical innovations demonstrating feasibility—for example, generating paired measurements of single-cell transcriptome (single-cell RNA sequencing [scRNA-seq]) and chromatin accessibility (single-cell assay for transposase-accessible chromatin using sequencing [scATAC-seq])—widespread application of joint profiling is challenging due to its experimental complexity, noise, and cost. Here, we introduce BABEL, a deep learning method that translates between the transcriptome and chromatin profiles of a single cell. Leveraging an interoperable neural network model, BABEL can predict single-cell expression directly from a cell’s scATAC-seq and vice versa after training on relevant data. This makes it possible to computationally synthesize paired multiomic measurements when only one modality is experimentally available. Across several paired single-cell ATAC and gene expression datasets in human and mouse, we validate that BABEL accurately translates between these modalities for individual cells. BABEL also generalizes well to cell types within new biological contexts not seen during training. Starting from scATAC-seq of patient-derived basal cell carcinoma (BCC), BABEL generated single-cell expression that enabled fine-grained classification of complex cell states, despite having never seen BCC data. These predictions are comparable to analyses of experimental BCC scRNA-seq data for diverse cell types related to BABEL’s training data. We further show that BABEL can incorporate additional single-cell data modalities, such as protein epitope profiling, thus enabling translation across chromatin, RNA, and protein. BABEL offers a powerful approach for data exploration and hypothesis generation.

Laboratory blood testing is routinely used to assay biomarkers to provide information on physiologic state beyond what clinicians can evaluate from interpreting medical imaging. We hypothesized that deep learning interpretation of echocardiogram videos can provide additional value in understanding disease states and can predict common biomarkers results. Using 70,066 echocardiograms and associated biomarker results from 39,460 patients, we developed EchoNet-Labs, a video-based deep learning algorithm to predict anemia, elevated B-type natriuretic peptide (BNP), troponin I, and blood urea nitrogen (BUN), and abnormal levels in ten additional lab tests. On held-out test data across different healthcare systems, EchoNet-Labs achieved an area under the curve (AUC) of 0.80 in predicting anemia, 0.82 in predicting elevated BNP, 0.75 in predicting elevated troponin I, and 0.69 in predicting elevated BUN. We further demonstrate the utility of the model in predicting abnormalities in 10 additional lab tests. We investigate the features necessary for EchoNet-Labs to make successful predictions and identify potential prediction mechanisms for each biomarker using well-known and novel explainability techniques. These results show that deep learning applied to diagnostic imaging can provide additional clinical value and identify phenotypic information beyond current imaging interpretation methods.

Simultaneous profiling of multi-omic modalities within a single cell is a grand challenge for single-cell biology. While there have been impressive technical innovations demonstrating feasibility – for example generating paired measurements of scRNA-seq and scATAC-seq – wide-spread application of joint profiling is challenging due to the experimental complexity, noise, and cost. Here we introduce BABEL, a deep learning method that translates between the transcriptome and chromatin profiles of a single cell. Leveraging a novel interoperable neural network model, BABEL can generate scRNA-seq directly from a cell’s scATAC-seq, and vice versa. This makes it possible to computationally synthesize paired multi-omic measurements when only one modality is experimentally available. Across several paired scRNA-seq and scATAC-seq datasets in human and mouse, we validate that BABEL accurately translates between these modalities for individual cells. BABEL also generalizes well to new biological contexts not seen during training. For example, starting from scATAC-seq of patient derived basal cell carcinoma (BCC), BABEL generated scRNA-seq that enabled fine-grained classification of complex cell states, despite having never seen BCC data. These predictions are comparable to analyses of the experimental BCC scRNA-seq data. We further show that BABEL can incorporate additional single-cell data modalities, such as CITE-seq, thus enabling translation across chromatin, RNA, and protein. BABEL offers a powerful approach for data exploration and hypothesis generation.

BackgroundOlfactory impairment is evident in Alzheimer’s disease (AD), however, its precise relationships with clinical biomarker measures of tau pathology and neuroinflammation are not well understood.ObjectiveTo determine if odor identification performance measured with the University of Pennsylvania Smell Identification Test (UPSIT) is related to in vivo measures of tau pathology and neuroinflammation.MethodsParticipants were selected from an established research cohort of adults aged 50 and older who underwent neuropsychological testing, brain MRI, and amyloid PET. Fifty-four participants were administered the UPSIT. Forty-one underwent 18F-MK-6240 PET and fifty-three underwent 11C-PBR28 PET to measure tau pathology and neuroinflammation, respectively. Twenty-three participants had lumbar puncture to measure CSF concentrations of total tau (t-tau), phosphorylated tau (p-tau) and β-amyloid (Aβ42).ResultsLow UPSIT performance was associated with greater18F-MK-6240 binding in medial temporal cortex, hippocampus, middle/inferior temporal gyri, inferior parietal cortex and posterior cingulate cortex (p < 0.05). Similar relationships were seen for 11C-PBR28. These relationships were primarily driven by amyloid-positive participants. Lower UPSIT performance was associated with greater CSF concentrations of t-tau and p-tau (p < 0.05). Amyloid status and cognitive status exhibited independent effects on UPSIT performance (p < 0.01).ConclusionsOlfactory identification deficits are related to extent of tau pathology and neuroinflammation, particularly in those with amyloid pathophysiology. The independent association of amyloid-positivity and cognitive impairment with odor identification suggests that low UPSIT performance may be a marker for AD pathophysiology in cognitive normal individuals, although impaired odor identification is associated with both AD and non-AD related neurodegeneration.NCT Registration Numbers:NCT03373604; NCT02831283

The reliability of machine learning models can be compromised when trained on low quality data. Many large-scale medical imaging datasets contain low quality labels extracted from sources such as medical reports. Moreover, images within a dataset may have heterogeneous quality due to artifacts and biases arising from equipment or measurement errors. Therefore, algorithms that can automatically identify low quality data are highly desired. In this study, we used data Shapley, a data valuation metric, to quantify the value of training data to the performance of a pneumonia detection algorithm in a large chest X-ray dataset. We characterized the effectiveness of data Shapley in identifying low quality versus valuable data for pneumonia detection. We found that removing training data with high Shapley values decreased the pneumonia detection performance, whereas removing data with low Shapley values improved the model performance. Furthermore, there were more mislabeled examples in low Shapley value data and more true pneumonia cases in high Shapley value data. Our results suggest that low Shapley value indicates mislabeled or poor quality images, whereas high Shapley value indicates data that are valuable for pneumonia detection. Our method can serve as a framework for using data Shapley to denoise large-scale medical imaging datasets.

Background Transparent and accessible reporting of COVID-19 data is critical for public health efforts. Each state and union territory (UT) of India has its own mechanism for reporting COVID-19 data, and the quality of their reporting has not been systematically evaluated. We present a comprehensive assessment of the quality of COVID-19 data reporting done by the Indian state and union territory governments. This assessment informs the public health efforts in India and serves as a guideline for pandemic data reporting by other governments. Methods We designed a semi-quantitative framework to assess the quality of COVID-19 data reporting done by the states and union territories of India. This framework captures four key aspects of public health data reporting – availability, accessibility, granularity, and privacy. We then used this framework to calculate a COVID-19 Data Reporting Score (CDRS, ranging from 0 to 1) for 29 statesi based on the quality of COVID-19 data reporting done by the state during the two-week period from 19 May to 1 June, 2020. States that reported less than 10 total confirmed cases as of May 18, were excluded from the study. Findings Our results indicate a strong disparity in the quality of COVID-19 data reporting done by the state governments in India. CDRS varies from 0.61 (good) in Karnataka to 0.0 (poor) in Bihar and Uttar Pradesh, with a median value of 0.26. Only ten states provide a visual representation of the trend in COVID-19 data. Ten states do not report any data stratified by age, gender, comorbidities or districts. In addition, we identify that Punjab and Chandigarh compromised the privacy of individuals under quarantine by releasing their personally identifiable information on the official websites. Across the states, the CDRS is positively associated with the state’s sustainable development index for good health and well-being (Pearson correlation: r = 0.630, p = 0.0003). Interpretation The disparity in CDRS across states highlights three important findings at the national, state, and individual level. At the national level, it shows the lack of a unified framework for reporting COVID-19 data in India, and highlights the need for a central agency to monitor or audit the quality of data reporting done by the states. Without a unified framework, it is difficult to aggregate the data from different states, gain insights from them, and coordinate an effective nationwide response to the pandemic. Moreover, it reflects the inadequacy in coordination or sharing of resources among the states in India. Coordination among states is particularly important as more people start moving across states in the coming months. The disparate reporting score also reflects inequality in individual access to public health information and privacy protection based on the state of residence. Funding J.Z. is supported by NSF CCF 1763191, NIH R21 MD012867-01, NIH P30AG059307, NIH U01MH098953 and grants from the Silicon Valley Foundation and the Chan-Zuckerberg Initiative. Research in context Evidence before this study Two key components in containing the COVID-19 pandemic is public awareness and public trust in the government. These components critically depend on timely and accessible dissemination of COVID-19 data by the government. While there are studies showing disparities in personal healthcare access in India, very little is known about the quality of access to “public health data” across India, especially during the COVID-19 pandemic. Janiaud and Goodman characterize the incomplete and absent reporting of critical COVID-19 epidemic statistics by state departments of health in the U.S. However, there are no such studies on a low middle-income country like India which has an underfunded public health system. Added value of this study To our knowledge, this study is the first comprehensive assessment of the quality of COVID-19 data reporting across India. We developed a semi-quantitative framework to assess the quality of COVID-19 data reporting, and used it to calculate a COVID-19 Data Reporting Score (CDRS) for 29 state and union territory governments of India. Our framework captures four key elements of public health data reporting – availability, accessibility, granularity, and privacy – and provides a guideline for high-quality COVID-19 data reporting that can also be used in other countries. Our findings highlight a large variation in the quality of COVID-19 data reporting across India. CDRS varies from 0.61 to 0.0 with a median value of 0.26 and an inter-quartile range of 0.21. No single state does best in all four elements of data reporting. We find that: (i) only ten states provide trend graphics; (ii) ten states do not report any data stratified by age, gender, comorbidities or districts; (iii) Punjab and Chandigarh compromised the privacy of individuals under quarantine by releasing personally identifiable information on their official websites. Across the states, the CDRS score is positively associated with the state’s sustainable development index for good health and well-being (Pearson correlation: r = 0.630, p = 0.0003). Implications of all the available evidence Our assessment informs the public health efforts in India about the disparity in the quality of COVID-19 data reporting across the country. The available evidence shows that an improvement in the quality of data reporting is required all across India. The disparity in CDRS shows the lack of a unified framework for reporting COVID-19 data in India, and highlights the need for a central agency to monitor or audit the quality of data reporting done by the states. The disparate reporting score also reflects inequality in individual access to public health information and privacy protection based on the state of residence.

/Summary SARS-CoV-2 genomic and subgenomic RNA (sgRNA) transcripts hijack the host cell's machinery. Subcellular localization of its viral RNA could thus play important roles in viral replication and host antiviral immune response. We perform computational modeling of SARS-CoV-2 viral RNA subcellular residency across eight subcellular neighborhoods. We compare hundreds of SARS-CoV-2 genomes to the human transcriptome and other coronaviruses. We predict the SARS-CoV-2 RNA genome and sgRNAs to be enriched towards the host mitochondrial matrix and nucleolus, and that the 5’ and 3’ viral untranslated regions contain the strongest, most distinct localization signals. We interpret the mitochondrial residency signal as an indicator of intracellular RNA trafficking with respect to double-membrane vesicles, a critical stage in the coronavirus life cycle. Our computational analysis serves as a hypothesis generation tool to suggest models for SARS-CoV-2 biology and inform experimental efforts to combat the virus. A record of this paper’s Transparent Peer Review process is included in the Supplemental Information., Graphical Abstract, Highlights ● Application of machine learning model of RNA subcellular localization to SARS-CoV-2 ● Viral RNAs show residency signal for host mitochondria and nucleolus ● Mitochondria prediction suggests viruses repurpose endogenous pathways ● Predictions may be linked to vesicle formation and viral-host protein interactions, Where the SARS-CoV-2 genome localizes inside human cells remains understudied but may regulate viral replication and host response. We use a machine learning model to predict subcellular residency of the SARS-CoV-2 genome and its encoded transcripts, as well as for other coronaviruses. Our predictions suggest new hypotheses for SARS-CoV-2 mechanisms.

Genetics researchers and clinical professionals rely on diversity measures such as race, ethnicity, and ancestry (REA) to stratify study participants and patients for a variety of applications in research and precision medicine. However, there are no comprehensive, widely accepted standards or guidelines for collecting and using such data in either setting. Two NIH-funded research consortia, the Clinical Genome Resource (ClinGen) and Clinical Sequencing Evidence-generating Research (CSER), have partnered to address this issue and report how REA are currently collected, conceptualized, and used. Surveying clinical genetics professionals and researchers (N=448), we found heterogeneity in the way REA are perceived, defined, and measured, with variation in the perceived importance of REA in both clinical and research settings. The majority of respondents (>55%) felt that REA are at least somewhat important for clinical variant interpretation, ordering genetic tests, and communicating results to patients. However, there was no consensus on the relevance of REA, including how each of these measures should be used in different scenarios and what information they can convey in the context of human genetics. A lack of common definitions and applications of REA across the precision medicine pipeline may contribute to inconsistencies in data collection, missing or inaccurate classifications, and misleading or inconclusive results. Thus, our findings support the need for standardization and harmonization of REA data collection and use in clinical genetics and precision health research.

Genetics researchers and clinical professionals rely on diversity measures such as race, ethnicity, and ancestry (REA) to stratify study participants and patients for a variety of applications in research and precision medicine. However, there are no comprehensive, widely accepted standards or guidelines for collecting and using such data in clinical genetics practice. Two NIH-funded research consortia, the Clinical Genome Resource (ClinGen) and Clinical Sequencing Evidence-generating Research (CSER), have partnered to address this issue and report how REA are currently collected, conceptualized, and used. Surveying clinical genetics professionals and researchers (n = 448), we found heterogeneity in the way REA are perceived, defined, and measured, with variation in the perceived importance of REA in both clinical and research settings. The majority of respondents (>55%) felt that REA are at least somewhat important for clinical variant interpretation, ordering genetic tests, and communicating results to patients. However, there was no consensus on the relevance of REA, including how each of these measures should be used in different scenarios and what information they can convey in the context of human genetics. A lack of common definitions and applications of REA across the precision medicine pipeline may contribute to inconsistencies in data collection, missing or inaccurate classifications, and misleading or inconclusive results. Thus, our findings support the need for standardization and harmonization of REA data collection and use in clinical genetics and precision health research.

Aging is characterized by a progressive loss of physiological integrity, leading to impaired function and increased vulnerability to death(1). Despite rapid advances over recent years, many of the molecular and cellular processes which underlie progressive loss of healthy physiology are poorly understood(2). To gain a better insight into these processes we have created a single cell transcriptomic atlas across the life span of Mus musculus which includes data from 23 tissues and organs. We discovered cell-specific changes occurring across multiple cell types and organs, as well as age related changes in the cellular composition of different organs. Using single-cell transcriptomic data we were able to assess cell type specific manifestations of different hallmarks of aging, such as senescence(3), genomic instability(4) and changes in the organism’s immune system(2). This Tabula Muris Senis provides a wealth of new molecular information about how the most significant hallmarks of aging are reflected in a broad range of tissues and cell types.

Importance Clinical artificial intelligence (AI) algorithms have the potential to improve clinical care, but fair, generalizable algorithms depend on the clinical data on which they are trained and tested. Objective To assess whether data sets used for training diagnostic AI algorithms addressing skin disease are adequately described and to identify potential sources of bias in these data sets. Data sources In this scoping review, PubMed was used to search for peer-reviewed research articles published between January 1, 2015, and November 1, 2020, with the following paired search terms: deep learning and dermatology, artificial intelligence and dermatology, deep learning and dermatologist, and artificial intelligence and dermatologist. Study selection Studies that developed or tested an existing deep learning algorithm for triage, diagnosis, or monitoring using clinical or dermoscopic images of skin disease were selected, and the articles were independently reviewed by 2 investigators to verify that they met selection criteria. Consensus process Data set audit criteria were determined by consensus of all authors after reviewing existing literature to highlight data set transparency and sources of bias. Results A total of 70 unique studies were included. Among these studies, 1 065 291 images were used to develop or test AI algorithms, of which only 257 372 (24.2%) were publicly available. Only 14 studies (20.0%) included descriptions of patient ethnicity or race in at least 1 data set used. Only 7 studies (10.0%) included any information about skin tone in at least 1 data set used. Thirty-six of the 56 studies developing new AI algorithms for cutaneous malignant neoplasms (64.3%) met the gold standard criteria for disease labeling. Public data sets were cited more often than private data sets, suggesting that public data sets contribute more to new development and benchmarks. Conclusions and relevance This scoping review identified 3 issues in data sets that are used to develop and test clinical AI algorithms for skin disease that should be addressed before clinical translation: (1) sparsity of data set characterization and lack of transparency, (2) nonstandard and unverified disease labels, and (3) inability to fully assess patient diversity used for algorithm development and testing.

Introduction Sleep disorders and sleep characteristics have been linked to higher risk of mortality. Despite the emerging evidence of a sleep-mortality association, the relationship between sleep architecture and mortality aren’t well understood. We hypothesize that reduced REM is associated with increased mortality risk. Methods The Osteoporotic Fractures in Men (MrOS) study is a population-based study of 2,675 older men. Cox regression was used to evaluate the association between %REM and mortality rate. Potential covariates were evaluated using 6-fold cross validation. Sensitivity analyses were performed to rule out alternative explanations. Wisconsin Sleep Cohort (WSC) and Sleep Heart Health Study (SHHS) data were used to replicate the findings. Results The MrOS sample mean age was 76.3 years (SD=5.51) and the median follow-up time was 12.1 years. There was a 13% higher rate of mortality for every absolute 5% reduction in REM sleep (HR=1.13, 95%CI, 1.08–1.19) after adjusting for multiple demographic, sleep, and health covariates. The association persisted for cardiovascular disease-related mortality (CVD) (HR=1.18, 95%CI, 1.09–1.28), cancer-related mortality (HR=1.14, 95%CI, 1.03–1.26), and other mortality (HR=1.19, 95%CI, 1.10–1.28). The WSC included 45.7% women. The mean age of the 1,388 individuals analyzed was 51.5 (SD=8.5); the median follow-up time was 20.8 years. The effect size for 5% reduction in REM on rate of all-cause mortality was similar in this cohort despite the younger age, inclusion of women, and longer follow-up period (HR=1.17, 95%CI, 1.03–1.34). SHHS data is still being analyzed; however the unadjusted model is consistent with the other cohorts. Conclusion We found an association between reduced REM and mortality in two, possibly three independent cohorts, which persisted across different causes of death and multiple sensitivity analyses. Mechanistic studies are needed and strategies to preserve REM may influence clinical therapies and reduce mortality risk. Support NHLBI provides funding for the MrOS Sleep ancillary study “Outcomes of Sleep Disorders in Older Men” under grant numbers: R01 HL071194, R01 HL070848, R01 HL070847, R01 HL070842, R01 HL070841, R01 HL070837, R01 HL070838, and R01 HL070839. Wisconsin Sleep Cohort was supported by R01HL62252, RR03186, and R01AG14124 from the NIH. Dr. Redline was partially supported by NHLBI R35 HL135818.

Accurate assessment of cardiac function is crucial for diagnosing cardiovascular disease1, screening for cardiotoxicity2,3, and deciding clinical management in patients with critical illness4. However human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has significant interobserver variability despite years of training2,5,6. To overcome this challenge, we present the first beat-to-beat deep learning algorithm that surpasses human expert performance in the critical tasks of segmenting the left ventricle, estimating ejection fraction, and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice Similarity Coefficient of 0.92, predicts ejection fraction with mean absolute error of 4.1%, and reliably classifies heart failure with reduced ejection fraction (AUC of 0.97). Prospective evaluation with repeated human measurements confirms that our model has less variance than experts. By leveraging information across multiple cardiac cycles, our model can identify subtle changes in ejection fraction, is more reproducible than human evaluation, and lays the foundation for precise diagnosis of cardiovascular disease. As a new resource to promote further innovation, we also make publicly available one of the largest medical video dataset of over 10,000 annotated echocardiograms.Key PointsVideo based deep learning evaluation of cardiac ultrasound accurately identifies cardiomyopathy and predict ejection fraction, the most common metric of cardiac function.Using human tracings obtained during standard clinical workflow, deep learning semantic segmentation accurately labels the left ventricle frame-by-frame, including in frames without prior human annotation.Computational cardiac function analysis allows for beat-by-beat assessment of ejection fraction, which more accurately assesses cardiac function in patients with atrial fibrillation, arrhythmias, and heart rate variability.

Accurate assessment of cardiac function is crucial for the diagnosis of cardiovascular disease1, screening for cardiotoxicity2 and decisions regarding the clinical management of patients with a critical illness3. However, human assessment of cardiac function focuses on a limited sampling of cardiac cycles and has considerable inter-observer variability despite years of training4,5. Here, to overcome this challenge, we present a video-based deep learning algorithm—EchoNet-Dynamic—that surpasses the performance of human experts in the critical tasks of segmenting the left ventricle, estimating ejection fraction and assessing cardiomyopathy. Trained on echocardiogram videos, our model accurately segments the left ventricle with a Dice similarity coefficient of 0.92, predicts ejection fraction with a mean absolute error of 4.1% and reliably classifies heart failure with reduced ejection fraction (area under the curve of 0.97). In an external dataset from another healthcare system, EchoNet-Dynamic predicts the ejection fraction with a mean absolute error of 6.0% and classifies heart failure with reduced ejection fraction with an area under the curve of 0.96. Prospective evaluation with repeated human measurements confirms that the model has variance that is comparable to or less than that of human experts. By leveraging information across multiple cardiac cycles, our model can rapidly identify subtle changes in ejection fraction, is more reproducible than human evaluation and lays the foundation for precise diagnosis of cardiovascular disease in real time. As a resource to promote further innovation, we also make publicly available a large dataset of 10,030 annotated echocardiogram videos. A video-based deep learning algorithm—EchoNet-Dynamic—accurately identifies subtle changes in ejection fraction and classifies heart failure with reduced ejection fraction using information from multiple cardiac cycles.

Spatial transcriptomics allows for the measurement of RNA abundance at a high spatial resolution, making it possible to systematically link the morphology of cellular neighbourhoods and spatially localized gene expression. Here, we report the development of a deep learning algorithm for the prediction of local gene expression from haematoxylin-and-eosin-stained histopathology images using a new dataset of 30,612 spatially resolved gene expression data matched to histopathology images from 23 patients with breast cancer. We identified over 100 genes, including known breast cancer biomarkers of intratumoral heterogeneity and the co-localization of tumour growth and immune activation, the expression of which can be predicted from the histopathology images at a resolution of 100 µm. We also show that the algorithm generalizes well to The Cancer Genome Atlas and to other breast cancer gene expression datasets without the need for re-training. Predicting the spatially resolved transcriptome of a tissue directly from tissue images may enable image-based screening for molecular biomarkers with spatial variation.

Echocardiography uses ultrasound technology to capture high temporal and spatial resolution images of the heart and surrounding structures, and is the most common imaging modality in cardiovascular medicine. Using convolutional neural networks on a large new dataset, we show that deep learning applied to echocardiography can identify local cardiac structures, estimate cardiac function, and predict systemic phenotypes that modify cardiovascular risk but not readily identifiable to human interpretation. Our deep learning model, EchoNet, accurately identified the presence of pacemaker leads (AUC = 0.89), enlarged left atrium (AUC = 0.86), left ventricular hypertrophy (AUC = 0.75), left ventricular end systolic and diastolic volumes ($${R}^{2}$$ R 2 = 0.74 and $${R}^{2}$$ R 2 = 0.70), and ejection fraction ($${R}^{2}$$ R 2 = 0.50), as well as predicted systemic phenotypes of age ($${R}^{2}$$ R 2 = 0.46), sex (AUC = 0.88), weight ($${R}^{2}$$ R 2 = 0.56), and height ($${R}^{2}$$ R 2 = 0.33). Interpretation analysis validates that EchoNet shows appropriate attention to key cardiac structures when performing human-explainable tasks and highlights hypothesis-generating regions of interest when predicting systemic phenotypes difficult for human interpretation. Machine learning on echocardiography images can streamline repetitive tasks in the clinical workflow, provide preliminary interpretation in areas with insufficient qualified cardiologists, and predict phenotypes challenging for human evaluation.

The large volume of data used in cancer diagnosis presents a unique opportunity for deep learning algorithms, which improve in predictive performance with increasing data. When applying deep learning to cancer diagnosis, the goal is often to learn how to classify an input sample (such as images or biomarkers) into predefined categories (such as benign or cancerous). In this article, we examine examples of how deep learning algorithms have been implemented to make predictions related to cancer diagnosis using clinical, radiological, and pathological image data. We present a systematic approach for evaluating the development and application of clinical deep learning algorithms. Based on these examples and the current state of deep learning in medicine, we discuss the future possibilities in this space and outline a roadmap for implementations of deep learning in cancer diagnosis.

Background Multidrug resistant organism (MDRO) infections are a threat to public health. Urinary tract infections (UTIs) are the most common MDRO infection and are responsible for a significant proportion of antibiotic use. Studies demonstrate both duration and type of antibiotics prescribed to patients with MDRO UTI are inappropriate, and that asymptomatic MDRO bacteriuria is inappropriately treated. In addition, antibiotics prescribed at hospital discharge are inappropriate in ~70% of patients. We sought to characterize inpatient and outpatient antibiotic durations to describe burden of antibiotic use for patients with an MDRO isolated from a urine specimen during a hospitalization. Methods This retrospective study was conducted at Barnes-Jewish Hospital, a 1266-bed academic medical center in St. Louis, Missouri from 11/7/12-11/7/17. Patients ≥ 18 years of age were included if they had an MDRO isolated from a urine specimen and no other positive bacterial cultures during their hospitalization. Demographics, comorbidities, cultures, and antibiotics were collected via data pulls and chart review. MDROs were defined according to European and US Center for Disease Control and Prevention guidelines. Antibiotic use was described as percentages of all antibiotics used. Results A total of 1052 patients had MDROs in urine cultures. Of these patients, 747 (71.0%) were discharged on oral antibiotics for a mean duration of 6.7 days, while 135 (12.8%) were discharged on IV antibiotics for a mean of 10.9 days. The five most commonly administered inpatient antibiotics after urine culture results were available (% prescribed) were IV ceftriaxone (43.0%), IV vancomycin (26.0%), PO ciprofloxacin (25.6%), IV cefepime (24.5%), and PO trimethoprim-sulfamethoxazole (17.6%). The five most commonly prescribed antibiotics at discharge were PO ciprofloxacin (22.3%), PO trimethoprim-sulfamethoxazole (17.8%), PO nitrofurantoin (8.4%), PO cephalexin (6.2%), and PO doxycycline (5.0%). Conclusion Patients with MDROs in urine cultures receive prolonged durations of inpatient and outpatient antibiotics, longer than what is recommended by current evidence and guidelines. Disclosures Dustin Stwalley, MA, AbbVie Inc (Shareholder)Bristol-Myers Squibb (Shareholder) Margaret A. Olsen, PhD, MPH, Merck (Grant/Research Support)Pfizer (Consultant, Grant/Research Support)

Importance Rapid eye movement (REM) sleep has been linked with health outcomes, but little is known about the relationship between REM sleep and mortality. Objective To investigate whether REM sleep is associated with greater risk of mortality in 2 independent cohorts and to explore whether another sleep stage could be driving the findings. Design, Setting, and Participants This multicenter population-based cross-sectional study used data from the Outcomes of Sleep Disorders in Older Men (MrOS) Sleep Study and Wisconsin Sleep Cohort (WSC). MrOS participants were recruited from December 2003 to March 2005, and WSC began in 1988. MrOS and WSC participants who had REM sleep and mortality data were included. Analysis began May 2018 and ended December 2019. Main Outcomes and Measures All-cause and cause-specific mortality confirmed with death certificates. Results The MrOS cohort included 2675 individuals (2675 men [100%]; mean [SD] age, 76.3 [5.5] years) and was followed up for a median (interquartile range) of 12.1 (7.8-13.2) years. The WSC cohort included 1386 individuals (753 men [54.3%]; mean [SD] age, 51.5 [8.5] years) and was followed up for a median (interquartile range) of 20.8 (17.9-22.4) years. MrOS participants had a 13% higher mortality rate for every 5% reduction in REM sleep (percentage REM sleep SD = 6.6%) after adjusting for multiple demographic, sleep, and health covariates (age-adjusted hazard ratio, 1.12; fully adjusted hazard ratio, 1.13; 95% CI, 1.08-1.19). Results were similar for cardiovascular and other causes of death. Possible threshold effects were seen on the Kaplan-Meier curves, particularly for cancer; individuals with less than 15% REM sleep had a higher mortality rate compared with individuals with 15% or more for each mortality outcome with odds ratios ranging from 1.20 to 1.35. Findings were replicated in the WSC cohort despite younger age, inclusion of women, and longer follow-up (hazard ratio, 1.17; 95% CI, 1.03-1.34). A random forest model identified REM sleep as the most important sleep stage associated with survival. Conclusions and Relevance Decreased percentage REM sleep was associated with greater risk of all-cause, cardiovascular, and other noncancer-related mortality in 2 independent cohorts.

A persistent concern with CRISPR-Cas9 gene editing has been the potential to generate mutations at off-target genomic sites. While CRISPR-engineering mice to delete a ~360 bp intronic enhancer, here we discovered a founder line that had marked immune dysregulation caused by a 24 kb tandem duplication of the sequence adjacent to the on-target deletion. Our results suggest unintended repair of on-target genomic cuts can cause pathogenic “bystander” mutations that escape detection by routine targeted genotyping assays., Dimitre Simeonov, Alexander Brandt et al. report a pathogenic bystander mutation caused by unintended repair of a CRISPR-Cas9-mediated deletion in mice. They generate mice lacking an IL2RA intronic enhancer previously associated with human disease risk and find that one line of edited mice show unexpected disease features due to a bystander mutation.

Cell surfaces are decorated by a variety of proteins that facilitate interactions with their environments and support cell stability. These secreted proteins are anchored to the cell by mechanisms that are diverse, and, in archaea, poorly understood. Recently published in silico data suggest that in some species a subset of secreted euryarchaeal proteins, which includes the S-layer glycoprotein, is processed and covalently linked to the cell membrane by enzymes referred to as archaeosortases. In silico work led to the proposal that an independent, sortase-like system for proteolysis-coupled, carboxy-terminal lipid modification exists in bacteria (exosortase) and archaea (archaeosortase). Here, we provide the first in vivo characterization of an archaeosortase in the haloarchaeal model organism Haloferax volcanii. Deletion of the artA gene (HVO_0915) resulted in multiple biological phenotypes: (a) poor growth, especially under low-salt conditions, (b) alterations in cell shape and the S-layer, (c) impaired motility, suppressors of which still exhibit poor growth, and (d) impaired conjugation. We studied one of the ArtA substrates, the S-layer glycoprotein, using detailed proteomic analysis. While the carboxy-terminal region of S-layer glycoproteins, consisting of a putative threonine-rich O-glycosylated region followed by a hydrophobic transmembrane helix, has been notoriously resistant to any proteomic peptide identification, we were able to identify two overlapping peptides from the transmembrane domain present in the ΔartA strain but not in the wild-type strain. This clearly shows that ArtA is involved in carboxy-terminal post-translational processing of the S-layer glycoprotein. As it is known from previous studies that a lipid is covalently attached to the carboxy-terminal region of the S-layer glycoprotein, our data strongly support the conclusion that archaeosortase functions analogously to sortase, mediating proteolysis-coupled, covalent cell surface attachment.

Background Religion shapes everyday beliefs and activities, but few studies have examined its associations with attitudes about HIV. This exploratory study in Tanzania probed associations between religious beliefs and HIV stigma, disclosure, and attitudes toward antiretroviral (ARV) treatment. Methods A self-administered survey was distributed to a convenience sample of parishioners (n = 438) attending Catholic, Lutheran, and Pentecostal churches in both urban and rural areas. The survey included questions about religious beliefs, opinions about HIV, and knowledge and attitudes about ARVs. Multivariate logistic regression analysis was performed to assess how religion was associated with perceptions about HIV, HIV treatment, and people living with HIV/AIDS. Results Results indicate that shame-related HIV stigma is strongly associated with religious beliefs such as the belief that HIV is a punishment from God (p < 0.01) or that people living with HIV/AIDS (PLWHA) have not followed the Word of God (p < 0.001). Most participants (84.2%) said that they would disclose their HIV status to their pastor or congregation if they became infected. Although the majority of respondents (80.8%) believed that prayer could cure HIV, almost all (93.7%) said that they would begin ARV treatment if they became HIV-infected. The multivariate analysis found that respondents' hypothetical willingness to begin ARV treatme was not significantly associated with the belief that prayer could cure HIV or with other religious factors. Refusal of ARV treatment was instead correlated with lack of secondary schooling and lack of knowledge about ARVs. Conclusion The decision to start ARVs hinged primarily on education-level and knowledge about ARVs rather than on religious factors. Research results highlight the influence of religious beliefs on HIV-related stigma and willingness to disclose, and should help to inform HIV-education outreach for religious groups.