Characterizing Thrombotic Complication Risk Factors Associated With COVID-19 via Heterogeneous Patient Data: Retrospective Observational Study.

BACKGROUND: COVID-19 has been observed to be associated with venous and arterial thrombosis. The inflammatory disease prolongs hospitalization, and preexisting comorbidities can intensity the thrombotic burden in patients with COVID-19. However, venous thromboembolism, arterial thrombosis, and other vascular complications may go unnoticed in critical care settings. Early risk stratification is paramount in the COVID-19 patient population for proactive monitoring of thrombotic complications. OBJECTIVE: The aim of this exploratory research was to characterize thrombotic complication risk factors associated with COVID-19 using information from electronic health record (EHR) and insurance claims databases. The goal is to develop an approach for analysis using real-world data evidence that can be generalized to characterize thrombotic complications and additional conditions in other clinical settings as well, such as pneumonia or acute respiratory distress syndrome in COVID-19 patients or in the intensive care unit. METHODS: We extracted deidentified patient data from the insurance claims database IBM MarketScan, and formulated hypotheses on thrombotic complications in patients with COVID-19 with respect to patient demographic and clinical factors using logistic regression. The hypotheses were then verified with analysis of deidentified patient data from the Research Patient Data Registry (RPDR) Mass General Brigham (MGB) patient EHR database. Data were analyzed according to odds ratios, 95% CIs, and P values. RESULTS: The analysis identified significant predictors (P<.001) for thrombotic complications in 184,831 COVID-19 patients out of the millions of records from IBM MarketScan and the MGB RPDR. With respect to age groups, patients 60 years and older had higher odds (4.866 in MarketScan and 6.357 in RPDR) to have thrombotic complications than those under 60 years old. In terms of gender, men were more likely (odds ratio of 1.245 in MarketScan and 1.693 in RPDR) to have thrombotic complications than women. Among the preexisting comorbidities, patients with heart disease, cerebrovascular diseases, hypertension, and personal history of thrombosis all had significantly higher odds of developing a thrombotic complication. Cancer and obesity were also associated with odds>1. The results from RPDR validated the IBM MarketScan findings, as they were largely consistent and afford mutual enrichment. CONCLUSIONS: The analysis approach adopted in this study can work across heterogeneous databases from diverse organizations and thus facilitates collaboration. Searching through millions of patient records, the analysis helped to identify factors influencing a phenotype. Use of thrombotic complications in COVID-19 patients represents only a case study; however, the same design can be used across other disease areas by extracting corresponding disease-specific patient data from available databases.

Workforce readiness for pharmacogenomics and key elements for sustainment within the Veterans Health Administration.

Aim: Understanding barriers and facilitators to pharmacogenomics (PGx) implementation and how to structure a clinical program with the Veterans Health Administration (VA). Materials & methods: Healthcare provider (HCP) survey at 20 VA facilities assessing PGx knowledge/acceptance and qualitative interviews to understand how best to design and sustain a national program. Results: 186 (12% response rate) surveyed believed PGx informs drug efficacy (74.7%) and adverse events (71.0%). Low confidence in knowledge (43.0%) and ability to implement (35.4-43.5%). 23 (60.5% response rate) interviewees supported a nationally program to oversee VA education, consultation and IT resources. Prescribing HCPs should be directing local activities. Conclusion: HCPs recognize PGx value but are not prepared to implement. Healthcare systems should build system-wide programs for implementation education and support.

Mutational profiles of head and neck squamous cell carcinomas based upon human papillomavirus status in the Veterans Affairs National Precision Oncology Program.

BACKGROUND: Patients with advanced head and neck squamous cell carcinoma (HNSCC) associated with human papillomavirus (HPV) demonstrate favorable clinical outcomes compared to patients bearing HPV-negative HNSCC. We sought to characterize the association between HPV status and mutational profiles among patients served by the Veterans Health Administration (VHA). METHODS: We performed a retrospective analysis of all Veterans with primary HNSCC tumors who underwent next-generation sequencing (NGS) through the VHA's National Precision Oncology Program between July 2016 and February 2019. HPV status was determined by clinical pathology reports of p16 immunohistochemical staining; gene variant pathogenicity was classified using OncoKB, an online precision oncology knowledge database, and mutation frequencies were compared using Fisher's exact test. RESULTS: A total of 79 patients met inclusion criteria, of which 48 (60.8%) had p16-positive tumors. Patients with p16-negative HNSCC were more likely to have mutations in TP53 (p < 0.0001), and a trend towards increased mutation frequency was observed within NOTCH1 (p = 0.032) and within the composite CDK/Rb pathway (p = 0.065). Mutations in KRAS, NRAS, HRAS, and FBXW7 were exclusively identified within p16-positive tumors, and a trend towards increased frequency was observed within the PI3K pathway (p = 0.051). No difference in overall mutational burden was observed between the two groups. CONCLUSIONS: In accordance with the previous studies, no clear molecular basis for improved prognosis among patients harboring HPV-positive disease has been elucidated. Though no targeted therapies are approved based upon HPV-status, current efforts to trial PI3K inhibitors and mTOR inhibitors across patients with HPV-positive disease bear genomic rationale based upon the current findings.

Artificial Intelligence and Machine Learning Technologies in Cancer Care: Addressing Disparities, Bias, and Data Diversity.

SUMMARY: Artificial intelligence (AI) and machine learning (ML) technologies have not only tremendous potential to augment clinical decision-making and enhance quality care and precision medicine efforts, but also the potential to worsen existing health disparities without a thoughtful, transparent, and inclusive approach that includes addressing bias in their design and implementation along the cancer discovery and care continuum. We discuss applications of AI/ML tools in cancer and provide recommendations for addressing and mitigating potential bias with AI and ML technologies while promoting cancer health equity.

Characterizing Pain Points in Clinical Data Management and Assessing the Impact of Mid-Study Updates.

BACKGROUND: The causes, degree and disruptive nature of mid-study database updates and other pain points were evaluated to understand if and how the clinical data management function is managing rapid growth in data volume and diversity. METHODS: Tufts Center for the Study of Drug Development (Tufts CSDD)-in collaboration with IBM Watson Health-conducted an online global survey between September and October 2020. RESULTS: One hundred ninety four verified responses were analyzed. Planned and unplanned mid-study updates were the top challenges mentioned and their management was time intensive. Respondents reported an average of 4.1 planned and 3.7 unplanned mid-study updates per clinical trial. CONCLUSION: Mid-study database updates are disruptive and present a major opportunity to accelerate cycle times and improve efficiency, particularly as protocol designs become more flexible and the diversity of data, most notably unstructured data, increases.

Precision Medicine, AI, and the Future of Personalized Health Care.

The convergence of artificial intelligence (AI) and precision medicine promises to revolutionize health care. Precision medicine methods identify phenotypes of patients with less-common responses to treatment or unique healthcare needs. AI leverages sophisticated computation and inference to generate insights, enables the system to reason and learn, and empowers clinician decision making through augmented intelligence. Recent literature suggests that translational research exploring this convergence will help solve the most difficult challenges facing precision medicine, especially those in which nongenomic and genomic determinants, combined with information from patient symptoms, clinical history, and lifestyles, will facilitate personalized diagnosis and prognostication.

Clinical insights into hematologic malignancies and comparative analysis of molecular signatures of acute myeloid leukemia in different ethnicities using an artificial intelligence offering.

ABSTRACT: Next generation sequencing generates copious amounts of genomics data, causing manual interpretation to be laborious and non-scalable while remaining subjective (even for highly trained specialists). We evaluated the performance of the artificial intelligence-based offering Watson for Genomics (WfG), a variant interpretation platform, in hematologic malignancies for the first time.Next generation sequencing was performed for patients treated for various hematological malignancies at Hallym University Sacred Heart Hospital, South Korea, between December 2017 and August 2020 using a 54-gene panel. Both WfG and expert manual curation were used to evaluate the performance of WfG. Acute myeloid leukemia (AML) molecular profiles were compared between Koreans and other ethnic groups using a publicly available dataset.Seventy-seven patients were analyzed (AML: 45, myeloproliferative neoplasms: 12, multiple myeloma: 7, myelodysplastic syndromes: 6, and others: 7). The concordance between the manual and WfG interpretations of 35 variants in 11 random patients was 94%. Among all patients, WfG identified 39 (51%) with at least 1 clinically actionable therapeutic alteration (i.e., a variant targeted by a United States Food and Drug Administration [US FDA]-approved drug, off-label drug, or clinical trial). Moreover, 46% of these patients (18/39) had genes that were targeted by a US FDA-approved therapy. WfG identified diagnostic or prognostic insights in 65% of the patients with no targetable alterations. In those with AML, FLT3-internal tandem duplications or tyrosine kinase domain mutations were less frequent among Koreans than among Caucasians (6.7% vs 30.2%, P < .001) or Hispanics (6.7% vs 28.3%, P = .005), suggesting ethnic differences.Variant interpretation using WfG correlated well with manually curated expert opinions. WfG provided therapeutic insights (including variant-specific drugs and clinical trials that cannot easily be provided by expert manual curation), as well as diagnostic and/or prognostic information.

Barriers to Prescribing Targeted Therapies for Patients With NSCLC With Highly Actionable Gene Variants in the Veterans Affairs National Precision Oncology Program.

PURPOSE: Next-generation sequencing (NGS) gene panels are frequently completed for patients with advanced non-small-cell lung cancer (NSCLC). Patients with highly actionable gene variants have improved outcomes and reduced toxicities with the use of corresponding targeted agents. We sought to identify barriers to targeted agent use within the Veterans Health Affairs' National Precision Oncology Program (NPOP). METHODS: A retrospective evaluation of patients with NSCLC who underwent NGS multigene panels through NPOP between July 2015 and February 2019 was conducted. Patients who were assigned level 1 or 2A evidence for oncogenic gene variants by an artificial intelligence offering (IBM Watson for Genomics [WfG]) and NPOP staff were selected. Antineoplastic drug prescriptions and provider notes were reviewed. Reasons for withholding targeted treatments were categorized. RESULTS: Of 1,749 patients with NSCLC who successfully underwent NGS gene panel testing, 112 (6.4%) patients were assigned level 1 and/or 2A evidence for available targeted treatments by WfG and NPOP staff. All highly actionable gene variants were within ALK, BRAF, EGFR, ERBB2, MET, RET, and ROS1. Of these, 36 (32.1%) patients were not prescribed targeted agents. The three most common reasons were (1) patient did not carry a diagnosis of metastatic disease (33.3%), (2) treating provider did not comment on the NGS results (25.0%), and (3) provider felt that patient could not tolerate therapy (19.4%). No patients were denied access to level 1 or 2A targeted drugs because of rejection of a nonformulary drug request. CONCLUSION: A substantial minority of patients with NSCLC bearing highly actionable gene variants are not prescribed targeted agents. Further provider- and pathologist-directed educational efforts and implementation of health informatics systems to provide real-time decision support for test ordering and interpretation are needed.

Emergence of Drift Variants That May Affect COVID-19 Vaccine Development and Antibody Treatment.

New coronavirus (SARS-CoV-2) treatments and vaccines are under development to combat COVID-19. Several approaches are being used by scientists for investigation, including (1) various small molecule approaches targeting RNA polymerase, 3C-like protease, and RNA endonuclease; and (2) exploration of antibodies obtained from convalescent plasma from patients who have recovered from COVID-19. The coronavirus genome is highly prone to mutations that lead to genetic drift and escape from immune recognition; thus, it is imperative that sub-strains with different mutations are also accounted for during vaccine development. As the disease has grown to become a pandemic, B-cell and T-cell epitopes predicted from SARS coronavirus have been reported. Using the epitope information along with variants of the virus, we have found several variants which might cause drifts. Among such variants, 23403A>G variant (p.D614G) in spike protein B-cell epitope is observed frequently in European countries, such as the Netherlands, Switzerland, and France, but seldom observed in China.

A Narrative Review of Emerging Therapeutics for COVID-19.

The novel severe acute respiratory syndrome coronavirus 2, the causal agent of coronavirus disease 2019 (COVID-19), quickly spread around the world, resulting in the most aggressive pandemic experienced in more than 100 years. Research on targeted therapies and vaccines has been initiated on an unprecedented scale and speed but will take months and even years to come to fruition. Meanwhile, the efficacy of emerging therapeutics for use in treating COVID-19 is feverishly being investigated to identify the best available treatment options for dealing with the current wave of disease. This review of publications with a "treatment" tag through June 29, 2020 in the National Library of Medicine's LitCovid literature hub, provides frontline clinicians with a pragmatic summary of the current state of the rapidly evolving evidence supporting emerging candidate therapeutics for COVID-19. Two main categories of pharmaceutical therapeutics are showing promise: those with antiviral activity directly addressing infection and those that counteract the inflammatory cytokine storm induced by severe disease. Preliminary results suggest that other approaches such as convalescent plasma therapy and lung radiation therapy may have some efficacy. The current clinical evidence for potential treatments is preliminary-often small retrospective series or early results of randomized trials-and the science is evolving rapidly. The long-term results from large, well-designed randomized controlled trials will provide definitive evidence for therapeutic effectiveness and are likely months away. The trial landscape for promising therapies is described.

Medical oncologists' perspectives of the Veterans Affairs National Precision Oncology Program.

BACKGROUND: To support the rising need for testing and to standardize tumor DNA sequencing practices within the U.S. Department of Veterans Affairs (VA)'s Veterans Health Administration (VHA), the National Precision Oncology Program (NPOP) was launched in 2016. We sought to assess oncologists' practices, concerns, and perceptions regarding Next-Generation Sequencing (NGS) and the NPOP. MATERIALS AND METHODS: Using a purposive total sampling approach, oncologists who had previously ordered NGS for at least one tumor sample through the NPOP were invited to participate in semi-structured interviews. Questions assessed the following: expectations for the NPOP, procedural requirements, applicability of testing results, and the summative utility of the NPOP. Interviews were assessed using an open coding approach. Thematic analysis was conducted to evaluate the completed codebook. Themes were defined deductively by reviewing the direct responses to interview questions as well as inductively by identifying emerging patterns of data. RESULTS: Of the 105 medical oncologists who were invited to participate, 20 (19%) were interviewed from 19 different VA medical centers in 14 states. Five recurrent themes were observed: (1) Educational Efforts Regarding Tumor DNA Sequencing Should be Undertaken, (2) Pathology Departments Share a Critical Role in Facilitating Test Completion, (3) Tumor DNA Sequencing via NGS Serves as the Most Comprehensive Testing Modality within Precision Oncology, (4) The Availability of the NPOP Has Expanded Options for Select Patients, and (5) The Completion of Tumor DNA Sequencing through the NPOP Could Help Improve Research Efforts within VHA Oncology Practices. CONCLUSION: Medical oncologists believe that the availability of tumor DNA sequencing through the NPOP could potentially lead to an improvement in outcomes for veterans with metastatic solid tumors. Efforts should be directed toward improving oncologists' understanding of sequencing, strengthening collaborative relationships between oncologists and pathologists, and assessing the role of comprehensive NGS panels within the battery of precision tests.

Predictive article recommendation using natural language processing and machine learning to support evidence updates in domain-specific knowledge graphs.

OBJECTIVES: Describe an augmented intelligence approach to facilitate the update of evidence for associations in knowledge graphs. METHODS: New publications are filtered through multiple machine learning study classifiers, and filtered publications are combined with articles already included as evidence in the knowledge graph. The corpus is then subjected to named entity recognition, semantic dictionary mapping, term vector space modeling, pairwise similarity, and focal entity match to identify highly related publications. Subject matter experts review recommended articles to assess inclusion in the knowledge graph; discrepancies are resolved by consensus. RESULTS: Study classifiers achieved F-scores from 0.88 to 0.94, and similarity thresholds for each study type were determined by experimentation. Our approach reduces human literature review load by 99%, and over the past 12 months, 41% of recommendations were accepted to update the knowledge graph. CONCLUSION: Integrated search and recommendation exploiting current evidence in a knowledge graph is useful for reducing human cognition load.