Trustworthy Explanations for Knowledge Discovered from E-Health Records

In the current era of big data, very large amounts of data are generating at a rapid rate from a wide variety of rich data sources. Electronic health (e-health) records are examples of the big data. With the technological advancements, more healthcare practice has gradually been supported by electronic processes and communication. This enables health informatics, in which computer science meets the healthcare sector to address healthcare and medical problems. Embedded in the big data are valuable information and knowledge that can be discovered by data science, data mining and machine learning techniques. Many of these techniques apply "opaque box"approaches to make accurate predictions. However, these techniques may not be crystal clear to the users. As the users not necessarily be able to clearly view the entire knowledge discovery (e.g., prediction) process, they may not easily trust the discovered knowledge (e.g., predictions). Hence, in this paper, we present a system for providing trustworthy explanations for knowledge discovered from e-health records. Specifically, our system provides users with global explanations for the important features among the records. It also provides users with local explanations for a particular record. Evaluation results on real-life e-health records show the practicality of our system in providing trustworthy explanations to knowledge discovered (e.g., accurate predictions made). © 2022 IEEE.

COVID Impact on Functional Status of Hospitalized Patients

Summary Originating with unexplained symptoms from Wuhan, city of China, COVID-19 being a global pandemic causing tremendous morbidity and mortality, has proved to be the biggest challenge of the 20th century. This study aimed to explore the functional impacts of COVID-19 upon those patients who were diagnosed with this disease and were admitted in hospitals. This cross-sectional survey included 183 COVID-19 diagnosed patients from COVID-19 isolation wards of public and private hospitals of Islamabad and Rawalpindi. After getting ethical permission from Institutional Review Board of Shifa International Hospital (Ref # 070-21), this survey was conducted for the time period of 6 months from December 2020 to May 2021. Through convenient sampling, 183 patients with the age range of 25 to 55 years with no already diagnosed psychological complaints were assessed for eligibility briefed regarding the study purpose and then were asked for their voluntary participation. The Functional Status Scale for the Intensive Care Unit (FSS-ICU) was used to assess the functional status impacted due to COVID-19 during hospitalization. Frequencies and percentages were calculated through SPSS-21. On FSS-ICU, out of 183 COVID-19, 11 (6%) patients reported that they were dependent, 18 (9.8%) required maximum assistance, 32 (17.5%) required moderate assistance, 27 (14.8%) required minimal, 24 (13.1%) required supervision to complete their tasks, 28 (15.3%) required assistive devices, whereas 43 (23.5%) were totally independent. Results indicated a temporal impact of COVID-19 upon functional status of hospitalized patients in intensive care units, therefore highlighting the need of physiotherapeutic and psychotherapeutic interventions.

Markers of coagulation and hemostatic activation identify COVID-19 patients at high risk for thrombotic events

Introduction: COVID-19 has been associated with venous and arterial thrombotic complications. The objective of our study was to determine whether markers of coagulation and hemostatic activation (MOCHA) on admission could identify COVID-19 patients at risk for thrombotic events. Methods: COVID-19 patients admitted to a tertiary academic healthcare system from April 3, 2020 to July 31, 2020 underwent admission testing of MOCHA profile parameters (plasma d-dimer, prothrombin fragment 1.2, thrombin-antithrombin complex, and fibrin monomer). For this analysis we excluded patients on outpatient anticoagulation therapy preceding admission. Prespecified endpoints monitored during hospitalization included deep vein thrombosis, pulmonary embolism, myocardial infarction, ischemic stroke and access line thrombosis. Results: During the study period, 276 patients were included in the analysis cohort (mean age 59 ± 6.3 years, 47% female, 83% non-white race). Arterial and venous thrombotic events occurred in 43 (16%) patients (see Table). Each coagulation marker was independently associated with the composite endpoint (p<0.05). Admission MOCHA with ≥ 2 abnormalities was associated with the composite endpoint (OR 3.1, 95% CI 1.2-8.3), ICU admission (OR 3.2, 95% CI 1.8-5.5) and intubation (OR 2.8, 95% CI 1.5-5.5). Admission MOCHA with < 2 abnormalities (26% of the cohort) had sensitivity of 88% and a negative predictive value of 93% for an in-hospital endpoint. Conclusion: Admission MOCHA with ≥ 2 abnormalities identified COVID-19 patients at risk for a thrombotic event, ICU admission and intubation while < 2 abnormalities identified a subgroup of patients who were at low risk for thrombotic events. Our results suggest that an admission MOCHA profile can be useful to risk stratify COVID-19 patients. Further studies are needed to determine whether an admission MOCHA profile can guide anticoagulation therapy and improve overall clinical outcomes.(Figure Presented).