scholarly journals Efficacy and Safety of Anticoagulation Treatment in COVID-19 Patient Subgroups Identified by Clinical-Based Stratification and Unsupervised Machine Learning: A Matched Cohort Study

2021 ◽  
Vol 8 ◽  
Author(s):  
Yi Bian ◽  
Yue Le ◽  
Han Du ◽  
Junfang Chen ◽  
Ping Zhang ◽  
...  
Keyword(s):  
Machine Learning ◽  
Multiple Organ ◽  
Hospital Death ◽  
Matched Cohort ◽  
Multiple Organ Dysfunction ◽  
Bleeding Events ◽  
Full Cohort ◽  
Unsupervised Machine Learning ◽  
Death Risk ◽  
Learning Analysis

Objective: To explore the efficacy of anticoagulation in improving outcomes and safety of Coronavirus disease 2019 (COVID-19) patients in subgroups identified by clinical-based stratification and unsupervised machine learning.Methods: This single-center retrospective cohort study unselectively reviewed 2,272 patients with COVID-19 admitted to the Tongji Hospital between Jan 25 and Mar 23, 2020. The association between AC treatment and outcomes was investigated in the propensity score (PS) matched cohort and the full cohort by inverse probability of treatment weighting (IPTW) analysis. Subgroup analysis, identified by clinical-based stratification or unsupervised machine learning, was used to identify sub-phenotypes with meaningful clinical features and the target patients benefiting most from AC.Results: AC treatment was associated with lower in-hospital death risk either in the PS matched cohort or by IPTW analysis in the full cohort. A higher incidence of clinically relevant non-major bleeding (CRNMB) was observed in the AC group, but not major bleeding. Clinical subgroup analysis showed that, at admission, severe cases of COVID-19 clinical classification, mild acute respiratory distress syndrome (ARDS) cases, and patients with a D-dimer level ≥0.5 μg/mL, may benefit from AC. During the hospital stay, critical cases and severe ARDS cases may benefit from AC. Unsupervised machine learning analysis established a four-class clustering model. Clusters 1 and 2 were non-critical cases and might not benefit from AC, while clusters 3 and 4 were critical patients. Patients in cluster 3 might benefit from AC with no increase in bleeding events. While patients in cluster 4, who were characterized by multiple organ dysfunction (neurologic, circulation, coagulation, kidney and liver dysfunction) and elevated inflammation biomarkers, did not benefit from AC.Conclusions: AC treatment was associated with lower in-hospital death risk, especially in critically ill COVID-19 patients. Unsupervised learning analysis revealed that the most critically ill patients with multiple organ dysfunction and excessive inflammation might not benefit from AC. More attention should be paid to bleeding events (especially CRNMB) when using AC.

Unsupervised Machine Learning Analysis of Urinary Transcriptome Reveals Distinct Genotypic Clustering in Surgical Sepsis

2017 ◽  
Vol 225 (4) ◽  
pp. S66-S67
Author(s):  
Nicholas Lysak ◽  
Ashkan Ebadi ◽  
Sabyasachi Bandyopadhyay ◽  
Tezcan Ozrazgat-Baslanti ◽  
Larysa Sautina ◽  
...  
Keyword(s):  
Machine Learning ◽  
Unsupervised Machine Learning ◽  
Learning Analysis

ICU staffing feature phenotypes and their relationship with patients’ outcomes: an unsupervised machine learning analysis

2019 ◽  
Vol 45 (11) ◽  
pp. 1599-1607 ◽  
Author(s):  
Fernando G. Zampieri ◽  
◽  
Jorge I. F. Salluh ◽  
Luciano C. P. Azevedo ◽  
Jeremy M. Kahn ◽  
...  
Keyword(s):  
Machine Learning ◽  
Unsupervised Machine Learning ◽  
Learning Analysis

scholarly journals The epidemiology of hospital death following pediatric severe community acquired pneumonia

2021 ◽  
Vol 47 (1) ◽  
Author(s):  
Xiao-Xiao Ao
Keyword(s):  
Organ Dysfunction ◽  
Multiple Organ Dysfunction Syndrome ◽  
Severe Pneumonia ◽  
Multiple Organ ◽  
Community Acquired Pneumonia ◽  
Hospital Death ◽  
Multiple Organ Dysfunction ◽  
Respiratory Dysfunction ◽  
Time To Death ◽  
Severe Community Acquired Pneumonia

Abstract Background Community acquired pneumonia is the primary cause of pediatric hospitalizations and deaths in children under 5 years of age. But the epidemiology of death in pediatric severe community acquired pneumonia was not well characterized. Methods This retrospective observational study was performed at the academic Emergency department and intensive care unit and we investigated the timing, cause, mode and attribution of death in children with severe community acquired pneumonia. Results Of 962 subjects with severe community acquired pneumonia, there were 57 non-survivors (5.9% mortality). Median time to death was 7 [IQR 3,16] days from severe community acquired pneumonia recognition. Patients dying ≤7 days were younger, had greater illness severity and higher rate of congenital heart disease, who were more likely to die of a cardiovascular cause. Multiple organ dysfunction syndrome predominated in deaths > 7 days. Unsuccessful cardiopulmonary resuscitation was the most common mode of death at all timepoints. Our findings suggested that in pediatric severe community acquired pneumonia, early deaths were due primarily to cardiovascular dysfunction, while later deaths were more commonly due to multiple organ dysfunction syndrome. Conclusions Deaths from non-pulmonary factors accounted for a substantial portion of non-survivors. Respiratory dysfunction accounted for only a minority of deaths. Our study highlighted limitations associated with rescuing patients with severe pneumonia from death if extrapulmonary organ dysfunctions could not be simultaneously managed.

Towards a new classification of stable phase schizophrenia into major and simple neuro-cognitive psychosis: Results of unsupervised machine learning analysis

2018 ◽  
Vol 24 (4) ◽  
pp. 879-891 ◽  
Author(s):  
Buranee Kanchanatawan ◽  
Sira Sriswasdi ◽  
Supaksorn Thika ◽  
Drozdstoy Stoyanov ◽  
Sunee Sirivichayakul ◽  
...  
Keyword(s):  
Machine Learning ◽  
Stable Phase ◽  
New Classification ◽  
Unsupervised Machine Learning ◽  
Learning Analysis

scholarly journals The Epidemiology of Hospital Death Following Pediatric Severe Community Acquired Pneumonia

2020 ◽  
Author(s):  
Xiao-Xiao Ao ◽  
Li-Ping Tan ◽  
Qiu-Feng Wan ◽  
Yong-Qin Li
Keyword(s):  
Organ Dysfunction ◽  
Multiple Organ Dysfunction Syndrome ◽  
Severe Pneumonia ◽  
Multiple Organ ◽  
Community Acquired Pneumonia ◽  
Hospital Death ◽  
Multiple Organ Dysfunction ◽  
Respiratory Dysfunction ◽  
Time To Death ◽  
Severe Community Acquired Pneumonia

Abstract BackgroundCommunity acquired pneumonia is the primary cause of pediatric hospitalizations and deaths in children under 5 years of age. But the epidemiology of death in pediatric severe community acquired pneumonia was not well characterized. MethodsThis retrospective observational study was performed at the academic Emergency department and intensive care unit and we investigated the timing, cause, mode and attribution of death in children with severe community acquired pneumonia. ResultsOf 962 subjects with severe community acquired pneumonia, there were 57 non-survivors (5.9% mortality). Median time to death was 7 [IQR 3,16] days from severe community acquired pneumonia recognition. Patients dying ≤ 7 days were younger, had greater illness severity and higher rate of congenital heart disease, who were more likely to die of a cardiovascular cause. Multiple organ dysfunction syndrome predominated in deaths > 7 days. Unsuccessful cardiopulmonary resuscitation was the most common mode of death at all timepoints. Our findings suggested that in pediatric severe community acquired pneumonia, early deaths were due primarily to cardiovascular dysfunction, while later deaths were more commonly due to multiple organ dysfunction syndrome. ConclusionsDeaths from non-pulmonary factors accounted for a substantial portion of non-survivors. Respiratory dysfunction accounted for only a minority of deaths. Our study highlighted limitations associated with rescuing patients with severe pneumonia from death if extrapulmonary organ dysfunctions could not be simultaneously managed.

Sign in / Sign up

Export Citation Format

Share Document