A radiomics-based model for the outcome prediction in COVID-19 positive patients through deep learning with both longitudinal chest x-ray and chest computed tomography images

The coronavirus disease 2019 (COVID-19) pandemic had a major impact on global health and was associated with millions of deaths worldwide. During the pandemic, imaging characteristics of chest X-ray (CXR) and chest computed tomography (CT) played an important role in the screening, diagnosis and monitoring the disease progression. Various studies suggested that quantitative image analysis methods including artificial intelligence and radiomics can greatly boost the value of imaging in the management of COVID-19. However, few studies have explored the use of longitudinal multi-modal medical images with varying visit intervals for outcome prediction in COVID-19 patients. This study aims to explore the potential of longitudinal multimodal radiomics in predicting the outcome of COVID-19 patients by integrating both CXR and CT images with variable visit intervals through deep learning. 2274 patients who underwent CXR and/or CT scans during disease progression were selected for this study. Of these, 946 patients were treated at the University of Pennsylvania Health System (UPHS) and the remaining 1328 patients were acquired at Stony Brook University (SBU) and curated by the Medical Imaging and Data Resource Center (MIDRC). 532 radiomic features were extracted with the Cancer Imaging Phenomics Toolkit (CaPTk) from the lung regions in CXR and CT images at all visits. We employed two commonly used deep learning algorithms to analyze the longitudinal multimodal features, and evaluated the prediction results based on the area under the receiver operating characteristic curve (AUC). Our models achieved testing AUC scores of 0.816 and 0.836, respectively, for the prediction of mortality. © 2023 SPIE.

SARS-CoV-2 infections in patients enrolled on the Children's Oncology Group standard-risk B-cell acute lymphoblastic leukemia trial, AALL1731

Hematologic malignancy is a risk factor for severe coronavirus disease 2019 (COVID-19) in adults;however, data specific to children with leukemia are limited. High-quality infectious adverse event data from the ongoing Children's Oncology Group (COG) standard-risk B acute lymphoblastic leukemia/lymphoma (ALL/LLy) trial, AALL1731, were analyzed to provide a disease-specific estimate of SARS-CoV-2 infection outcomes in pediatric ALL. Of 253 patients with reported infections, the majority (77.1%) were asymptomatic or mildly symptomatic (CTCAE grade 1/2) and there was a single COVID-19-related death. These data suggest SARS-CoV-2 infection does not confer substantial morbidity among young patients with B-lymphoblastic leukemia/lymphoma (B-ALL/LLy).Copyright © 2023 The Authors. eJHaem published by British Society for Haematology and John Wiley & Sons Ltd.

To Include an Error Once May Be Regarded as a Misfortune, to Include It Again Looks Like Carelessness

Objectives: Retractions related to COVID-19 publications has highlighted how prevalent retractions of primary research can be. Whilst there is a responsibility for authors of primary research to correct errors or remove fraudulent studies, the responsibility of correcting errors in downstream research is less clear. To further understand the situation we identifyed case studies where evidence synthesis has included retracted articles or articles with subsequently identified errors, how it has been handled and propose potential solutions. Method(s): Identified case studies from work the authors were undertaking where evidence synthesis ended up including primary studies with errors or retractions included. Result(s): Case studies with different responses to errors in primary articles were identified: A typographical error in a primary study was identified in evidence synthesis used to support a NICE health technology assessment;authors of the primary study acknowledged the error but did not correct the publication meaning the error remained in the publication and subsequent meta-analyses. Retracted COVID-19 publications were acknowledged by authors of one published meta-analysis;authors updated analysis to remove the offending research. A primary study was retracted whilst the evidence synthesis publication was under peer-review;following publication authors were notified of the retraction and opted to retract rather than revise their analysis. Conclusion(s): Prevailing errors in evidence synthesis, despite retraction or correction of a primary study, could negatively influence healthcare decision making. Living systematic reviews or meta-analyses are one solution but may not always be practicable. To minimise the risk of perpetuating errors, authors of secondary analyses could commit to ensure data included in their analyses is accurate for a defined period after the initial analysis has been conducted, e.g., 2 years, after which the analyses could be presumed to be outdated. The defined period could be influenced by several factors including rate of new studies being published in the indication. Copyright © 2022

Risks for Hospitalization and Death Among Patients with Blood Disorders from the ASH RC COVID-19 Registry for Hematology

INTRODUCTION: Patients (pts) with blood disorders are at particular risk for severe infection and death from COVID-19. Factors that contribute to this risk, including cancer treatment, have not been clearly delineated. The ASH RC COVID-19 Registry for Hematology is a public-facing, volunteer registry reporting outcomes of COVID-19 infection in pts with underlying blood disorders. We report a multivariable analysis of the impact of cancer treatment and other key variables on COVID-19 mortality and hospitalization among pts with blood cancer. METHODS: Data were collected between April 1, 2020, and July 2, 2021. All analyses were performed using R version 4.0.2. Multivariable logistic regression explored associations between mortality and seven patient/disease factors previously reported as important to COVID-19 outcome. Independent variables included: age (>60);sex;presence of a major comorbidity (defined as any of heart disease, hypertension, pulmonary disease and/or diabetes);type of hematologic malignancy;estimated prognosis of < 6 months prior to COVID-19;deferral of ICU care;and administration of cancer treatment in the previous year (excluding single agent hydroxyurea). A secondary multivariable logistic regression explored associations between the same variables and hospitalization with COVID-19. RESULTS: We included all pts in the registry with a malignant diagnosis except for 3 patients excluded based on a data sharing agreement (N=1029). Median age category was 50-59y (range <5y to > 90y). The sample was 42% female and 28% had major comorbidities. Types of hematologic malignancies were 354 (34%) acute leukemia/MDS, 255 (25%) lymphoma, 206 (20%) plasma cell dyscrasia (myeloma/amyloid/POEMS), 116 (11%) CLL, 98 (10%) myeloproliferative neoplasm (MPN). Most pts (73%) received cancer treatment during the previous year, 9% had a pre-COVID-19 prognosis of <6months, and 10% deferred ICU care. COVID-19 mortality in the entire cohort was 17%. In multivariable analyses, age > 60 (OR 2.03, 1.31-3.18), male sex (OR 1.69, 1.11 - 2.61), estimated pre-COVID-19 prognosis of less than 6 months (OR 6.16, 3.26 - 11.70) and ICU deferral (OR 10.87, 6.36 - 18.96) were all independently associated with an increased risk of death. Receiving cancer treatment in the year prior to COVID-19 diagnosis and type of hematologic malignancy were not significantly associated with death. In multivariable analyses, age > 60 (OR 2.46, 1.83 - 3.31), male sex (OR 1.34, 1.02 - 1.76), estimated pre-COVID-19 prognosis of < 6 months (OR 4.81, 2.45 - 10.50), presence of a major comorbidity (OR 1.57, 1.15 - 2.16), and cancer treatment in the previous year (OR 1.50, 1.10 - 2.06) were all independently associated with an increased risk of a severe COVID-19 requiring hospitalization. Pts with a MPN or plasma cell dyscrasia and COVID-19 were less likely to require hospitalization for COVID-19 compared to patients with CLL, leukemia/MDS, or lymphoma. CONCLUSIONS: These analyses confirm the negative impact of age > 60, male sex, pre-COVID-19 prognosis of < 6 months, and deferral of ICU care on mortality among patients with hematologic malignancy and COVID-19. We did not observe an increased risk of COVID-19 mortality among pts with COVID-19 who received blood cancer treatment in the previous year, although rate of hospitalization was higher. Pts with some hematologic malignancies (MPN, plasma cell dyscrasias), may experience less severe COVID-19 infections than others. Disclosures: Anderson: Celgene: Membership on an entity's Board of Directors or advisory committees;Millenium-Takeda: Membership on an entity's Board of Directors or advisory committees;Gilead: Membership on an entity's Board of Directors or advisory committees;Janssen: Membership on an entity's Board of Directors or advisory committees;Sanofi-Aventis: Membership on an entity's Board of Directors or advisory committees;Bristol Myers Squibb: Membership on an entity's Board of Directors or advisory committees;Pfizer: Membership on an entity's Board of Directors or advisory committees;Scientific Founder of Oncopep and C4 Therapeutics: Current equity holder in publicly-traded company, Current holder of individual stocks in a privately-held company;AstraZeneca: Membership on an entity's Board of Directors or advisory committees;Mana Therapeutics: Membership on an entity's Board of Directors or advisory committees. Desai: Janssen R&D: Research Funding;Astex: Research Funding;Kura Oncology: Consultancy;Agios: Consultancy;Bristol Myers Squibb: Consultancy;Takeda: Consultancy. Goldberg: Celularity: Research Funding;Genentech: Consultancy, Membership on an entity's Board of Directors or advisory committees;Astellas: Consultancy, Membership on an entity's Board of Directors or advisory committees;Aptose: Consultancy, Research Funding;Prelude Therapeutics: Research Funding;DAVA Oncology: Honoraria;Pfizer: Research Funding;Arog: Research Funding;Aprea: Research Funding;AbbVie: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding. Neuberg: Madrigal Pharmaceuticals: Other: Stock ownership;Pharmacyclics: Research Funding. Radhakrishnan: Janssen India: Honoraria;Dr Reddy's Laboratories: Honoraria, Membership on an entity's Board of Directors or advisory committees;Aurigene: Speakers Bureau;Novartis: Honoraria;Johnson and Johnson: Honoraria;Pfizer: Consultancy, Honoraria;Astrazeneca: Consultancy, Honoraria;Emcure Pharmaceuticals: Other: payment to institute;Cipla Pharmaceuticals: Honoraria, Other: payment to institute;Bristol Myers Squibb: Other: payment to institute;Roche: Honoraria, Other: payment to institute;Intas Pharmaceutical: Other: payment to institute;NATCO Pharmaceuticals: Research Funding. Sehn: Genmab: Consultancy;Debiopharm: Consultancy;Novartis: Consultancy. Sekeres: Novartis: Membership on an entity's Board of Directors or advisory committees;Takeda/Millenium: Membership on an entity's Board of Directors or advisory committees;BMS: Membership on an entity's Board of Directors or advisory committees. Tallman: Kura: Membership on an entity's Board of Directors or advisory committees;Syros: Membership on an entity's Board of Directors or advisory committees;Innate Pharma: Membership on an entity's Board of Directors or advisory committees;Novartis: Membership on an entity's Board of Directors or advisory committees;Biosight: Membership on an entity's Board of Directors or advisory committees;Roche: Membership on an entity's Board of Directors or advisory committees;Jazz Pharma: Membership on an entity's Board of Directors or advisory committees;Oncolyze: Membership on an entity's Board of Directors or advisory committees;KAHR: Membership on an entity's Board of Directors or advisory committees;Orsenix: Membership on an entity's Board of Directors or advisory committees;Daiichi-Sankyo: Membership on an entity's Board of Directors or advisory committees;Abbvie: Membership on an entity's Board of Directors or advisory committees;Amgen: Research Funding;Rafael Pharmaceuticals: Research Funding;Glycomimetics: Research Funding;Biosight: Research Funding;Orsenix: Research Funding;Abbvie: Research Funding;NYU Grand Rounds: Honoraria;Mayo Clinic: Honoraria;UC DAVIS: Honoraria;Northwell Grand Rounds: Honoraria;NYU Grand Rounds: Honoraria;Danbury Hospital Tumor Board: Honoraria;Acute Leukemia Forum: Honoraria;Miami Leukemia Symposium: Honoraria;New Orleans Cancer Symposium: Honoraria;ASH: Honoraria;NCCN: Honoraria.

Clinical Predictors of Outcome in Adult Patients with Acute Leukemias and Myelodysplastic Syndrome and COVID-19 Infection: Report from the American Society of Hematology Research Collaborative (ASH RC) Data Hub

Background: Predictors of severe infection and outcomes with COVID-19 in patients (pts) with acute myeloid leukemia (AML), acute lymphocytic leukemia (ALL) and myelodysplastic syndromes (MDS) are lacking. Pts with active disease may experience worse outcomes due to overall prognosis and cytopenias. Here we identify risk factors for severe COVID-19 infection and mortality in pts with AML, MDS, and ALL using the ASH RC COVID-19 Registry for Hematology. Methods: The ASH RC COVID-19 Registry for Hematology includes features and outcomes of a laboratory-confirmed or presumptive diagnosis of SARS-CoV-2 infection in adult pts with ongoing or a history of blood disorders. The Registry opened for data collection on April 1, 2020 and is a global effort housed on a secure data platform hosted by Prometheus Research, an IQVIA company. Data are made publicly available and regularly updated on the ASH RC website. Pt characteristics, outcomes, and predictors were analyzed and stratified by disease status (active initial diagnosis and relapsed/refractory vs. remission) and type of hematologic malignancy. Variables included age, comorbidities, type of hematologic malignancy (AML, MDS, ALL), neutrophil and lymphocyte count at time of COVID-19 diagnosis, and active treatment at the time of COVID-19 diagnosis. COVID-19 severity was defined as mild (no hospitalization required), moderate (hospitalization required), or severe (ICU admission required). Categorical pt characteristics for each response group and associations between response groups and characteristics (i.e., alive vs. dead, severity vs. non-severity) were summarized by frequency with differences between response groups evaluated by Fisher's exact test and odds ratios with 95% confidence intervals (CIs) estimated by logistic regression. Multivariable analyses identified independent predictors of outcomes. Results: Analyses were conducted on data from 257 pts with AML (n=135), MDS (n=40), and ALL (n=82);46% were in remission and 44% had active disease (10% unknown). Overall mortality from COVID-19 infection was 21%. Pts with active disease were significantly more likely to present with moderate and severe COVID-19 compared to those in remission (remission vs. active disease, severe 33% (n=20) vs. 67%(n=40), moderate 45% (n=35) vs.55% (n=42), and mild: 67% (n=56) vs. 33% (n=28), p value <0.001) (Figure 1). This was significant when categorized as severe vs. non severe as well (p=0.002). COVID-19 severity was also associated with AML diagnosis, major comorbidities, and neutropenia and lymphopenia at the time of COVID-19 diagnosis. Univariate analyses of increased mortality after COVID-19 diagnosis were significantly associated with advanced age, male sex, pre-diagnosis survival < 6 months, active disease status, neutropenia, lymphopenia and forgoing ICU care. Multivariable analyses in all pts (Figure 1), revealed that increased COVID-19 related mortality was significantly associated with neutropenia at diagnosis (OR 3.15, 95% C.I. 1.31-8.08, p=0.01), estimated pre-COVID-19 prognosis of < 6 months (OR 8.58, 95% C.I. 3.24-24.46, p<0.001) and forgoing ICU care (OR 6.66, 95% C.I. 2.56-18.23, p<0.001). Among hospitalized pts, increased COVID-19 mortality was associated with estimated pre-COVID-19 prognosis of < 6 months (OR 6.77, 95% C.I. 2.34-22.24, p<0.001) and forgoing ICU care (OR 3.98, 95% C.I. 1.45-11.66, p=0.007). Pts who were older, male, smokers, with active disease, or estimated to have pre-COVID-19 survival of < 6 months were more likely to forgo ICU care. Forgoing ICU care (n=37,16%) was associated with a higher COVID-19 mortality in all pts (n=234, OR 15.6, 95% C.I. 6.4-40.9, p<0.001), hospitalized pts (n=143, OR 9.2, 95% C.I., 3.5-26.5, p<0.001) and in pts where ICU admission was indicated and declined (n=61 OR 5.6, 95% C.I. 1.1-56.4, p=0.03)). Neither active disease status nor ongoing cancer treatment were associated with increased mortality among hospitalized patients. Conclusions: These data suggest that patients with active disease experience significantly higher COVID-19 severity but not increased mortality from COVID-19. Patients who had neutropenia and a pre-COVID-19 prognosis of < 6 months had higher mortality from COVID-19 infection and may be more likely to forgo ICU care. If desired by patients, aggressive support for hospitalized patients with COVID-19 is appropriate regardless of remission status. [Formula presented] Disclosures: Desai: Agios: Consultancy;Janssen R&D: Research Funding;Kura Oncology: Consultancy;Bristol Myers Squibb: Consultancy;Astex: Research Funding;Takeda: Consultancy. Goldberg: AbbVie: Consultancy, Membership on an entity's Board of Directors or advisory committees, Research Funding;Aprea: Research Funding;Prelude Therapeutics: Research Funding;Pfizer: Research Funding;Genentech: Consultancy, Membership on an entity's Board of Directors or advisory committees;DAVA Oncology: Honoraria;Astellas: Consultancy, Membership on an entity's Board of Directors or advisory committees;Arog: Research Funding;Celularity: Research Funding;Aptose: Consultancy, Research Funding. Anderson: Sanofi-Aventis: Membership on an entity's Board of Directors or advisory committees;Celgene: Membership on an entity's Board of Directors or advisory committees;Gilead: Membership on an entity's Board of Directors or advisory committees;Janssen: Membership on an entity's Board of Directors or advisory committees;Bristol Myers Squibb: Membership on an entity's Board of Directors or advisory committees;Pfizer: Membership on an entity's Board of Directors or advisory committees;Millenium-Takeda: Membership on an entity's Board of Directors or advisory committees;Scientific Founder of Oncopep and C4 Therapeutics: Current equity holder in publicly-traded company, Current holder of individual stocks in a privately-held company;AstraZeneca: Membership on an entity's Board of Directors or advisory committees;Mana Therapeutics: Membership on an entity's Board of Directors or advisory committees. Neuberg: Pharmacyclics: Research Funding;Madrigal Pharmaceuticals: Other: Stock ownership. Radhakrishnan: Emcure Pharmaceuticals: Other: payment to institute;Bristol Myers Squibb: Other: payment to institute;Astrazeneca: Consultancy, Honoraria;Cipla Pharmaceuticals: Honoraria, Other: payment to institute;Pfizer: Consultancy, Honoraria;Johnson and Johnson: Honoraria;Novartis: Honoraria;Aurigene: Speakers Bureau;Roche: Honoraria, Other: payment to institute;Intas Pharmaceutical: Other: payment to institute;Dr Reddy's Laboratories: Honoraria, Membership on an entity's Board of Directors or advisory committees;Janssen India: Honoraria;NATCO Pharmaceuticals: Research Funding. Roboz: Novartis: Consultancy;Mesoblast: Consultancy;Amgen: Consultancy;Actinium: Consultancy;AbbVie: Consultancy;Janssen: Consultancy;Blueprint Medicines: Consultancy;Astex: Consultancy;Janssen: Research Funding;Daiichi Sankyo: Consultancy;Jazz: Consultancy;Agios: Consultancy;Glaxo SmithKline: Consultancy;Celgene: Consultancy;Otsuka: Consultancy;Astellas: Consultancy;Helsinn: Consultancy;MEI Pharma - IDMC Chair: Consultancy;Jasper Therapeutics: Consultancy;Bristol Myers Squibb: Consultancy;AstraZeneca: Consultancy;Bayer: Consultancy;Pfizer: Consultancy;Roche/Genentech: Consultancy. Sehn: Novartis: Consultancy;Genmab: Consultancy;Debiopharm: Consultancy. Sekeres: Takeda/Millenium: Membership on an entity's Board of Directors or advisory committees;Novartis: Membership on an entity's Board of Directors or advisory committees;BMS: Membership on an entity's Board of Directors or advisory committees. Tallman: Syros: Membership on an entity's Board of Directors or advisory committees;Kura: Membership on an entity's Board of Directors or advisory committees;NYU Grand Rounds: Honoraria;Innate Pharma: Membership on an entity's Board of Directors or advisory committees;Novartis: Membership on an entity's Board of Directors or advisory committees;Biosight: Membership on an entity's Board of Directors or advisory committees;Roche: Membership on an entity's Board of Directors or advisory committees;Jazz Pharma: Membership on an entity's Board of Directors or advisory committees;Oncolyze: Membership on an entity's Board of Directors or advisory committees;KAHR: Membership on an entity's Board of Directors or advisory committees;Orsenix: Membership on an entity's Board of Directors or advisory committees;Daiichi-Sankyo: Membership on an entity's Board of Directors or advisory committees;Abbvie: Membership on an entity's Board of Directors or advisory committees;Amgen: Research Funding;Rafael Pharmaceuticals: Research Funding;Glycomimetics: Research Funding;Biosight: Research Funding;Orsenix: Research Funding;Abbvie: Research Funding;Mayo Clinic: Honoraria;UC DAVIS: Honoraria;Northwell Grand Rounds: Honoraria;NYU Grand Rounds: Honoraria;Danbury Hospital Tumor Board: Honoraria;Acute Leukemia Forum: Honoraria;Miami Leukemia Symposium: Honoraria;New Orleans Cancer Symposium: Honoraria;ASH: Honoraria;NCCN: Honoraria. Wood: Pfizer: Research Funding;Teladoc: Consultancy;Koneksa Health: Consultancy, Current equity holder in publicly-traded company.