ABSTRACT
Objectives: Care coordination is a key component of the population health management. However, the mechanism for identifying patients who may benefit the most from this model of care is unclear. The objective of study is to evaluate the performance of a risk-stratification instrument using a model of AI - Rule-based expert system (RBES) - in predicting healthcare utilization and costs. Method(s): Retrospective cohort study from beneficiaries of a health plan using administrative databases (prior authorizations claims systems): 27,539 individuals were assigned a predicted illness burden score using a case-mix adjustment system from diagnoses and health utilization data (2019 to 2021). Population was stratified according to the score into three main groups: G1) case management;G2) health support;G3) health promotion. Analysis was also performed in subgroups: prolonged hospitalization, readmission, complex medical conditions (CC), continued therapy (CT) (G1);chronic unstable (CU), post-COVID 19, high cost, high user (G2);healthy elderly, risk factor, low risk (G3). Data Science team analyzed population using algorithms which uses a set of logical rules derivatives of human specialists. Result(s): According to score 1,053 individuals stratified in G1, average age 68 years, annual cost U$11,318, 10 times more than average;G2, n=5,429;67 years;U$2,863;G3, n=21,037;53 years;U$246. The sickest population: 3.8%, 19.7% and 76.5% uses about 37%, 48% and 15% of healthcare expenses respectively. Most representative subgroups: CC, CT, and CU with average annual cost five or more times than average. Conclusion(s): Dashboard developed using RBES tools can supports healthcare management. Stratifying risk helps to address specific health care challenges, to align levels of care, to implement a value-based care approach. Also demonstrates to be the most logical and practical initial step to create a data set with labeled variables to start a machine learning using supervised training - the next phase in this project. Copyright © 2022
ABSTRACT
The supply chain impact of COVID-19 led to varying levels of uncertainty in every country. For Hilti, a global manufacturing company supplying the construction industry, with a vertically integrated supply chain, the following specific risks arose: closures of suppliers, production plants, or country borders could lead to production stops or import stops limiting the replenishment capabilities from the supply side. To illustrate how the company copes with these challenges this business case focuses on the warehousing function as it represents the “moment of truth,” the final delivery to the customer. During the COVID pandemic Hilti benefited from the existing structure and could bring the different resilience elements—visibility, flexibility, collaboration, and control—into play. The combination of ad-hoc actions and at the same time strengthening supply chain resilience within its global logistics strategy was the key to successfully manage the delivery challenges and to keep operations up and running with limited customer impact. While business environments become more complex and uncertain, previous methods of risk mitigation reach their limits and a resilient supply chain becomes a critical key factor for future business success. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.
ABSTRACT
Objectives: Covid 19 was declared a pandemic by the WHO on March 2020. Brazil emerged as an epicenter of the coronavirus pandemic with more than 12.8 million cases of COVID-19, including over 325,000 fatalities until April 2021. This study evaluates the survival curve and associated factors with mortality after COVID-19 hospitalizations. Methods: Retrospective analysis until May 2021 from administrative database of 37,462 people. Mortality after hospital discharge was investigated in different groups: presence or absence of comorbidities prior to admission (Charlson Comorbidity Index), age (greater/less than 60 years), sex, mean time hospital stay (up to 13/14+ days) and ICU admission. For survival analysis we used the Kaplan-Meier method. Log-rank test applied to compare curves. 95% confidence interval (CI) and significance when p <0.05. Results: Analysis included 916 patients, mean age 69.1 (95% CI 68.1 to 70.1), 50.0% women (n=458) and 50.0% men (n=458). Hospital stay average was 10.9 days (95% CI 10.1 to 11.7). From hospitalizations, 38.9% admitted in the ICU (n=356). The overall mortality rate during period was 23.1% (n=212), men 24.0% (n=110) and women 22.3% (n=102). Mortality rate during Covid hospitalization was 11.6% (n=106), 10.9% in men (n=50) and 12.2% in women (n=56). Risk of death at any time during the follow-up period was significantly higher when presence of previous comorbidities (p=0.020), age greater than 60 years (p <0.001), ICU stay (p <0.001), and higher average length hospital stay (p=0.001). Conclusions: During the follow-up period after COVID 19 hospitalization patients aged 60 or over, previous comorbidities, prolonged hospital stay, and ICU admissions showed higher mortality. This observed correlation was used to develop a calculator using artificial intelligence to predict which individuals present high risk of death after COVID-19 hospital discharges and to implement models for monitoring and health management.
ABSTRACT
Objectives: Brazil emerged as an epicenter of the coronavirus pandemic with more than 12.8 million cases, including over 500,000 fatalities. Some private health plans implemented early assistance to cancer patients, due to be more susceptible to infections and complications. This study evaluates mortality curves rates of hospitalized cancer patients. Methods: Retrospective analysis from March 2020-May 2021 of 37,462 people administrative database. Mortality during and after hospital discharge studied into two groups: presence/absence of cancer prior to admission, with/without previous chemotherapy. Variables: In-hospital mortality (IHM) and after discharge or anytime death during the study. For survival analysis after discharge, we used the Kaplan-Meier method. Log-rank test was applied to compare curves. For statistical significance, Chi-square tests (Mantel-Haenszel and Fisher's Exact), when p <0.05. Confidence interval (CI) 95%. Results: Overall rate of oncologic patients from total was 2.7%. Among 916 COVID-19 admissions, 79 with cancer (8.6%;p< 0,001, hazard ratio 3.4). Mean age 69.1 (CI 68.1-70.1), 50% women (n=458) and 50% men (n=458). IHM 16.5% (n=13) in oncologic group and 11.2% (n=93) in non-oncologic patients (p=ns). Risk of death during hospitalization and follow-up (14 months) was significantly higher when presence of previous cancer (35.5%;n=28) than without cancer (24.35%;n=203), p=0.029. Mortality rate of cancer patients without COVID was 17.4% in the same period of follow up. Risk of death for oncologic patients was 3.8 higher if they had COVID (p< 0.001). Conclusions: COVID-19 hospitalization and death risk are significantly higher in patients with cancer, even with early strategies by the HC plan to reduce the risk. IHM wasn’t different from patients without cancer, but overall mortality was higher after discharge, comparing to cancer patients without COVID19. There is a crucial need to understand better and mitigate these excess hospitalization risks and higher mortality which may be revealed over the follow up.
ABSTRACT
Objectives: Predicting survival and risk of death after hospital discharge due to COVID-19 can help in screening patients who require special care after hospitalization. This study evaluates the survival curve and associated factors with mortality after COVID-19 admissions. Methods: Retrospective analysis until May 2021 from administrative database of 37,462 people. Analysis included 810 inpatients admitted with COVID-19 followed each month regarding survival after hospital discharge. Survival analysis performed using Cox Ridge Penalized Regression (CRPR), Gradient Boost Survival (GBS) and Random Survival Forest (RFS) from the Python library scikit-survival. Dataset separated into training and test set with the proportions of 75% and 25% respectively. Our predictive variables were patient’s age, sex, if had any comorbidity, cancer, hospitalization longer than 14 days or intensive care unit (ICU) stay. Results: From the 810 patients, 125 had died after hospital discharge, mean time of death 9.28 months. Model performance evaluated through the Concordance Index (C-Index) metric. CRPR had better performance with a C-Index of 0.74, while RFS and GBS had a C-Index of 0.73. Risk of death at any time during the follow-up period was significantly higher when presence of previous comorbidities (p=0.020), age greater than 60 years (p <0.001), ICU stay (p <0.001), and higher average length hospital stay (p=0.001). Conclusions: Several tools have been developed for to calculate absolute risk or chances of needing to go into hospital or dying from Covid-19. The online risk calculator that we developed is unique and suitable to predict which person present high risk of death after COVID-19 hospital discharges and prioritizing individuals to receive special care after leaving the hospital. Models like the one we have developed are only as good as the data they are trained on. We will update the calculator as the amount of data we are able to collect increases.
ABSTRACT
The increasing implementation of digital technologies has various positive impacts on companies. However, many companies often rush into such an implementation of technological trends without sufficient preparation and pay insufficient attention to the human factors involved in digitization. This phenomenon can be exacerbated when these technologies become highly dependent, as during the COVID-19 pandemic. This study aims to better understand challenges and to propose solutions for a successful implementation of digitized technology. A literature review is combined with survey results and specific consulting strategies. Data from the first wave of the COVID-19 pandemic in Germany were collected by means of an online survey, with a representative sample of the German population. However, we did not reveal any correlation between home office and suffering, mental health, and physical health (indicators of digitization usage to cope with COVID-19 pandemic), but rather that younger workers are more prone to using digitized technology. Based on previous findings that older individuals tend to have negative attitudes toward digital transformation, appropriate countermeasures are needed to help them become more tech-savvy. Accordingly, a software tool is proposed. The tool can help the management team to manage digitization efficiently. Employee well-being can be increased as companies are made aware of necessary measures such as training for individuals and groups at an early stage. © 2021 by the authors. Licensee MDPI, Basel, Switzerland.
ABSTRACT
Background: Acute kidney injury (AKI) is frequently observed in critically ill patients and is associated with a poor prognosis. AKI has recently moved into the focus of interest during the SARS-CoV-2 pandemic as high rates of AKI have been reported in severe COVID-19. We aimed to delineate cell type-specific molecular phenotypes associated with human AKI, including COVID-associated AKI. Methods: We analyzed human kidney tissues using histology and single-nuclei RNA sequencing. Samples included kidney biopsies obtained within 2 hours post mortem from patients who succumbed to critical illness with and without evidence of AKI. Samples also included tumor-adjacent normal kidney tissues obtained during surgeries. AKI cases included patients with severe courses of COVID-19 (COVID AKI) and patients with other types of critical illness associated with systemic inflammation (Non-COVID AKI). Postmortem kidney tissues obtained 30 min, 1 hour and 2 hours after death from a brain-dead patient without AKI were analyzed to assess the impact of post-mortem effects. Results: Single-nuclei sequencing from kidney tissues yielded data of high transcriptional depth, which allowed transcriptome-based identification and de-novo spatial reconstruction of kidney cells. Principal component and differential gene expression analyses indicated that the presence of clinically confirmed AKI was the primary driver of global kidney transcriptomes and that different molecular subtypes of AKI existed. In contrast, the sampling time post-mortem and the presence of COVID-19 had minor effects. Subclustering analyses of different kidney cell types identified subclasses of cells representing injured kidney tubular cells, which were marked by distinct biomarker expression and expression signatures signifying intrinsic responses to inflammation, an induction of epithelial-to-mesenchymal transition, and an upregulation of hitheto unrecognized novel receptor-ligand pairs. Conclusions: We provide the first cell type-specific molecular atlas of human AKI, revealing unanticipated disease subtypes and cell type-specific injury patterns.
ABSTRACT
Objectives: By January 6, 2021, 7,812,007 cases and 197,777 deaths in total have been confirmed in Brazil, suggesting that the overall death rate of COVID-19 was 2.6%. Diabetes is the most common comorbidities in adult patients infected with Severe Acute Syndrome Coronavirus 2 (SARS-CoV-2) and has been associated with increased mortality. This study analyzed the mortality of hospitalized COVID-19 patients with diabetes. Methods: 654 patients with COVID-19, including 81 diabetic patients and 573 nondiabetic patients from March to December/2020, were registered. Administrative data from hospitalizations reimbursed by the health plan were analyzed. Dependent variable: mortality rate (MR) of both groups had the number of deaths as a numerator and the number of patients hospitalized with COVID-19 in the period as denominator. Independent variables: age and sex. The main outcome was mortality by the SARS-CoV2. Statistical: Microsoft Excel® v2010 and Qlik Sense® v13.21 were used for relative and absolute frequencies, means and standard deviation (95% confidence intervals, significance when p<0.05). Results: From the total number of hospitalized COVID-19 patients, 50.6% were male and 49.4% female. The median age was 64.3 years. Approximately 12.4% of patients had diabetes. The mortality rate in diabetic patients was 28.4% and 18.0% in nondiabetic patients, with a pooled Odds Ratio of 1.81 (95% CI 1.07 – 3.07;p < 0.05). When comparing the rate by sex, mortality in diabetic men was higher than in women (21.1% and 17.3%, respectively;p > 0.05). Conclusions: This study suggests that diabetes are associated with an increased risk of COVID-19-related in-hospital death confirming a need for close monitoring of diabetic patients during hospitalization. Increased COVID-19-related mortality usually was associated with cardiovascular and renal complications of diabetes. Diabetes requires uninterrupted treatment, so Healthcare System must take steps to ensure access to the care it needs.
ABSTRACT
Objectives: One of the major concerns is the burden COVID-19 will impose on the health care system worldwide. Brazil is the second country with the most confirmed cases (more than 1 million cases and 60 thousand deaths). The study aims to evaluate the impact on use of the health plan by COVID-19. Methods: Design: retrospective non-interventional study using population-based health administrative databases. Setting: payer provider healthcare organization. Participants: 41,640 individuals attended by plan. Outcomes: number of prior authorizations to tests and hospitalizations during two periods of 90 days, before (P1) and after (P2) the first registered case of COVID-19. Hospitalizations were classified into surgical, clinical potentially avoidable and other types. Statistics: data were analyzed descriptively considering measures of central tendency for continuous variables and frequency measures for categorical variables. Microsoft Excel® v2010 and Qlik Sense® v13.21 were used to data and statistics. Results: During the study period (180 days), 21,583 patients underwent to tests, 15,018 in P1 and 6,565 in P2, a reduction of 56.3% and 3,316 hospitalizations occurred (P1=2,066;P2=1,250;reduction of 39.5%). Segmented analysis of hospitalizations demonstrates 69.8% reduction in surgical cases (1,043, P1=801 and P2=242) and 20.1% in clinical admissions (2.089, P1=1,161 and P2=928). We also observed a 37.2% reduction in cases of potentially preventable hospitalizations. All other types decreased 23.1% (184, P1=104 and P2=80). Conclusions: Local health guidelines recommended to postpone procedures due risk of COVID-19 infection during hospital stay and block of hospital beds to attend to the pandemic. After the critical period, we observed a rising curve suggesting a gradual return to standard performance of tests (+80.6%), not yet observed in hospitalizations (+0.2%). The behavior of beneficiaries, professionals and health services that resulted in the postponement of procedures contributed to avoid the collapse of the Brazilian health system during the pandemic period.