1
|
Su C, Hou Y, Xu J, Xu Z, Zhou M, Ke A, Li H, Xu J, Brendel M, Maasch JRMA, Bai Z, Zhang H, Zhu Y, Cincotta MC, Shi X, Henchcliffe C, Leverenz JB, Cummings J, Okun MS, Bian J, Cheng F, Wang F. Identification of Parkinson's disease PACE subtypes and repurposing treatments through integrative analyses of multimodal data. NPJ Digit Med 2024; 7:184. [PMID: 38982243 PMCID: PMC11233682 DOI: 10.1038/s41746-024-01175-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/24/2023] [Accepted: 06/21/2024] [Indexed: 07/11/2024] Open
Abstract
Parkinson's disease (PD) is a serious neurodegenerative disorder marked by significant clinical and progression heterogeneity. This study aimed at addressing heterogeneity of PD through integrative analysis of various data modalities. We analyzed clinical progression data (≥5 years) of individuals with de novo PD using machine learning and deep learning, to characterize individuals' phenotypic progression trajectories for PD subtyping. We discovered three pace subtypes of PD exhibiting distinct progression patterns: the Inching Pace subtype (PD-I) with mild baseline severity and mild progression speed; the Moderate Pace subtype (PD-M) with mild baseline severity but advancing at a moderate progression rate; and the Rapid Pace subtype (PD-R) with the most rapid symptom progression rate. We found cerebrospinal fluid P-tau/α-synuclein ratio and atrophy in certain brain regions as potential markers of these subtypes. Analyses of genetic and transcriptomic profiles with network-based approaches identified molecular modules associated with each subtype. For instance, the PD-R-specific module suggested STAT3, FYN, BECN1, APOA1, NEDD4, and GATA2 as potential driver genes of PD-R. It also suggested neuroinflammation, oxidative stress, metabolism, PI3K/AKT, and angiogenesis pathways as potential drivers for rapid PD progression (i.e., PD-R). Moreover, we identified repurposable drug candidates by targeting these subtype-specific molecular modules using network-based approach and cell line drug-gene signature data. We further estimated their treatment effects using two large-scale real-world patient databases; the real-world evidence we gained highlighted the potential of metformin in ameliorating PD progression. In conclusion, this work helps better understand clinical and pathophysiological complexity of PD progression and accelerate precision medicine.
Collapse
Grants
- R21 AG083003 NIA NIH HHS
- R01 AG082118 NIA NIH HHS
- R56 AG074001 NIA NIH HHS
- R01AG076448 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- RF1AG072449 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- MJFF-023081 Michael J. Fox Foundation for Parkinson's Research (Michael J. Fox Foundation)
- R01AG080991 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- P30 AG072959 NIA NIH HHS
- 3R01AG066707-01S1 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- R21AG083003 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- R01AG066707 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- R35 AG071476 NIA NIH HHS
- RF1 AG082211 NIA NIH HHS
- R56AG074001 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- R01AG082118 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- R25 AG083721 NIA NIH HHS
- RF1AG082211 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- U01 NS093334 NINDS NIH HHS
- AG083721-01 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- RF1NS133812 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- P20GM109025 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- RF1 NS133812 NINDS NIH HHS
- R35AG71476 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- U01 AG073323 NIA NIH HHS
- R01 AG066707 NIA NIH HHS
- R01AG053798 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- R01AG076234 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- R01 AG076448 NIA NIH HHS
- R01 AG080991 NIA NIH HHS
- R01 AG076234 NIA NIH HHS
- U01NS093334 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- P20 GM109025 NIGMS NIH HHS
- P30AG072959 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- RF1 AG072449 NIA NIH HHS
- R01 AG053798 NIA NIH HHS
- 3R01AG066707-02S1 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- U01AG073323 Foundation for the National Institutes of Health (Foundation for the National Institutes of Health, Inc.)
- ALZDISCOVERY-1051936 Alzheimer's Association
Collapse
Affiliation(s)
- Chang Su
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, USA
- Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, Cornell University, New York, NY, USA
| | - Yu Hou
- Department of Surgery, University of Minnesota, Minneapolis, MN, USA
| | - Jielin Xu
- Genomic Medicine Institute, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Zhenxing Xu
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, USA
- Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, Cornell University, New York, NY, USA
| | - Manqi Zhou
- Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, Cornell University, New York, NY, USA
- Department of Computational Biology, Cornell University, Ithaca, NY, USA
| | - Alison Ke
- Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, Cornell University, New York, NY, USA
- Department of Computational Biology, Cornell University, Ithaca, NY, USA
| | - Haoyang Li
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, USA
- Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, Cornell University, New York, NY, USA
| | - Jie Xu
- Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, FL, USA
| | - Matthew Brendel
- Institute for Computational Biomedicine, Department of Physiology and Biophysics, Weill Cornell Medicine, New York, NY, USA
| | - Jacqueline R M A Maasch
- Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, Cornell University, New York, NY, USA
- Department of Computer Science, Cornell Tech, Cornell University, New York, NY, USA
| | - Zilong Bai
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, USA
- Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, Cornell University, New York, NY, USA
| | - Haotan Zhang
- Department of Physiology and Biophysics, Weill Cornell Medicine, New York, NY, USA
| | - Yingying Zhu
- Department of Computer Science, University of Texas at Arlington, Arlington, TX, USA
| | - Molly C Cincotta
- Lewis Katz School of Medicine, Temple University, Philadelphia, PA, USA
| | - Xinghua Shi
- Department of Computer and Information Sciences, Temple University, Philadelphia, PA, USA
| | - Claire Henchcliffe
- Department of Neurology, University of California Irvine, Irvine, CA, USA
| | - James B Leverenz
- Lou Ruvo Center for Brain Health, Neurological Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Jeffrey Cummings
- Chambers-Grundy Center for Transformative Neuroscience, Pam Quirk Brain Health and Biomarker Laboratory, Department of Brain Health, School of Integrated Health Sciences, University of Nevada Las Vegas, Las Vegas, NV, USA
| | - Michael S Okun
- Department of Neurology, Fixel Institute for Neurological Diseases, University of Florida, Gainesville, FL, USA
| | - Jiang Bian
- Department of Health Outcomes and Biomedical Informatics, University of Florida, Gainesville, FL, USA
| | - Feixiong Cheng
- Genomic Medicine Institute, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
- Department of Molecular Medicine, Cleveland Clinic Lerner College of Medicine, Case Western Reserve University, Cleveland, OH, USA
| | - Fei Wang
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York, NY, USA.
- Institute of Artificial Intelligence for Digital Health, Weill Cornell Medicine, Cornell University, New York, NY, USA.
| |
Collapse
|
2
|
Yu J, Zhang K, Chen T, Lin R, Chen Q, Chen C, Tong M, Chen J, Yu J, Lou Y, Xu P, Zhong C, Chen Q, Sun K, Liu L, Cao L, Zheng C, Wang P, Chen Q, Yang Q, Chen W, Wang X, Yan Z, Zhang X, Cui W, Chen L, Zhang Z, Zhang G. Temporal patterns of organ dysfunction in COVID-19 patients hospitalized in the intensive care unit: A group-based multitrajectory modeling analysis. Int J Infect Dis 2024; 144:107045. [PMID: 38604470 DOI: 10.1016/j.ijid.2024.107045] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2023] [Revised: 03/19/2024] [Accepted: 04/07/2024] [Indexed: 04/13/2024] Open
Abstract
BACKGROUND The course of organ dysfunction (OD) in Corona Virus Disease 2019 (COVID-19) patients is unknown. Herein, we analyze the temporal patterns of OD in intensive care unit-admitted COVID-19 patients. METHODS Sequential organ failure assessment scores were evaluated daily within 2 weeks of admission to determine the temporal trajectory of OD using group-based multitrajectory modeling (GBMTM). RESULTS A total of 392 patients were enrolled with a 28-day mortality rate of 53.6%. GBMTM identified four distinct trajectories. Group 1 (mild OD, n = 64), with a median APACHE II score of 13 (IQR 9-21), had an early resolution of OD and a low mortality rate. Group 2 (moderate OD, n = 140), with a median APACHE II score of 18 (IQR 13-22), had a 28-day mortality rate of 30.0%. Group 3 (severe OD, n = 117), with a median APACHR II score of 20 (IQR 13-27), had a deterioration trend of respiratory dysfunction and a 28-day mortality rate of 69.2%. Group 4 (extremely severe OD, n = 71), with a median APACHE II score of 20 (IQR 17-27), had a significant and sustained OD affecting all organ systems and a 28-day mortality rate of 97.2%. CONCLUSIONS Four distinct trajectories of OD were identified, and respiratory dysfunction trajectory could predict nonpulmonary OD trajectories and patient prognosis.
Collapse
Affiliation(s)
- Jiafei Yu
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China; Department of Critical Care Medicine, Haiyan People's Hospital, Zhejiang 314300, China
| | - Kai Zhang
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China
| | - Tianqi Chen
- Department of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310016, China
| | - Ronghai Lin
- Department of Critical Care Medicine, Taizhou Municipal Hospital, Zhejiang, 318000, China
| | - Qijiang Chen
- Intensive Care Unit, Ninghai First Hospital, Zhejiang, 315600, China
| | - Chensong Chen
- Intensive Care Unit, Xiangshan First People's Hospital Medical and Health Group, Zhejiang, 315700, China
| | - Minfeng Tong
- Department of Neurosurgery, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Zhejiang, 321000, China
| | - Jianping Chen
- Department of Emergency Medicine, Dongyang People' Hospital of Wenzhou Medical University, Zhejiang, 322100, China
| | - Jianhua Yu
- Department of Critical Care Medicine, Longquan People's Hospital, Zhejiang, 323700, China
| | - Yuhang Lou
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China
| | - Panpan Xu
- Department of Critical Care Medicine, Taizhou Municipal Hospital, Zhejiang, 318000, China
| | - Chao Zhong
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China; Intensive Care Unit, Ninghai First Hospital, Zhejiang, 315600, China
| | - Qianfeng Chen
- Intensive Care Unit, Xiangshan First People's Hospital Medical and Health Group, Zhejiang, 315700, China
| | - Kangwei Sun
- Department of Emergency Medicine, Dongyang People' Hospital of Wenzhou Medical University, Zhejiang, 322100, China
| | - Liyuan Liu
- Department of Critical Care Medicine, Longquan People's Hospital, Zhejiang, 323700, China
| | - Lanxin Cao
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China
| | - Cheng Zheng
- Department of Critical Care Medicine, Taizhou Municipal Hospital, Zhejiang, 318000, China
| | - Ping Wang
- Intensive Care Unit, Ninghai First Hospital, Zhejiang, 315600, China
| | - Qitao Chen
- Department of Neurosurgery, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Zhejiang, 321000, China
| | - Qianqian Yang
- Department of Neurosurgery, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Zhejiang, 321000, China
| | - Weiting Chen
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China; Department of Emergency and Intensive Care Unit, The First People's Hospital of Linhai, Taizhou, Zhejiang 317000, China
| | - Xiaofang Wang
- Department of Cardiovascular Surgery, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China
| | - Zuxi Yan
- Department of Critical Care Medicine, Haiyan People's Hospital, Zhejiang 314300, China
| | - Xuefeng Zhang
- Department of Critical Care Medicine, Second Affiliated Hospital, Jiaxing College School of Medicine, Jiaxing 314031, China
| | - Wei Cui
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China
| | - Lin Chen
- Department of Neurosurgery, Affiliated Jinhua Hospital, Zhejiang University School of Medicine, Zhejiang, 321000, China
| | - Zhongheng Zhang
- Department of Emergency Medicine, Sir Run Run Shaw Hospital, Zhejiang University School of Medicine, Hangzhou, 310016, China
| | - Gensheng Zhang
- Department of Critical Care Medicine, Second Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310009, China; Key Laboratory of Multiple Organ Failure (Zhejiang University), Ministry of Education, Hangzhou 310009, China.
| |
Collapse
|
3
|
Jensen TO, Murray TA, Grandits GA, Jain MK, Grund B, Shaw-Saliba K, Matthay MA, Abassi M, Ardelt M, Baker JV, Chen P, Dewar RL, Goodman AL, Hatlen TJ, Highbarger HC, Holodniy M, Lallemand P, Laverdure S, Leshnower BG, Looney D, Moschopoulos CD, Mugerwa H, Murray DD, Mylonakis E, Nagy-Agren S, Rehman MT, Rupert A, Stevens R, Turville S, Weintrob A, Wick K, Lundgren J, Ko ER. Early trajectories of virological and immunological biomarkers and clinical outcomes in patients admitted to hospital for COVID-19: an international, prospective cohort study. THE LANCET. MICROBE 2024; 5:e559-e569. [PMID: 38815595 PMCID: PMC11181148 DOI: 10.1016/s2666-5247(24)00015-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/24/2023] [Revised: 01/08/2024] [Accepted: 01/11/2024] [Indexed: 06/01/2024]
Abstract
BACKGROUND Serial measurement of virological and immunological biomarkers in patients admitted to hospital with COVID-19 can give valuable insight into the pathogenic roles of viral replication and immune dysregulation. We aimed to characterise biomarker trajectories and their associations with clinical outcomes. METHODS In this international, prospective cohort study, patients admitted to hospital with COVID-19 and enrolled in the Therapeutics for Inpatients with COVID-19 platform trial within the Accelerating COVID-19 Therapeutic Interventions and Vaccines programme between Aug 5, 2020 and Sept 30, 2021 were included. Participants were included from 108 sites in Denmark, Greece, Poland, Singapore, Spain, Switzerland, Uganda, the UK, and the USA, and randomised to placebo or one of four neutralising monoclonal antibodies: bamlanivimab (Aug 5 to Oct 13, 2020), sotrovimab (Dec 16, 2020, to March 1, 2021), amubarvimab-romlusevimab (Dec 16, 2020, to March 1, 2021), and tixagevimab-cilgavimab (Feb 10 to Sept 30, 2021). This trial included an analysis of 2149 participants with plasma nucleocapsid antigen, anti-nucleocapsid antibody, C-reactive protein (CRP), IL-6, and D-dimer measured at baseline and day 1, day 3, and day 5 of enrolment. Day-90 follow-up status was available for 1790 participants. Biomarker trajectories were evaluated for associations with baseline characteristics, a 7-day pulmonary ordinal outcome, 90-day mortality, and 90-day rate of sustained recovery. FINDINGS The study included 2149 participants. Participant median age was 57 years (IQR 46-68), 1246 (58·0%) of 2149 participants were male and 903 (42·0%) were female; 1792 (83·4%) had at least one comorbidity, and 1764 (82·1%) were unvaccinated. Mortality to day 90 was 172 (8·0%) of 2149 and 189 (8·8%) participants had sustained recovery. A pattern of less favourable trajectories of low anti-nucleocapsid antibody, high plasma nucleocapsid antigen, and high inflammatory markers over the first 5 days was observed for high-risk baseline clinical characteristics or factors related to SARS-CoV-2 infection. For example, participants with chronic kidney disease demonstrated plasma nucleocapsid antigen 424% higher (95% CI 319-559), CRP 174% higher (150-202), IL-6 173% higher (144-208), D-dimer 149% higher (134-165), and anti-nucleocapsid antibody 39% lower (60-18) to day 5 than those without chronic kidney disease. Participants in the highest quartile for plasma nucleocapsid antigen, CRP, and IL-6 at baseline and day 5 had worse clinical outcomes, including 90-day all-cause mortality (plasma nucleocapsid antigen hazard ratio (HR) 4·50 (95% CI 3·29-6·15), CRP HR 3·37 (2·30-4·94), and IL-6 HR 5·67 (4·12-7·80). This risk persisted for plasma nucleocapsid antigen and CRP after adjustment for baseline biomarker values and other baseline factors. INTERPRETATION Patients admitted to hospital with less favourable 5-day biomarker trajectories had worse prognosis, suggesting that persistent viral burden might drive inflammation in the pathogenesis of COVID-19, identifying patients that might benefit from escalation of antiviral or anti-inflammatory treatment. FUNDING US National Institutes of Health.
Collapse
Affiliation(s)
- Tomas O Jensen
- Centre of Excellence for Health, Immunity, and Infections, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark.
| | - Thomas A Murray
- Division of Biostatistics, University of Minnesota, Minneapolis, MN, USA
| | - Greg A Grandits
- Division of Biostatistics, University of Minnesota, Minneapolis, MN, USA
| | | | - Birgit Grund
- School of Statistics, University of Minnesota, Minneapolis, MN, USA
| | | | - Michael A Matthay
- Division of Pulmonary and Critical Care Medicine, University of California San Francisco, San Francisco, CA, USA
| | - Mahsa Abassi
- Division of Infectious Diseases and International Medicine, University of Minnesota, Minneapolis, MN, USA
| | - Magdalena Ardelt
- Division of Pulmonary and Critical Care Medicine, University of California San Francisco, San Francisco, CA, USA
| | - Jason V Baker
- Division of Infectious Diseases and International Medicine, University of Minnesota, Minneapolis, MN, USA; Division of Infectious Diseases, Hennepin Healthcare, Minneapolis, MN, USA
| | - Peter Chen
- Cedars-Sinai Medical Center, Los Angeles, CA, USA
| | - Robin L Dewar
- Frederick National Laboratory for Cancer Research, Frederick, MD, USA
| | - Anna L Goodman
- The Medical Research Council Clinical Trials Unit, University College London, London, UK; Department of Infectious Diseases, Guy's and St Thomas' National Health Service Foundation Trust, London, UK
| | - Timothy J Hatlen
- Lundquist Institute at Harbor-UCLA Medical Center, Torrance, CA, USA
| | | | - Mark Holodniy
- VA Palo Alto Health Care System, Palo Alto, CA, USA; Department of Medicine, Infectious Diseases, Stanford University, Stanford, CA, USA
| | - Perrine Lallemand
- Frederick National Laboratory for Cancer Research, Frederick, MD, USA
| | - Sylvain Laverdure
- Laboratory of Human Retrovirology and Immunoinformatics, Frederick National Laboratory for Cancer Research, Frederick, MD, USA
| | | | - David Looney
- VA San Diego Healthcare Center, San Diego, CA, USA; Division of Infectious Diseases and Global Public Health, University of California San Diego, San Diego, CA, USA
| | | | | | - Daniel D Murray
- Centre of Excellence for Health, Immunity, and Infections, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Eleftherios Mylonakis
- Department of Medicine, Houston Methodist Hospital, Houston, TX, USA; Infectious Diseases Division, Brown University, Providence, RI, USA
| | - Stephanie Nagy-Agren
- Salem Veterans Affairs Medical Center, Salem, VA, USA; Department of Internal Medicine, Virginia Tech Carilion School of Medicine, Roanoke, VA, USA
| | - M Tauseef Rehman
- Frederick National Laboratory for Cancer Research, Frederick, MD, USA
| | - Adam Rupert
- Frederick National Laboratory for Cancer Research, Frederick, MD, USA
| | - Randy Stevens
- Frederick National Laboratory for Cancer Research, Frederick, MD, USA
| | | | - Amy Weintrob
- Washington DC Veterans Affairs Medical Center, Washington, DC, USA
| | - Katherine Wick
- Department of Internal Medicine, University of California Davis, Davis, CA, USA
| | - Jens Lundgren
- Centre of Excellence for Health, Immunity, and Infections, Rigshospitalet, University of Copenhagen, Copenhagen, Denmark
| | - Emily R Ko
- Division of General Internal Medicine, Department of Medicine, Duke University School of Medicine, Durham, NC, USA
| |
Collapse
|
4
|
Dubowski K, Braganza GT, Bozack A, Colicino E, DeFelice N, McGuinn L, Maru D, Lee AG. COVID-19 subphenotypes at hospital admission are associated with mortality: a cross-sectional study. Ann Med 2023; 55:12-23. [PMID: 36444856 PMCID: PMC10795648 DOI: 10.1080/07853890.2022.2148733] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/13/2022] [Accepted: 11/13/2022] [Indexed: 11/30/2022] Open
Abstract
BACKGROUND We have an incomplete understanding of COVID-19 characteristics at hospital presentation and whether underlying subphenotypes are associated with clinical outcomes and therapeutic responses. METHODS For this cross-sectional study, we extracted electronic health data from adults hospitalized between 1 March and 30 August 2020 with a PCR-confirmed diagnosis of COVID-19 at five New York City Hospitals. We obtained clinical and laboratory data from the first 24 h of the patient's hospitalization. Treatment with tocilizumab and convalescent plasma was assessed over hospitalization. The primary outcome was mortality; secondary outcomes included intubation, intensive care unit (ICU) admission and length of stay (LOS). First, we employed latent class analysis (LCA) to identify COVID-19 subphenotypes on admission without consideration of outcomes and assigned each patient to a subphenotype. We then performed robust Poisson regression to examine associations between COVID-19 subphenotype assignment and outcome. We explored whether the COVID-19 subphenotypes had a differential response to tocilizumab and convalescent plasma therapies. RESULTS A total of 4620 patients were included. LCA identified six subphenotypes, which were distinct by level of inflammation, clinical and laboratory derangements and ranged from a hypoinflammatory subphenotype with the fewest derangements to a hyperinflammatory with multiorgan dysfunction subphenotypes. Multivariable regression analyses found differences in risk for mortality, intubation, ICU admission and LOS, as compared to the hypoinflammatory subphenotype. For example, in multivariable analyses the moderate inflammation with fever subphenotype had 3.29 times the risk of mortality (95% CI 2.05, 5.28), while the hyperinflammatory with multiorgan failure subphenotype had 17.87 times the risk of mortality (95% CI 11.56, 27.63), as compared to the hypoinflammatory subphenotype. Exploratory analyses suggested that subphenotypes may differential respond to convalescent plasma or tocilizumab therapy. CONCLUSION COVID-19 subphenotype at hospital admission may predict risk for mortality, ICU admission and intubation and differential response to treatment.KEY MESSAGEThis cross-sectional study of COVID patients admitted to the Mount Sinai Health System, identified six distinct COVID subphenotypes on admission. Subphenotypes correlated with ICU admission, intubation, mortality and differential response to treatment.
Collapse
Affiliation(s)
- Kathryn Dubowski
- Division of Pulmonary, Critical Care and Sleep Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Giovanna T. Braganza
- School of Public Health, State University of New York, Downstate Health Sciences University, Brooklyn, NY, USA
| | - Anne Bozack
- School of Public Health, Environmental Health Sciences, University of California Berkeley, Berkeley, CA, USA
| | - Elena Colicino
- Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Nicholas DeFelice
- Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Laura McGuinn
- Environmental Medicine and Public Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Duncan Maru
- Department of Global Health, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| | - Alison G. Lee
- Division of Pulmonary, Critical Care and Sleep Medicine, Icahn School of Medicine at Mount Sinai, New York, NY, USA
| |
Collapse
|
5
|
Papathanakos G, Andrianopoulos I, Xenikakis M, Papathanasiou A, Koulenti D, Blot S, Koulouras V. Clinical Sepsis Phenotypes in Critically Ill Patients. Microorganisms 2023; 11:2165. [PMID: 37764009 PMCID: PMC10538192 DOI: 10.3390/microorganisms11092165] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/30/2023] [Revised: 08/10/2023] [Accepted: 08/24/2023] [Indexed: 09/29/2023] Open
Abstract
Sepsis, defined as the life-threatening dysregulated host response to an infection leading to organ dysfunction, is considered as one of the leading causes of mortality worldwide, especially in intensive care units (ICU). Moreover, sepsis remains an enigmatic clinical syndrome, with complex pathophysiology incompletely understood and a great heterogeneity both in terms of clinical expression, patient response to currently available therapeutic interventions and outcomes. This heterogeneity proves to be a major obstacle in our quest to deliver improved treatment in septic critical care patients; thus, identification of clinical phenotypes is absolutely necessary. Although this might be seen as an extremely difficult task, nowadays, artificial intelligence and machine learning techniques can be recruited to quantify similarities between individuals within sepsis population and differentiate them into distinct phenotypes regarding not only temperature, hemodynamics or type of organ dysfunction, but also fluid status/responsiveness, trajectories in ICU and outcome. Hopefully, we will eventually manage to determine both the subgroup of septic patients that will benefit from a therapeutic intervention and the correct timing of applying the intervention during the disease process.
Collapse
Affiliation(s)
- Georgios Papathanakos
- Department of Intensive Care Medicine, University Hospital of Ioannina, 45500 Ioannina, Greece; (I.A.); (M.X.); (A.P.); (V.K.)
| | - Ioannis Andrianopoulos
- Department of Intensive Care Medicine, University Hospital of Ioannina, 45500 Ioannina, Greece; (I.A.); (M.X.); (A.P.); (V.K.)
| | - Menelaos Xenikakis
- Department of Intensive Care Medicine, University Hospital of Ioannina, 45500 Ioannina, Greece; (I.A.); (M.X.); (A.P.); (V.K.)
| | - Athanasios Papathanasiou
- Department of Intensive Care Medicine, University Hospital of Ioannina, 45500 Ioannina, Greece; (I.A.); (M.X.); (A.P.); (V.K.)
| | - Despoina Koulenti
- UQ Centre for Clinical Research, Faculty of Medicine, The University of Queensland, Brisbane, QL 4029, Australia;
- Second Critical Care Department, Attikon University Hospital, Rimini Street, 12462 Athens, Greece
| | - Stijn Blot
- Department of Internal Medicine & Pediatrics, Ghent University, 9000 Ghent, Belgium;
| | - Vasilios Koulouras
- Department of Intensive Care Medicine, University Hospital of Ioannina, 45500 Ioannina, Greece; (I.A.); (M.X.); (A.P.); (V.K.)
| |
Collapse
|
6
|
Bhavani SV, Xiong L, Pius A, Semler M, Qian ET, Verhoef PA, Robichaux C, Coopersmith CM, Churpek MM. Comparison of time series clustering methods for identifying novel subphenotypes of patients with infection. J Am Med Inform Assoc 2023; 30:1158-1166. [PMID: 37043759 PMCID: PMC10198539 DOI: 10.1093/jamia/ocad063] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/09/2023] [Revised: 03/06/2023] [Accepted: 03/28/2023] [Indexed: 04/14/2023] Open
Abstract
OBJECTIVE Severe infection can lead to organ dysfunction and sepsis. Identifying subphenotypes of infected patients is essential for personalized management. It is unknown how different time series clustering algorithms compare in identifying these subphenotypes. MATERIALS AND METHODS Patients with suspected infection admitted between 2014 and 2019 to 4 hospitals in Emory healthcare were included, split into separate training and validation cohorts. Dynamic time warping (DTW) was applied to vital signs from the first 8 h of hospitalization, and hierarchical clustering (DTW-HC) and partition around medoids (DTW-PAM) were used to cluster patients into subphenotypes. DTW-HC, DTW-PAM, and a previously published group-based trajectory model (GBTM) were evaluated for agreement in subphenotype clusters, trajectory patterns, and subphenotype associations with clinical outcomes and treatment responses. RESULTS There were 12 473 patients in training and 8256 patients in validation cohorts. DTW-HC, DTW-PAM, and GBTM models resulted in 4 consistent vitals trajectory patterns with significant agreement in clustering (71-80% agreement, P < .001): group A was hyperthermic, tachycardic, tachypneic, and hypotensive. Group B was hyperthermic, tachycardic, tachypneic, and hypertensive. Groups C and D had lower temperatures, heart rates, and respiratory rates, with group C normotensive and group D hypotensive. Group A had higher odds ratio of 30-day inpatient mortality (P < .01) and group D had significant mortality benefit from balanced crystalloids compared to saline (P < .01) in all 3 models. DISCUSSION DTW- and GBTM-based clustering algorithms applied to vital signs in infected patients identified consistent subphenotypes with distinct clinical outcomes and treatment responses. CONCLUSION Time series clustering with distinct computational approaches demonstrate similar performance and significant agreement in the resulting subphenotypes.
Collapse
Affiliation(s)
- Sivasubramanium V Bhavani
- Department of Medicine, Emory University, Atlanta, Georgia, USA
- Emory Critical Care Center, Atlanta, Georgia, USA
| | - Li Xiong
- Department of Computer Science, Emory University, Atlanta, Georgia, USA
| | - Abish Pius
- Department of Computational & Systems Biology, University of Pittsburgh School of Medicine, Pittsburgh, Pennsylvania, USA
| | - Matthew Semler
- Department of Medicine, Vanderbilt University, Nashville, Tennessee, USA
| | - Edward T Qian
- Department of Medicine, Vanderbilt University, Nashville, Tennessee, USA
| | - Philip A Verhoef
- Department of Medicine, University of Hawaii John A. Burns School of Medicine, Honolulu, Hawaii, USA
- Hawaii Permanente Medical Group, Honolulu, Hawaii, USA
| | - Chad Robichaux
- Department of Biomedical Informatics, Emory University, Atlanta, Georgia, USA
| | - Craig M Coopersmith
- Emory Critical Care Center, Atlanta, Georgia, USA
- Department of Surgery, Emory University, Atlanta, Georgia, USA
| | - Matthew M Churpek
- Department of Medicine, University of Wisconsin, Madison, Wisconsin, USA
- Department of Biostatistics and Medical Informatics, University of Wisconsin, Madison, Wisconsin, USA
| |
Collapse
|
7
|
A two-gene marker for the two-tiered innate immune response in COVID-19 patients. PLoS One 2023; 18:e0280392. [PMID: 36649304 PMCID: PMC9844909 DOI: 10.1371/journal.pone.0280392] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/30/2022] [Accepted: 12/28/2022] [Indexed: 01/18/2023] Open
Abstract
For coronavirus disease 2019 (COVID-19), a pandemic disease characterized by strong immune dysregulation in severe patients, convenient and efficient monitoring of the host immune response is critical. Human hosts respond to viral and bacterial infections in different ways, the former is characterized by the activation of interferon stimulated genes (ISGs) such as IFI27, while the latter is characterized by the activation of anti-bacterial associated genes (ABGs) such as S100A12. This two-tiered innate immune response has not been examined in COVID-19. In this study, the activation patterns of this two-tiered innate immune response represented by IFI27 and S100A12 were explored based on 1421 samples from 17 transcriptome datasets derived from the blood of COVID-19 patients and relevant controls. It was found that IFI27 activation occurred in most of the symptomatic patients and displayed no correlation with disease severity, while S100A12 activation was more restricted to patients under severe and critical conditions with a stepwise activation pattern. In addition, most of the S100A12 activation was accompanied by IFI27 activation. Furthermore, the activation of IFI27 was most pronounced within the first week of symptom onset, but generally waned after 2-3 weeks. On the other hand, the activation of S100A12 displayed no apparent correlation with disease duration and could last for several months in certain patients. These features of the two-tiered innate immune response can further our understanding on the disease mechanism of COVID-19 and may have implications to the clinical triage. Development of a convenient two-gene protocol for the routine serial monitoring of this two-tiered immune response will be a valuable addition to the existing laboratory tests.
Collapse
|
8
|
An interpretable machine learning prognostic system for risk stratification in oropharyngeal cancer. Int J Med Inform 2022; 168:104896. [DOI: 10.1016/j.ijmedinf.2022.104896] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/25/2022] [Revised: 09/27/2022] [Accepted: 10/07/2022] [Indexed: 11/07/2022]
|
9
|
Sprockel Díaz JJ, Torres Tobar LA, Rodríguez Acosta MJ. Aplicación de la calculadora de probabilidad fenotípica FEN-COVID en pacientes hospitalizados por COVID-19 en una población latinoamericana. REPERTORIO DE MEDICINA Y CIRUGÍA 2022. [DOI: 10.31260/repertmedcir.01217372.1363] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/17/2022] Open
Abstract
Introducción: la variabilidad del comportamiento clínico del COVID-19 puede ser uno de los determinantes que limitan la toma de decisiones terapéuticas. Se busca clasificar a pacientes latinoamericanos hospitalizados mediante la herramienta FEN-COVID para la identificación de fenotipos clínicos y determinar su asociación con mortalidad e ingreso a la unidad de cuidado intensivo (UCI). Métodos: estudio observacional de cohorte retrospectivo, que incluyó adultos hospitalizados en dos centros de tercer nivel de atención con COVID-19 confirmado entre septiembre 2020 y marzo 2021. A cada paciente seleccionado se asignó un fenotipo aplicando la calculadora FEN-COVID. Se llevó a cabo un análisis multivariado para documentar las asociaciones entre el fenotipo, las complicaciones hospitalarias y los desenlaces clínicos. Resultados: se identificaron 126 pacientes hospitalizados por COVID-19, edad promedio de 58 años, 45 mujeres (35.7%), 23% diabéticos, 45% hipertensos y 20% obesos. 108 (85.7%) fueron del fenotipo B y 18 (14.2%) fenotipo C. Aunque en este último los desenlaces fueron peores (requerimiento de UCI 77.8% vs 45.4% y mortalidad 66% vs 22%, OR 1.408, IC95% 3.191-5.243, p <0.007), esta asociación no se mantuvo en el análisis multivariado con OR 1.110 (IC95% 0.780 - 1.581, p de 0.555) Conclusión: los fenotipos identificados a partir de FEN-COVID parecen discriminar un subgrupo de pacientes que ostenta el peor comportamiento clínico, aunque no tuvo representación del fenotipo más leve. El análisis bivariado documentó asociación con la muerte o ingreso a UCI que no se mantuvo en el modelo multivariado.
Collapse
|
10
|
Abstract
Acute respiratory distress syndrome (ARDS) is a heterogeneous syndrome arising from multiple causes with a range of clinical severity. In recent years, the potential for prognostic and predictive enrichment of clinical trials has been increased with identification of more biologically homogeneous subgroups or phenotypes within ARDS. COVID-19 ARDS also exhibits significant clinical heterogeneity despite a single causative agent. In this review the authors summarize the existing literature on COVID-19 ARDS phenotypes, including physiologic, clinical, and biological subgroups as well as the implications for improving both prognostication and precision therapy.
Collapse
Affiliation(s)
- Susannah Empson
- Department of Anesthesiology, Perioperative, and Pain Medicine, 300 Pasteur Drive, H3580, Stanford, CA 94305, USA.
| | - Angela J Rogers
- Department of Pulmonary, Allergy & Critical Care Medicine, 300 Pasteur Drive, H3153, Stanford, CA 94305, USA
| | - Jennifer G Wilson
- Department of Emergency Medicine, 900 Welch Road, Suite 350, Stanford, CA 94305, USA
| |
Collapse
|
11
|
San-Cristobal R, Martín-Hernández R, Ramos-Lopez O, Martinez-Urbistondo D, Micó V, Colmenarejo G, Villares Fernandez P, Daimiel L, Martínez JA. Longwise Cluster Analysis for the Prediction of COVID-19 Severity within 72 h of Admission: COVID-DATA-SAVE-LIFES Cohort. J Clin Med 2022; 11:jcm11123327. [PMID: 35743398 PMCID: PMC9224935 DOI: 10.3390/jcm11123327] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/05/2022] [Revised: 06/02/2022] [Accepted: 06/07/2022] [Indexed: 01/27/2023] Open
Abstract
The use of routine laboratory biomarkers plays a key role in decision making in the clinical practice of COVID-19, allowing the development of clinical screening tools for personalized treatments. This study performed a short-term longitudinal cluster from patients with COVID-19 based on biochemical measurements for the first 72 h after hospitalization. Clinical and biochemical variables from 1039 confirmed COVID-19 patients framed on the “COVID Data Save Lives” were grouped in 24-h blocks to perform a longitudinal k-means clustering algorithm to the trajectories. The final solution of the three clusters showed a strong association with different clinical severity outcomes (OR for death: Cluster A reference, Cluster B 12.83 CI: 6.11−30.54, and Cluster C 14.29 CI: 6.66−34.43; OR for ventilation: Cluster-B 2.22 CI: 1.64−3.01, and Cluster-C 1.71 CI: 1.08−2.76), improving the AUC of the models in terms of age, sex, oxygen concentration, and the Charlson Comorbidities Index (0.810 vs. 0.871 with p < 0.001 and 0.749 vs. 0.807 with p < 0.001, respectively). Patient diagnoses and prognoses remarkably diverged between the three clusters obtained, evidencing that data-driven technologies devised for the screening, analysis, prediction, and tracking of patients play a key role in the application of individualized management of the COVID-19 pandemics.
Collapse
Affiliation(s)
- Rodrigo San-Cristobal
- Precision Nutrition and Cardiometabolic Health Researh Program, Institute on Food and Health Sciences (Institute IMDEA Food), 28049 Madrid, Spain; (V.M.); (J.A.M.)
- Correspondence:
| | - Roberto Martín-Hernández
- Biostatistics & Bioinformatics Unit, Madrid Institute for Advanced Studies (IMDEA) Food, CEI UAM + CSIS, 28049 Madrid, Spain; (R.M.-H.); (G.C.)
| | - Omar Ramos-Lopez
- Medicine and Psychology School, Autonomous University of Baja California, Tijuana 22390, Baja California, Mexico;
| | - Diego Martinez-Urbistondo
- Internal Medicine Department, Hospital Universitario HM Sanchinarro, 28050 Madrid, Spain; (D.M.-U.); (P.V.F.)
| | - Víctor Micó
- Precision Nutrition and Cardiometabolic Health Researh Program, Institute on Food and Health Sciences (Institute IMDEA Food), 28049 Madrid, Spain; (V.M.); (J.A.M.)
| | - Gonzalo Colmenarejo
- Biostatistics & Bioinformatics Unit, Madrid Institute for Advanced Studies (IMDEA) Food, CEI UAM + CSIS, 28049 Madrid, Spain; (R.M.-H.); (G.C.)
| | - Paula Villares Fernandez
- Internal Medicine Department, Hospital Universitario HM Sanchinarro, 28050 Madrid, Spain; (D.M.-U.); (P.V.F.)
| | - Lidia Daimiel
- Nutritional Control of the Epigenome Group, IMDEA Food Institute, CEI UAM + CSIC, 28049 Madrid, Spain;
| | - Jose Alfredo Martínez
- Precision Nutrition and Cardiometabolic Health Researh Program, Institute on Food and Health Sciences (Institute IMDEA Food), 28049 Madrid, Spain; (V.M.); (J.A.M.)
- CIBERobn Physiopathology of Obesity and Nutrition, Institute of Health Carlos III (ISCIII), 28029 Madrid, Spain
| |
Collapse
|
12
|
Zhang K, Karanth S, Patel B, Murphy R, Jiang X. A multi-task Gaussian process self-attention neural network for real-time prediction of the need for mechanical ventilators in COVID-19 patients. J Biomed Inform 2022; 130:104079. [PMID: 35489596 PMCID: PMC9044651 DOI: 10.1016/j.jbi.2022.104079] [Citation(s) in RCA: 4] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/21/2021] [Revised: 04/06/2022] [Accepted: 04/18/2022] [Indexed: 02/04/2023]
Abstract
OBJECTIVE The Coronavirus Disease 2019 (COVID-19) pandemic has overwhelmed the capacity of healthcare resources and posed a challenge for worldwide hospitals. The ability to distinguish potentially deteriorating patients from the rest helps facilitate reasonable allocation of medical resources, such as ventilators, hospital beds, and human resources. The real-time accurate prediction of a patient's risk scores could also help physicians to provide earlier respiratory support for the patient and reduce the risk of mortality. METHODS We propose a robust real-time prediction model for the in-hospital COVID-19 patients' probability of requiring mechanical ventilation (MV). The end-to-end neural network model incorporates the Multi-task Gaussian Process to handle the irregular sampling rate in observational data together with a self-attention neural network for the prediction task. RESULTS We evaluate our model on a large database with 9,532 nationwide in-hospital patients with COVID-19. The model demonstrates significant robustness and consistency improvements compared to conventional machine learning models. The proposed prediction model also shows performance improvements in terms of area under the receiver operating characteristic curve (AUROC) and area under the precision-recall curve (AUPRC) compared to various deep learning models, especially at early times after a patient's hospital admission. CONCLUSION The availability of large and real-time clinical data calls for new methods to make the best use of them for real-time patient risk prediction. It is not ideal for simplifying the data for traditional methods or for making unrealistic assumptions that deviate from observation's true dynamics. We demonstrate a pilot effort to harmonize cross-sectional and longitudinal information for mechanical ventilation needing prediction.
Collapse
Affiliation(s)
- Kai Zhang
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX 77030, USA.
| | - Siddharth Karanth
- Department of Internal Medicine, McGovern Medical School of The University of Texas Health Science Center at Houston, Houston, TX 77030, USA
| | - Bela Patel
- Department of Internal Medicine, McGovern Medical School of The University of Texas Health Science Center at Houston, Houston, TX 77030, USA
| | - Robert Murphy
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX 77030, USA
| | - Xiaoqian Jiang
- School of Biomedical Informatics, University of Texas Health Science Center at Houston, Houston, TX 77030, USA
| |
Collapse
|
13
|
Outcomes of Cancer Patients with COVID-19 in a Hospital System in the Chicago Metropolitan Area. Cancers (Basel) 2022; 14:cancers14092209. [PMID: 35565336 PMCID: PMC9105648 DOI: 10.3390/cancers14092209] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/08/2022] [Revised: 04/09/2022] [Accepted: 04/19/2022] [Indexed: 01/27/2023] Open
Abstract
Patients with a history of malignancy have been shown to be at an increased risk of COVID-19-related morbidity and mortality. Poorer clinical outcomes in that patient population are likely due to the underlying systemic illness, comorbidities, and the cytotoxic and immunosuppressive anti-tumor treatments they are subjected to. We identified 416 cancer patients with SARS-CoV-2 infection being managed for their malignancy at Northwestern Medicine in Chicago, Illinois, between March and July of 2020. Seventy-five (18.0%) patients died due to COVID-related complications. Older age (>60), male gender, and current treatment with immunotherapy were associated with shorter overall survival. Laboratory findings showed that higher platelet counts, ALC, and hemoglobin were protective against critical illness and death from COVID-19. Conversely, elevated inflammatory markers such as ferritin, d-dimer, procalcitonin, CRP, and LDH led to worse clinical outcomes. Our findings suggest that a thorough clinical and laboratory assessment of infected patients with cancer might help identify a more vulnerable population and implement more aggressive proactive strategies.
Collapse
|
14
|
Xu Z, Su C, Xiao Y, Wang F. Artificial intelligence for COVID-19: battling the pandemic with computational intelligence. INTELLIGENT MEDICINE 2022; 2:13-29. [PMID: 34697578 PMCID: PMC8529224 DOI: 10.1016/j.imed.2021.09.001] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 07/20/2021] [Revised: 09/15/2021] [Accepted: 09/29/2021] [Indexed: 12/15/2022]
Abstract
The new coronavirus disease 2019 (COVID-19) has become a global pandemic leading to over 180 million confirmed cases and nearly 4 million deaths until June 2021, according to the World Health Organization. Since the initial report in December 2019 , COVID-19 has demonstrated a high transmission rate (with an R0 > 2), a diverse set of clinical characteristics (e.g., high rate of hospital and intensive care unit admission rates, multi-organ dysfunction for critically ill patients due to hyperinflammation, thrombosis, etc.), and a tremendous burden on health care systems around the world. To understand the serious and complex diseases and develop effective control, treatment, and prevention strategies, researchers from different disciplines have been making significant efforts from different aspects including epidemiology and public health, biology and genomic medicine, as well as clinical care and patient management. In recent years, artificial intelligence (AI) has been introduced into the healthcare field to aid clinical decision-making for disease diagnosis and treatment such as detecting cancer based on medical images, and has achieved superior performance in multiple data-rich application scenarios. In the COVID-19 pandemic, AI techniques have also been used as a powerful tool to overcome the complex diseases. In this context, the goal of this study is to review existing studies on applications of AI techniques in combating the COVID-19 pandemic. Specifically, these efforts can be grouped into the fields of epidemiology, therapeutics, clinical research, social and behavioral studies and are summarized. Potential challenges, directions, and open questions are discussed accordingly, which may provide new insights into addressing the COVID-19 pandemic and would be helpful for researchers to explore more related topics in the post-pandemic era.
Collapse
Affiliation(s)
- Zhenxing Xu
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York 10065, United States
| | - Chang Su
- Department of Health Service Administration and Policy, Temple University, Philadelphia 19122, United States
| | - Yunyu Xiao
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York 10065, United States
| | - Fei Wang
- Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York 10065, United States,Corresponding author: Fei Wang, Department of Population Health Sciences, Weill Cornell Medicine, Cornell University, New York 10065, United States of America
| |
Collapse
|
15
|
Suhre K, Sarwath H, Engelke R, Sohail MU, Cho SJ, Whalen W, Alvarez-Mulett S, Krumsiek J, Choi AMK, Schmidt F. Identification of Robust Protein Associations With COVID-19 Disease Based on Five Clinical Studies. Front Immunol 2022; 12:781100. [PMID: 35145507 PMCID: PMC8821526 DOI: 10.3389/fimmu.2021.781100] [Citation(s) in RCA: 16] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2021] [Accepted: 12/27/2021] [Indexed: 01/08/2023] Open
Abstract
Multiple studies have investigated the role of blood circulating proteins in COVID-19 disease using the Olink affinity proteomics platform. However, study inclusion criteria and sample collection conditions varied between studies, leading to sometimes incongruent associations. To identify the most robust protein markers of the disease and the underlying pathways that are relevant under all conditions, it is essential to identify proteins that replicate most widely. Here we combined the Olink proteomics profiles of two newly recruited COVID-19 studies (N=68 and N=98) with those of three previously published COVID-19 studies (N=383, N=83, N=57). For these studies, three Olink panels (Inflammation and Cardiovascular II & III) with 253 unique proteins were compared. Case/control analysis revealed thirteen proteins (CCL16, CCL7, CXCL10, CCL8, LGALS9, CXCL11, IL1RN, CCL2, CD274, IL6, IL18, MERTK, IFNγ, and IL18R1) that were differentially expressed in COVID-19 patients in all five studies. Except CCL16, which was higher in controls, all proteins were overexpressed in COVID-19 patients. Pathway analysis revealed concordant trends across all studies with pathways related to cytokine-cytokine interaction, IL18 signaling, fluid shear stress and rheumatoid arthritis. Our results reaffirm previous findings related to a COVID-19 cytokine storm syndrome. Cross-study robustness of COVID-19 specific protein expression profiles support the utility of affinity proteomics as a tool and for the identification of potential therapeutic targets.
Collapse
Affiliation(s)
- Karsten Suhre
- Bioinformatics Core, Weill Cornell Medicine-Qatar, Doha, Qatar
- Department of Physiology and Biophysics, Weill Cornell Medicine, New York, NY, United States
| | - Hina Sarwath
- Proteomics Core, Weill Cornell Medicine-Qatar, Doha, Qatar
| | - Rudolf Engelke
- Proteomics Core, Weill Cornell Medicine-Qatar, Doha, Qatar
| | | | - Soo Jung Cho
- Department of Medicine, Division of Pulmonary and Critical Care Medicine, New York-Presbyterian Hospital-Weill Cornell Medical Center, Weill Cornell Medicine, New York, NY, United States
| | - William Whalen
- Department of Medicine, Division of Pulmonary and Critical Care Medicine, New York-Presbyterian Hospital-Weill Cornell Medical Center, Weill Cornell Medicine, New York, NY, United States
| | - Sergio Alvarez-Mulett
- Department of Medicine, Division of Pulmonary and Critical Care Medicine, New York-Presbyterian Hospital-Weill Cornell Medical Center, Weill Cornell Medicine, New York, NY, United States
| | - Jan Krumsiek
- Department of Physiology and Biophysics, Weill Cornell Medicine, New York, NY, United States
- Englander Institute for Precision Medicine, Weill Cornell Medicine, New York, NY, United States
| | - Augustine M K Choi
- Department of Medicine, Division of Pulmonary and Critical Care Medicine, New York-Presbyterian Hospital-Weill Cornell Medical Center, Weill Cornell Medicine, New York, NY, United States
| | - Frank Schmidt
- Proteomics Core, Weill Cornell Medicine-Qatar, Doha, Qatar
| |
Collapse
|
16
|
Stratifying individuals into non-alcoholic fatty liver disease risk levels using time series machine learning models. J Biomed Inform 2022; 126:103986. [PMID: 35007752 DOI: 10.1016/j.jbi.2022.103986] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/31/2021] [Revised: 12/01/2021] [Accepted: 01/03/2022] [Indexed: 02/07/2023]
Abstract
Non-alcoholic fatty liver disease (NAFLD) affects 25% of the population worldwide, and its prevalence is anticipated to increase globally. While most NAFLD patients are asymptomatic, NAFLD may progress to fibrosis, cirrhosis, cardiovascular disease, and diabetes. Research reports, with daunting results, show the challenge that NAFLD's burden causes to global population health. The current process for identifying fibrosis risk levels is inefficient, expensive, does not cover all potential populations, and does not identify the risk in time. Instead of invasive liver biopsies, we implemented a non-invasive fibrosis assessment process calculated from clinical data (accessed via EMRs/EHRs). We stratified patients' risks for fibrosis from 2007 to 2017 by modeling the risk in 5579 individuals. The process involved time-series machine learning models (Hidden Markov Models and Group-Based Trajectory Models) profiled fibrosis risk by modeling patients' latent medical status resulted in three groups. The high-risk group had abnormal lab test values and a higher prevalence of chronic conditions. This study can help overcome the inefficient, traditional process of detecting fibrosis via biopsies (that are also medically unfeasible due to their invasive nature, the medical resources involved, and costs) at early stages. Thus longitudinal risk assessment may be used to make population-specific medical recommendations targeting early detection of high risk patients, to avoid the development of fibrosis disease and its complications as well as decrease healthcare costs.
Collapse
|
17
|
Wang J, Li D, Cameron A, Zhou Q, Wiltse A, Nayak J, Pecora ND, Zand MS. OUP accepted manuscript. J Infect Dis 2022; 226:474-484. [PMID: 35091739 PMCID: PMC8807312 DOI: 10.1093/infdis/jiac022] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/20/2021] [Accepted: 01/24/2022] [Indexed: 11/12/2022] Open
Abstract
BACKGROUND A protective antibody response to severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) is crucial to decrease morbidity and mortality from severe coronavirus disease 2019 (COVID-19) disease. The effects of preexisting anti-human coronavirus (HCoV) antibodies on the SARS-CoV-2-specific immunoglobulin G (IgG) responses and severity of disease are currently unclear. METHODS We profiled anti-spike (S), S1, S2, and receptor-binding domain IgG antibodies against SARS-CoV-2 and 6 HCoVs using a multiplex assay (mPLEX-CoV) with serum samples from SARS-CoV-2 infected (n = 155) and pre-COVID-19 (n = 188) cohorts. RESULTS COVID-19 subjects showed significantly increased anti-S SARS-CoV-2 IgG levels that were highly correlated with IgG antibodies against OC43 and HKU1 S proteins. However, OC43 and HKU1 anti-S antibodies in pre-COVID-19 era sera did not cross-react with SARS-CoV-2. Unidirectional cross-reactive antibodies elicited by SARS-CoV-2 infection were distinct from the bidirectional cross-reactive antibodies recognizing homologous strains RaTG13 and SARS-CoV-1. High anti-OC43 and anti-S2 antibody levels were associated with both a rapid anti-SARS-CoV-2 antibody response and increased disease severity. Subjects with increased sequential organ failure assessment (SOFA) scores developed a higher ratio of S2- to S1-reactive antibodies. CONCLUSIONS Early and rapid emergence of OC43 S- and S2-reactive IgG after SARS-CoV-2 infection correlates with COVID-19 disease severity.
Collapse
Affiliation(s)
- Jiong Wang
- Department of Medicine, Division of Nephrology, University of Rochester, Rochester, New York, USA
| | - Dongmei Li
- Clinical and Translational Science Institute, University of Rochester, Rochester, New York, USA
| | - Andrew Cameron
- Clinical Microbiology, Department of Pathology and Laboratory Medicine, University of Rochester, Rochester, New York, USA
| | - Qian Zhou
- Department of Medicine, Division of Nephrology, University of Rochester, Rochester, New York, USA
| | - Alexander Wiltse
- Present affiliation: University of Maryland Medical Center, Baltimore, MD
| | - Jennifer Nayak
- Department of Pediatrics, Division of Infectious Diseases, University of Rochester, Rochester, New York, USA
| | - Nicole D Pecora
- Present affiliation: Brigham and Women’s Hospital, Harvard University, Boston, MA
| | - Martin S Zand
- Correspondence: Martin S. Zand, MD, PhD, University of Rochester Medical Center, Clinical and Translational Science Institute, Room 1.207, 265 Crittendon Boulevard, Rochester, NY 14642 ()
| |
Collapse
|
18
|
Sathe NA, Zelnick LR, Mikacenic C, Morrell ED, Bhatraju PK, McNeil JB, Kosamo S, Hough CL, Liles WC, Ware LB, Wurfel MM. Identification of persistent and resolving subphenotypes of acute hypoxemic respiratory failure in two independent cohorts. Crit Care 2021; 25:336. [PMID: 34526076 PMCID: PMC8442814 DOI: 10.1186/s13054-021-03755-7] [Citation(s) in RCA: 10] [Impact Index Per Article: 3.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/28/2021] [Accepted: 08/31/2021] [Indexed: 01/02/2023] Open
Abstract
BACKGROUND Acute hypoxemic respiratory failure (HRF) is associated with high morbidity and mortality, but its heterogeneity challenges the identification of effective therapies. Defining subphenotypes with distinct prognoses or biologic features can improve therapeutic trials, but prior work has focused on ARDS, which excludes many acute HRF patients. We aimed to characterize persistent and resolving subphenotypes in the broader HRF population. METHODS In this secondary analysis of 2 independent prospective ICU cohorts, we included adults with acute HRF, defined by invasive mechanical ventilation and PaO2-to-FIO2 ratio ≤ 300 on cohort enrollment (n = 768 in the discovery cohort and n = 1715 in the validation cohort). We classified patients as persistent HRF if still requiring mechanical ventilation with PaO2-to-FIO2 ratio ≤ 300 on day 3 following ICU admission, or resolving HRF if otherwise. We estimated relative risk of 28-day hospital mortality associated with persistent HRF, compared to resolving HRF, using generalized linear models. We also estimated fold difference in circulating biomarkers of inflammation and endothelial activation on cohort enrollment among persistent HRF compared to resolving HRF. Finally, we stratified our analyses by ARDS to understand whether this was driving differences between persistent and resolving HRF. RESULTS Over 50% developed persistent HRF in both the discovery (n = 386) and validation (n = 1032) cohorts. Persistent HRF was associated with higher risk of death relative to resolving HRF in both the discovery (1.68-fold, 95% CI 1.11, 2.54) and validation cohorts (1.93-fold, 95% CI 1.50, 2.47), after adjustment for age, sex, chronic respiratory illness, and acute illness severity on enrollment (APACHE-III in discovery, APACHE-II in validation). Patients with persistent HRF displayed higher biomarkers of inflammation (interleukin-6, interleukin-8) and endothelial dysfunction (angiopoietin-2) than resolving HRF after adjustment. Only half of persistent HRF patients had ARDS, yet exhibited higher mortality and biomarkers than resolving HRF regardless of whether they qualified for ARDS. CONCLUSION Patients with persistent HRF are common and have higher mortality and elevated circulating markers of lung injury compared to resolving HRF, and yet only a subset are captured by ARDS definitions. Persistent HRF may represent a clinically important, inclusive target for future therapeutic trials in HRF.
Collapse
Affiliation(s)
- Neha A Sathe
- Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, University of Washington, 325 9th Avenue, Box # 359640, Seattle, WA, 98104, USA.
| | - Leila R Zelnick
- Division of Nephrology, Department of Medicine, University of Washington, Seattle, WA, USA
| | - Carmen Mikacenic
- Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, University of Washington, 325 9th Avenue, Box # 359640, Seattle, WA, 98104, USA
- Benaroya Research Institute, Seattle, WA, USA
| | - Eric D Morrell
- Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, University of Washington, 325 9th Avenue, Box # 359640, Seattle, WA, 98104, USA
| | - Pavan K Bhatraju
- Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, University of Washington, 325 9th Avenue, Box # 359640, Seattle, WA, 98104, USA
- Sepsis Center of Research Excellence, University of Washington, Seattle, WA, USA
| | - J Brennan McNeil
- Division of Allergy, Pulmonary, and Critical Care Medicine, Department of Medicine, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Susanna Kosamo
- Department of Biochemistry and Molecular Medicine, University of Oulu, Oulu, Finland
| | - Catherine L Hough
- Division of Pulmonary and Critical Care, Department of Medicine, Oregon Health and Science University, Portland, OR, USA
| | - W Conrad Liles
- Sepsis Center of Research Excellence, University of Washington, Seattle, WA, USA
- Division of Allergy and Infectious Diseases, Department of Medicine, University of Washington, Seattle, WA, USA
| | - Lorraine B Ware
- Division of Allergy, Pulmonary, and Critical Care Medicine, Department of Medicine, Vanderbilt University School of Medicine, Nashville, TN, USA
- Department of Pathology, Microbiology and Immunology, Vanderbilt University School of Medicine, Nashville, TN, USA
| | - Mark M Wurfel
- Division of Pulmonary, Critical Care and Sleep Medicine, Department of Medicine, University of Washington, 325 9th Avenue, Box # 359640, Seattle, WA, 98104, USA
- Sepsis Center of Research Excellence, University of Washington, Seattle, WA, USA
| |
Collapse
|