Achieving widespread COVID-19 vaccine acceptance is a key step to global recovery from the pandem... more Achieving widespread COVID-19 vaccine acceptance is a key step to global recovery from the pandemic, but hesitancy towards vaccination remains a major challenge. Social proof, where a person’s attitude towards vaccination is influenced by their belief in the attitudes of their social network, has been shown to be effective for making in-roads upon hesitancy. However, it is not easy to know the attitudes of one’s network, nor reliably signal one’s own feelings towards COVID-19 vaccines, minimizing the impact of the social influence channel. To address this issue, Facebook launched a feature that enables users to overlay a message indicating that they support vaccination upon their profile picture. To raise awareness of these vaccine profile frames (VPFs), users received a variety of promotional messages from Facebook, a subset of which contained the social context of friends who had already adopted the frame. Leveraging this variation in promotional messaging, we analyzed the adoptio...
SLIViT: a general AI framework for clinical-feature diagnosis from limited 3D biomedical-imaging data
We present SLIViT, a deep-learning framework that accurately measures disease-related risk factor... more We present SLIViT, a deep-learning framework that accurately measures disease-related risk factors in volumetric biomedical imaging, such as magnetic resonance imaging (MRI) scans, optical coherence tomography (OCT) scans, and ultrasound videos. To evaluate SLIViT, we applied it to five different datasets of these three different data modalities tackling seven learning tasks (including both classification and regression) and found that it consistently and significantly outperforms domain-specific state-of-the-art models, typically improving performance (ROC AUC or correlation) by 10-40%. Notably, compared to existing approaches, SLIViT can be applied even when only a small number of annotated training samples is available, which is often a constraint in medical applications. When trained on less than 700 annotated volumes, SLIViT obtained accuracy comparable to trained clinical specialists while reducing annotation time by a factor of 5,000 demonstrating its utility to automate and ...
Prediction of Activity in Eyes with Macular Neovascularization Due to Age-related Macular Degeneration Using Deep Learning
Background: To evaluate several deep learning algorithms to detect activity of macular neovascula... more Background: To evaluate several deep learning algorithms to detect activity of macular neovascularization (MNV) using en face optical coherence tomography angiography (OCTA) images. Methods: Choriocapillaris en face OCTA 6x6 mm images from eyes with neovascular AMD imaged with the RTvue-XR Avanti SD-OCTA (Optovue) device were included in this retrospective analysis. Multiple machine learning models were trained to classify the presence of MNV activity by OCTA imaging, using the presence of fluid on the structural OCT as the ground truth evidence for activity. Specifically, a five-fold cross-validation was applied to assess the different models’ performance. The performance of the various models was evaluated by using the ROC and its area under the curve (AUC). A power analysis was used to assess the effect of sample size on models’ performance. Results: 637 en face OCTA images from 97 patients were included in this analysis. We observed that en face OCTA appearance of the MNV lesion...
Background Large medical centers in urban areas, like Los Angeles, care for a diverse patient pop... more Background Large medical centers in urban areas, like Los Angeles, care for a diverse patient population and offer the potential to study the interplay between genetic ancestry and social determinants of health. Here, we explore the implications of genetic ancestry within the University of California, Los Angeles (UCLA) ATLAS Community Health Initiative—an ancestrally diverse biobank of genomic data linked with de-identified electronic health records (EHRs) of UCLA Health patients (N=36,736). Methods We quantify the extensive continental and subcontinental genetic diversity within the ATLAS data through principal component analysis, identity-by-descent, and genetic admixture. We assess the relationship between genetically inferred ancestry (GIA) and >1500 EHR-derived phenotypes (phecodes). Finally, we demonstrate the utility of genetic data linked with EHR to perform ancestry-specific and multi-ancestry genome and phenome-wide scans across a broad set of disease phenotypes. Resul...
In two-thirds of intensive care unit (ICU) patients and 90% of surgical patients, arterial blood ... more In two-thirds of intensive care unit (ICU) patients and 90% of surgical patients, arterial blood pressure (ABP) is monitored non-invasively but intermittently using a blood pressure cuff. Since even a few minutes of hypotension increases the risk of mortality and morbidity, for the remaining (high-risk) patients ABP is measured continuously using invasive devices, and derived values are extracted from the recorded waveforms. However, since invasive monitoring is associated with major complications (infection, bleeding, thrombosis), the ideal ABP monitor should be both non-invasive and continuous. With large volumes of high-fidelity physiological waveforms, it may be possible today to impute a physiological waveform from other available signals. Currently, the state-of-the-art approaches for ABP imputation only aim at intermittent systolic and diastolic blood pressure imputation, and there is no method that imputes the continuous ABP waveform. Here, we developed a novel approach to i...
Age-related Macular Degeneration (AMD) is a major cause of irreversible vision loss in individual... more Age-related Macular Degeneration (AMD) is a major cause of irreversible vision loss in individuals over 55 years old in the United States. One of the late-stage manifestations of AMD, and a major cause of vision loss, is the development of exudative macular neovascularization (MNV). Optical Coherence Tomography (OCT) is the gold standard to identify fluid at different levels within the retina. The presence of fluid is considered the hallmark to define the presence of disease activity. Anti-vascular growth factor (anti-VEGF) injections can be used to treat exudative MNV. However, given the limitations of anti-VEGF treatment, as burdensome need for frequent visits and repeated injections to sustain efficacy, limited durability of the treatment, poor or no response, there is a great interest in detecting early biomarkers associated with a higher risk for AMD progression to exudative forms in order to optimize the design of early intervention clinical trials. The annotation of structural biomarkers on optical coherence tomography (OCT) B-scans is a laborious, complex and time-consuming process, and discrepancies between human graders can introduce variability into this assessment. To address this issue, a deep-learning model (SLIVER-net) was proposed, which could identify AMD biomarkers on structural OCT volumes with high precision and without human supervision. However, the validation was performed on a small dataset, and the true predictive power of these detected biomarkers in the context of a large cohort has not been evaluated. In this retrospective cohort study, we perform the largest-scale validation of these biomarkers to date. We also assess how these features combined with other EHR data (demographics, comorbidities, etc) affect and/or improve the prediction performance relative to known factors. Our hypothesis is that these biomarkers can be identified by a machine learning algorithm without human supervision, in a way that they preserve their predictive nature. The way we test this hypothesis is by building several machine learning models utilizing these machine-read biomarkers and assessing their added predictive PLOS DIGITAL HEALTH
Age-related Macular Degeneration (AMD) is a major cause of irreversible vision loss in individual... more Age-related Macular Degeneration (AMD) is a major cause of irreversible vision loss in individuals over 55 years old in the United States. While anti-vascular growth factor injections can be used to treat macular neovascularization (MNV), there are currently no treatments available to halt or reverse geographic atrophy, which is the late-stage of nonneovascular AMD. There is a great interest in detecting early biomarkers associated with a higher risk for AMD progression in order to design early intervention clinical trials. The annotation of structural biomarkers on optical coherence tomography (OCT) B-scans is a laborious, complex and time-consuming process, and discrepancies between human graders can introduce variability into this assessment. To address this issue, a deep-learning model (SLIVER-net) was proposed, which could identify AMD biomarkers on structural OCT volumes with high precision and without human supervision. However, the validation was performed on a small datase...
Coronavirus disease 2019 (COVID-19) has exposed health care disparities in minority groups includ... more Coronavirus disease 2019 (COVID-19) has exposed health care disparities in minority groups including Hispanics/Latinxs (HL). Studies of COVID-19 risk factors for HL have relied on county-level data. We investigated COVID-19 risk factors in HL using individual-level, electronic health records in a Los Angeles health system between March 9, 2020, and August 31, 2020. Of 9,287 HL tested for SARS-CoV-2, 562 were positive. HL constituted an increasing percentage of all COVID-19 positive individuals as disease severity escalated. Multiple risk factors identified in Non-Hispanic/Latinx whites (NHL-W), like renal disease, also conveyed risk in HL. Pre-existing nonrheumatic mitral valve disorder was a risk factor for HL hospitalization but not for NHL-W COVID-19 or HL influenza hospitalization, suggesting it may be a specific HL COVID-19 risk. Admission laboratory values also suggested that HL presented with a greater inflammatory response. COVID-19 risk factors for HL can help guide equitable government policies and identify at-risk populations. INTRODUCTION While still in the midst of the coronavirus disease 2019 (COVID-19) pandemic (Center for Systems Science and Engineering at Johns Hopkins University, 2020; Centers for Disease Control and Prevention, 2020; The Lancet, 2020), knowledge of risk factors associated with COVID-19 susceptibility and severity can shape government policies, identify at-risk populations, guide clinical decision-making, and prioritize future COVID-19 research. COVID-19 has further exposed health care disparities exacting a greater toll on minority groups including Hispanic or Latinx communities. COVID-19 diagnosis rates are greater in US counties with a high Latinx proportion compared with those with a low Latinx proportion (91 vs 82 per 100,000) (Rodriguez-Diaz et al., 2020). The Los Angeles County of Public Health data showed the age-adjusted rate of COVID-19 cases is 113 per 100,000 individuals self-reporting as Hispanics/Latinxs (HL) but only 78 for individuals self-reporting as Non-Hispanic/Latinx whites (NHL-W) (Los
Inference of clinical phenotypes is a fundamental task in precision medicine, and has therefore b... more Inference of clinical phenotypes is a fundamental task in precision medicine, and has therefore been heavily investigated in recent years in the context of electronic health records (EHR) using a large arsenal of machine learning techniques, as well as in the context of genetics using polygenic risk scores (PRS). In this work, we considered the epigenetic analog of PRS, methylation risk scores (MRS), a linear combination of methylation states. Since methylation states are influenced by both environmental and genetic factors, we hypothesized that MRS would complement PRS and EHR-based machine-learning methods, improving overall prediction accuracy. To evaluate this hypothesis, we performed the largest assessment of methylation risk scores in clinical datasets to be conducted to date. We measured methylation across a large cohort (n=831) of diverse samples in the UCLA Health biobank, for which both genetic and complete EHR data are available. We constructed MRS for 607 phenotypes span...
One of the core challenges in applying machine learning and artificial intelligence to medicine i... more One of the core challenges in applying machine learning and artificial intelligence to medicine is the limited availability of annotated medical data. Unlike in other applications of machine learning, where an abundance of labeled data is available, the labeling and annotation of medical data and images require a major effort of manual work by expert clinicians who do not have the time to annotate manually. In this work, we propose a new deep learning technique (SLIVER-net), to predict clinical features from 3-dimensional volumes using a limited number of manually annotated examples. SLIVER-net is based on transfer learning, where we borrow information about the structure and parameters of the network from publicly available large datasets. Since public volume data are scarce, we use 2D images and account for the 3-dimensional structure using a novel deep learning method which tiles the volume scans, and then adds layers that leverage the 3D structure. In order to illustrate its uti...
Large medical centers located in urban areas such as Los Angeles care for a diverse patient popul... more Large medical centers located in urban areas such as Los Angeles care for a diverse patient population and offer the potential to study the interplay between genomic ancestry and social determinants of health within a single medical system. Here, we introduce the UCLA ATLAS Community Health Initiative – a biobank of genomic data linked with de-identified electronic health records (EHRs) of UCLA Health patients. We leverage the unique genomic diversity of the patient population in ATLAS to explore the interplay between self-reported race/ethnicity and genetic ancestry within a disease context using phenotypes extracted from the EHR. First, we identify an extensive amount of continental and subcontinental genomic diversity within the ATLAS data that is consistent with the global diversity of Los Angeles; this includes clusters of ATLAS individuals corresponding to individuals with Korean, Japanese, Filipino, and Middle Eastern genomic ancestries. Most importantly, we find that common ...
Understanding the effectiveness of strategies such as social distancing is a central question in ... more Understanding the effectiveness of strategies such as social distancing is a central question in attempts to control the COVID-19 pandemic. A key unknown in social distancing strategies is the duration of time for which such strategies are needed. Answering this question requires an accurate model of the transmission trajectory. A challenge in fitting such a model is the limited COVID-19 case data available from a given location. To overcome this challenge, we propose fitting a model of SARS-CoV-2 transmission jointly across multiple locations. We apply the model to COVID-19 case data from Spain, UK, Germany, France, Denmark, and New York to estimate the distribution for the time needed for social distancing to end to range from May 2020 to July 2021 (95% credible interval), where the median date is October, 2020. Our method is not specific to COVID-19, and it can also be applied to future pandemics.
Background: Rapid, preoperative identification of patients with the highest risk for medical comp... more Background: Rapid, preoperative identification of patients with the highest risk for medical complications is necessary to ensure that limited infrastructure and human resources are directed towards those most likely to benefit. Existing risk scores either lack specificity at the patient level or utilise the American Society of Anesthesiologists (ASA) physical status classification, which requires a clinician to review the chart. Methods: We report on the use of machine learning algorithms, specifically random forests, to create a fully automated score that predicts postoperative in-hospital mortality based solely on structured data available at the time of surgery. Electronic health record data from 53 097 surgical patients (2.01% mortality rate) who underwent general anaesthesia between April 1, 2013 and December 10, 2018 in a large US academic medical centre were used to extract 58 preoperative features. Results: Using a random forest classifier we found that automatically obtained preoperative features (area under the curve [AUC] of 0.932, 95% confidence interval [CI] 0.910e0.951) outperforms Preoperative Score to Predict Postoperative Mortality (POSPOM) scores (AUC of 0.660, 95% CI 0.598e0.722), Charlson comorbidity scores (AUC of 0.742, 95% CI
Uploads
Papers by Nadav Rakocz