Prediction models for diagnosis and prognosis of covid-19: systematic review and critical appraisal

Evaluation of Risk of Bias in Neuroimaging-Based Artificial Intelligence Models for Psychiatric Diagnosis: A Systematic Review

IMPORTANCE

Neuroimaging-based artificial intelligence (AI) diagnostic models have proliferated in psychiatry. However, their clinical applicability and reporting quality (ie, feasibility) for clinical practice have not been systematically evaluated.

OBJECTIVE

To systematically assess the risk of bias (ROB) and reporting quality of neuroimaging-based AI models for psychiatric diagnosis.

EVIDENCE REVIEW

PubMed was searched for peer-reviewed, full-length articles published between January 1, 1990, and March 16, 2022. Studies aimed at developing or validating neuroimaging-based AI models for clinical diagnosis of psychiatric disorders were included. Reference lists were further searched for suitable original studies. Data extraction followed the CHARMS (Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modeling Studies) and PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-analyses) guidelines. A closed-loop cross-sequential design was used for quality control. The PROBAST (Prediction Model Risk of Bias Assessment Tool) and modified CLEAR (Checklist for Evaluation of Image-Based Artificial Intelligence Reports) benchmarks were used to systematically evaluate ROB and reporting quality.

FINDINGS

A total of 517 studies presenting 555 AI models were included and evaluated. Of these models, 461 (83.1%; 95% CI, 80.0%-86.2%) were rated as having a high overall ROB based on the PROBAST. The ROB was particular high in the analysis domain, including inadequate sample size (398 of 555 models [71.7%; 95% CI, 68.0%-75.6%]), poor model performance examination (with 100% of models lacking calibration examination), and lack of handling data complexity (550 of 555 models [99.1%; 95% CI, 98.3%-99.9%]). None of the AI models was perceived to be applicable to clinical practices. Overall reporting completeness (ie, number of reported items/number of total items) for the AI models was 61.2% (95% CI, 60.6%-61.8%), and the completeness was poorest for the technical assessment domain with 39.9% (95% CI, 38.8%-41.1%).

CONCLUSIONS AND RELEVANCE

This systematic review found that the clinical applicability and feasibility of neuroimaging-based AI models for psychiatric diagnosis were challenged by a high ROB and poor reporting quality. Particularly in the analysis domain, ROB in AI diagnostic models should be addressed before clinical application.

Serial measurement of circulating calprotectin as a prognostic biomarker in COVID-19 patients in intensive care setting

OBJECTIVES

Circulating calprotectin (cCLP) has been shown to be a promising prognostic marker for COVID-19 severity. We aimed to investigate the prognostic value of serial measurements of cCLP in COVID-19 patients admitted to an intensive care unit (ICU).

METHODS

From November 2020 to May 2021, patients with COVID-19, admitted at the ICU of the OLV Hospital, Aalst, Belgium, were prospectively included. For sixty-six (66) patients, blood samples were collected at admission and subsequently every 48 h during ICU stay. On every sample (total n=301), a cCLP (EliA™ Calprotectin 2, Phadia 200, Thermo Fisher Scientific; serum/plasma protocol (for Research Use Only, -RUO-) and C-reactive protein (CRP; cobas c501/c503, Roche Diagnostics) analysis were performed. Linear mixed models were used to associate biomarkers levels with mortality, need for mechanical ventilation, length of stay at ICU (LOS-ICU) and medication use (antibiotics, corticosteroids, antiviral and immune suppressant/modulatory drugs).

RESULTS

Longitudinally higher levels of all biomarkers were associated with LOS-ICU and with the need for mechanical ventilation. Medication use and LOS-ICU were not associated with variations in cCLP and CRP levels. cCLP levels increased significantly during ICU hospitalization in the deceased group (n=21/66) but decreased in the non-deceased group (n=45/66). In contrast, CRP levels decreased non-significantly in both patient groups, although significantly longitudinally higher CRP levels were obtained in the deceased subgroup.

CONCLUSIONS

Serial measurements of cCLP provides prognostic information which can be useful to guide clinical management of COVID-19 patients in ICU setting.

Encephalic nocardiosis after mild COVID-19: A case report

The COVID-19 pandemic and the associated post-acute sequelae of COVID-19 (PASC) have led to the identification of a complex disease phenotype that is associated with important changes in the immune system. Herein, we describe a unique case of Nocardia farcinica cerebral abscess in an individual with sudden immunodeficiency several months after mild COVID-19. Intravenous Bactrim and Imipenem were prescribed for 6 weeks. After this, a 12-month course of Bactrim and Clavulin was prescribed to be taken orally, given the N. farcinica infection at the level of the central nervous system. This case report highlights the need for future research into the pathophysiology of COVID-19 and PASC immune dysregulation in convalescent individuals. It also draws attention to the need for timely consideration of opportunistic infections in patients with a history of COVID-19.

Real-time estimation and forecasting of COVID-19 cases and hospitalizations in Wisconsin HERC regions for public health decision making processes

BACKGROUND

The spread of the COVID-19 (SARS-CoV-2) and the surging number of cases across the United States have resulted in full hospitals and exhausted health care workers. Limited availability and questionable reliability of the data make outbreak prediction and resource planning difficult. Any estimates or forecasts are subject to high uncertainty and low accuracy to measure such components. The aim of this study is to apply, automate, and assess a Bayesian time series model for the real-time estimation and forecasting of COVID-19 cases and number of hospitalizations in Wisconsin healthcare emergency readiness coalition (HERC) regions.

METHODS

This study makes use of the publicly available Wisconsin COVID-19 historical data by county. Cases and effective time-varying reproduction number [Formula: see text] by the HERC region over time are estimated using Bayesian latent variable models. Hospitalizations are estimated by the HERC region over time using a Bayesian regression model. Cases, effective Rt, and hospitalizations are forecasted over a 1-day, 3-day, and 7-day time horizon using the last 28 days of data, and the 20%, 50%, and 90% Bayesian credible intervals of the forecasts are calculated. The frequentist coverage probability is compared to the Bayesian credible level to evaluate performance.

RESULTS

For cases and effective [Formula: see text], all three time horizons outperform the three credible levels of the forecast. For hospitalizations, all three time horizons outperform the 20% and 50% credible intervals of the forecast. On the contrary, the 1-day and 3-day periods underperform the 90% credible intervals. Questions about uncertainty quantification should be re-calculated using the frequentist coverage probability of the Bayesian credible interval based on observed data for all three metrics.

CONCLUSIONS

We present an approach to automate the real-time estimation and forecasting of cases and hospitalizations and corresponding uncertainty using publicly available data. The models were able to infer short-term trends consistent with reported values at the HERC region level. Additionally, the models were able to accurately forecast and estimate the uncertainty of the measurements. This study can help identify the most affected regions and major outbreaks in the near future. The workflow can be adapted to other geographic regions, states, and even countries where decision-making processes are supported in real-time by the proposed modeling system.

Deep Learning With Chest Radiographs for Making Prognoses in Patients With COVID-19: Retrospective Cohort Study

BACKGROUND

An artificial intelligence (AI) model using chest radiography (CXR) may provide good performance in making prognoses for COVID-19.

OBJECTIVE

We aimed to develop and validate a prediction model using CXR based on an AI model and clinical variables to predict clinical outcomes in patients with COVID-19.

METHODS

This retrospective longitudinal study included patients hospitalized for COVID-19 at multiple COVID-19 medical centers between February 2020 and October 2020. Patients at Boramae Medical Center were randomly classified into training, validation, and internal testing sets (at a ratio of 8:1:1, respectively). An AI model using initial CXR images as input, a logistic regression model using clinical information, and a combined model using the output of the AI model (as CXR score) and clinical information were developed and trained to predict hospital length of stay (LOS) ≤2 weeks, need for oxygen supplementation, and acute respiratory distress syndrome (ARDS). The models were externally validated in the Korean Imaging Cohort of COVID-19 data set for discrimination and calibration.

RESULTS

The AI model using CXR and the logistic regression model using clinical variables were suboptimal to predict hospital LOS ≤2 weeks or the need for oxygen supplementation but performed acceptably in the prediction of ARDS (AI model area under the curve [AUC] 0.782, 95% CI 0.720-0.845; logistic regression model AUC 0.878, 95% CI 0.838-0.919). The combined model performed better in predicting the need for oxygen supplementation (AUC 0.704, 95% CI 0.646-0.762) and ARDS (AUC 0.890, 95% CI 0.853-0.928) compared to the CXR score alone. Both the AI and combined models showed good calibration for predicting ARDS (P=.079 and P=.859).

CONCLUSIONS

The combined prediction model, comprising the CXR score and clinical information, was externally validated as having acceptable performance in predicting severe illness and excellent performance in predicting ARDS in patients with COVID-19.

Digital public health leadership in the global fight for health security

The COVID-19 pandemic highlighted the need to prioritise mature digital health and data governance at both national and supranational levels to guarantee future health security. The Riyadh Declaration on Digital Health was a call to action to create the infrastructure needed to share effective digital health evidence-based practices and high-quality, real-time data locally and globally to provide actionable information to more health systems and countries. The declaration proposed nine key recommendations for data and digital health that need to be adopted by the global health community to address future pandemics and health threats. Here, we expand on each recommendation and provide an evidence-based roadmap for their implementation. This policy document serves as a resource and toolkit that all stakeholders in digital health and disaster preparedness can follow to develop digital infrastructure and protocols in readiness for future health threats through robust digital public health leadership.

Disease severity in hospitalized COVID-19 patients: comparing routine surveillance with cohort data from the LEOSS study in 2020 in Germany

INTRODUCTION

Studies investigating risk factors for severe COVID-19 often lack information on the representativeness of the study population. Here, we investigate factors associated with severe COVID-19 and compare the representativeness of the dataset to the general population.

METHODS

We used data from the Lean European Open Survey on SARS-CoV-2 infected patients (LEOSS) of hospitalized COVID-19 patients diagnosed in 2020 in Germany to identify associated factors for severe COVID-19, defined as progressing to a critical disease stage or death. To assess the representativeness, we compared the LEOSS cohort to cases of hospitalized patients in the German statutory notification data of the same time period. Descriptive methods and Poisson regression models were used.

RESULTS

Overall, 6672 hospitalized patients from LEOSS and 132,943 hospitalized cases from the German statutory notification data were included. In LEOSS, patients above 76 years were less likely represented (34.3% vs. 44.1%). Moreover, mortality was lower (14.3% vs. 21.5%) especially among age groups above 66 years. Factors associated with a severe COVID-19 disease course in LEOSS included increasing age, male sex (adjusted risk ratio (aRR) 1.69, 95% confidence interval (CI) 1.53-1.86), prior stem cell transplantation (aRR 2.27, 95% CI 1.53-3.38), and an elevated C-reactive protein at day of diagnosis (aRR 2.30, 95% CI 2.03-2.62).

CONCLUSION

We identified a broad range of factors associated with severe COVID-19 progression. However, the results may be less applicable for persons above 66 years since they experienced lower mortality in the LEOSS dataset compared to the statutory notification data.

Diagnostic Performance of Individual Symptoms to Predict SARS-CoV-2 RT-PCR Positivity and Symptom Persistence among Suspects Presenting in Primary Care during the First Wave of COVID-19

This study aimed to estimate the diagnostic performance of patient symptoms and to describe the clinical course of RT-PCR-positive compared with RT-PCR-negative patients in primary care. Symptomatic COVID-19 suspects were assessed clinically at the initial consultation in primary care between March and May 2020, followed by phone consultations over a span of at least 28 days. Sensitivity and specificity were estimated for each symptom using the initial RT-PCR result as a reference standard. The proportions of symptomatic patients according to the RT-PCR test results were compared over time, and time to recovery was estimated. Out of 883 patients, 13.9% had a positive RT-PCR test, and 17.4% were not tested. Most sensitive symptoms were cough, myalgia, and a history of fever, while most specific symptoms were fever for ≥4 days, hypo/anosmia, and hypo/ageusia. At the final follow up (median time 55 days, range 28-105 days), 44.7% of patients still reported symptoms in the RT-PCR-positive group, compared with 18.3% in the negative group (p < 0.001), mostly with hypo/anosmia (16.3%), dyspnea (12.2%), and fatigue (10.6%). The discriminative value of individual symptoms for diagnosing COVID-19 was limited. Almost half of the SARS-CoV-2-positive patients still reported symptoms at least 28 days after the initial consultation.

Plasma Proteomic Variables Related to COVID-19 Severity: An Untargeted nLC-MS/MS Investigation

Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2) infection leads to a wide range of clinical manifestations and determines the need for personalized and precision medicine. To better understand the biological determinants of this heterogeneity, we explored the plasma proteome of 43 COVID-19 patients with different outcomes by an untargeted liquid chromatography-mass spectrometry approach. The comparison between asymptomatic or pauci-symptomatic subjects (MILDs), and hospitalised patients in need of oxygen support therapy (SEVEREs) highlighted 29 proteins emerged as differentially expressed: 12 overexpressed in MILDs and 17 in SEVEREs. Moreover, a supervised analysis based on a decision-tree recognised three proteins (Fetuin-A, Ig lambda-2chain-C-region, Vitronectin) that are able to robustly discriminate between the two classes independently from the infection stage. In silico functional annotation of the 29 deregulated proteins pinpointed several functions possibly related to the severity; no pathway was associated exclusively to MILDs, while several only to SEVEREs, and some associated to both MILDs and SEVEREs; SARS-CoV-2 signalling pathway was significantly enriched by proteins up-expressed in SEVEREs (SAA1/2, CRP, HP, LRG1) and in MILDs (GSN, HRG). In conclusion, our analysis could provide key information for 'proteomically' defining possible upstream mechanisms and mediators triggering or limiting the domino effect of the immune-related response and characterizing severe exacerbations.

Regression-based prognostic models for functional independence after postacute brain injury rehabilitation are not transportable: a systematic review

BACKGROUND AND OBJECTIVES

To identify and summarize validated multivariable prognostic models for the Functional Independence Measure® (FIM®) at discharge from post-acute inpatient rehabilitation in adults with acquired brain injury (ABI).

METHODS

This review was conducted based on the recommendations of the Cochrane Prognosis Methods Group and adheres to the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Three databases were systematically searched in May 2021 and updated in April 2022. Main inclusion criteria were: a) adult patients with ABI, b) validated multivariable prognostic model, c) time of prognostication within 1-week of admission to post-acute rehabilitation, and d) outcome was the FIM® at discharge from post-acute rehabilitation.

RESULTS

The search yielded 3,169 unique articles. Three articles fulfilled the inclusion criteria, accounting for n = 6 internally and n = 2 externally validated prognostic models. Discrimination was estimated as an area under the curve between 0.76 and 0.89. Calibration was deemed to be assessed insufficiently. The included models were judged to be of high risk of bias.

CONCLUSION

Current prognostic models for the FIM® in post-acute rehabilitation for patients with ABI lack the methodological rigor to support clinical use outside the development setting. Future studies addressing functional independence should ensure appropriate model validation and conform to uniform reporting standards for prognosis research.

US and Dutch Perspectives on the Use of COVID-19 Clinical Prediction Models: Findings from a Qualitative Analysis

INTRODUCTION

Clinical prediction models (CPMs) for coronavirus disease 2019 (COVID-19) may support clinical decision making, treatment, and communication. However, attitudes about using CPMs for COVID-19 decision making are unknown.

METHODS

Online focus groups and interviews were conducted among health care providers, survivors of COVID-19, and surrogates (i.e., loved ones/surrogate decision makers) in the United States and the Netherlands. Semistructured questions explored experiences about clinical decision making in COVID-19 care and facilitators and barriers for implementing CPMs.

RESULTS

In the United States, we conducted 4 online focus groups with 1) providers and 2) surrogates and survivors of COVID-19 between January 2021 and July 2021. In the Netherlands, we conducted 3 focus groups and 4 individual interviews with 1) providers and 2) surrogates and survivors of COVID-19 between May 2021 and July 2021. Providers expressed concern about CPM validity and the belief that patients may interpret CPM predictions as absolute. They described CPMs as potentially useful for resource allocation, triaging, education, and research. Several surrogates and people who had COVID-19 were not given prognostic estimates but believed this information would have supported and influenced their decision making. A limited number of participants felt the data would not have applied to them and that they or their loved ones may not have survived, as poor prognosis may have suggested withdrawal of treatment.

CONCLUSIONS

Many providers had reservations about using CPMs for people with COVID-19 due to concerns about CPM validity and patient-level interpretation of the outcome predictions. However, several people who survived COVID-19 and their surrogates indicated that they would have found this information useful for decision making. Therefore, information provision may be needed to improve provider-level comfort and patient and surrogate understanding of CPMs.

HIGHLIGHTS

While clinical prediction models (CPMs) may provide an objective means of assessing COVID-19 prognosis, provider concerns about CPM validity and the interpretation of CPM predictions may limit their clinical use.Providers felt that CPMs may be most useful for resource allocation, triage, research, or educational purposes for COVID-19.Several survivors of COVID-19 and their surrogates felt that CPMs would have been informative and may have aided them in making COVID-19 treatment decisions, while others felt the data would not have applied to them.

Computational Simulation of Virtual Patients Reduces Dataset Bias and Improves Machine Learning-Based Detection of ARDS from Noisy Heterogeneous ICU Datasets

Goal: Machine learning (ML) technologies that leverage large-scale patient data are promising tools predicting disease evolution in individual patients. However, the limited generalizability of ML models developed on single-center datasets, and their unproven performance in real-world settings, remain significant constraints to their widespread adoption in clinical practice. One approach to tackle this issue is to base learning on large multi-center datasets. However, such heterogeneous datasets can introduce further biases driven by data origin, as data structures and patient cohorts may differ between hospitals. Methods: In this paper, we demonstrate how mechanistic virtual patient (VP) modeling can be used to capture specific features of patients' states and dynamics, while reducing biases introduced by heterogeneous datasets. We show how VP modeling can be used for data augmentation through identification of individualized model parameters approximating disease states of patients with suspected acute respiratory distress syndrome (ARDS) from observational data of mixed origin. We compare the results of an unsupervised learning method (clustering) in two cases: where the learning is based on original patient data and on data derived in the matching procedure of the VP model to real patient data. Results: More robust cluster configurations were observed in clustering using the model-derived data. VP model-based clustering also reduced biases introduced by the inclusion of data from different hospitals and was able to discover an additional cluster with significant ARDS enrichment. Conclusions: Our results indicate that mechanistic VP modeling can be used to significantly reduce biases introduced by learning from heterogeneous datasets and to allow improved discovery of patient cohorts driven exclusively by medical conditions.

Strategies to Improve the Impact of Artificial Intelligence on Health Equity: Scoping Review

BACKGROUND

Emerging artificial intelligence (AI) applications have the potential to improve health, but they may also perpetuate or exacerbate inequities.

OBJECTIVE

This review aims to provide a comprehensive overview of the health equity issues related to the use of AI applications and identify strategies proposed to address them.

METHODS

We searched PubMed, Web of Science, the IEEE (Institute of Electrical and Electronics Engineers) Xplore Digital Library, ProQuest U.S. Newsstream, Academic Search Complete, the Food and Drug Administration (FDA) website, and ClinicalTrials.gov to identify academic and gray literature related to AI and health equity that were published between 2014 and 2021 and additional literature related to AI and health equity during the COVID-19 pandemic from 2020 and 2021. Literature was eligible for inclusion in our review if it identified at least one equity issue and a corresponding strategy to address it. To organize and synthesize equity issues, we adopted a 4-step AI application framework: Background Context, Data Characteristics, Model Design, and Deployment. We then created a many-to-many mapping of the links between issues and strategies.

RESULTS

In 660 documents, we identified 18 equity issues and 15 strategies to address them. Equity issues related to Data Characteristics and Model Design were the most common. The most common strategies recommended to improve equity were improving the quantity and quality of data, evaluating the disparities introduced by an application, increasing model reporting and transparency, involving the broader community in AI application development, and improving governance.

CONCLUSIONS

Stakeholders should review our many-to-many mapping of equity issues and strategies when planning, developing, and implementing AI applications in health care so that they can make appropriate plans to ensure equity for populations affected by their products. AI application developers should consider adopting equity-focused checklists, and regulators such as the FDA should consider requiring them. Given that our review was limited to documents published online, developers may have unpublished knowledge of additional issues and strategies that we were unable to identify.

The Buffering Role of Self-compassion in the Association Between Loneliness with Depressive Symptoms: A Cross-Sectional Survey Study Among Older Adults Living in Residential Care Homes During COVID-19

The coronavirus disease 2019 (COVID-19) pandemic is an ongoing geriatric health emergency with a substantial increase in the prevalence of medical and mental health issues, particularly among older adults living in residential care homes. The knowledge of the risk and protective factors related to the psychological impact of the COVID-19 pandemic on older adults living in residential care homes is based on limited data. This study aimed to investigate whether loneliness mediates the effects of fear generated by a pandemic on depression. Additionally, we hypothesized that self-compassion moderates the effect of loneliness on depression. A sample comprised 323 older adults (females: n = 141, males: n = 182) with mean age = 74.98 years (standard deviation = 6.59, age 65-90) completed a survey comprising the Fear of COVID-19 Scale, De Jung Gierveld Loneliness Scale, the nine-item Patient Health Questionnaire, and the Self-compassion Scale. The results revealed that the total effect of fear on depression was statistically significant, with a medium effect size (Cohen's f 2 = .14) and this association was partially mediated by loneliness (β = .11, SE = .04, P < .001, t = 2.91, 95% CI 0.04-0.19). The self-compassion also moderated the loneliness effect on depression. The findings of this study support COVID-19 evidence, indicating that a greater level of fear generated by the pandemic is linked to depression and loneliness. The findings support the notion that self-compassion mitigates the adverse effects of stressful events in older adults. Customized self-compassion programs may be effective loneliness-mitigating interventions for older adults living in residential care homes.

Supplementary Information

The online version contains supplementary material available at 10.1007/s11469-023-01014-0.

Conventional and Novel Diagnostic Tools for the Diagnosis of Emerging SARS-CoV-2 Variants

Accurate identification at an early stage of infection is critical for effective care of any infectious disease. The "coronavirus disease 2019 (COVID-19)" outbreak, caused by the virus "Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2)", corresponds to the current and global pandemic, characterized by several developing variants, many of which are classified as variants of concern (VOCs) by the "World Health Organization (WHO, Geneva, Switzerland)". The primary diagnosis of infection is made using either the molecular technique of RT-PCR, which detects parts of the viral genome's RNA, or immunodiagnostic procedures, which identify viral proteins or antibodies generated by the host. As the demand for the RT-PCR test grew fast, several inexperienced producers joined the market with innovative kits, and an increasing number of laboratories joined the diagnostic field, rendering the test results increasingly prone to mistakes. It is difficult to determine how the outcomes of one unnoticed result could influence decisions about patient quarantine and social isolation, particularly when the patients themselves are health care providers. The development of point-of-care testing helps in the rapid in-field diagnosis of the disease, and such testing can also be used as a bedside monitor for mapping the progression of the disease in critical patients. In this review, we have provided the readers with available molecular diagnostic techniques and their pitfalls in detecting emerging VOCs of SARS-CoV-2, and lastly, we have discussed AI-ML- and nanotechnology-based smart diagnostic techniques for SARS-CoV-2 detection.

Prognostic Value of Magnesium in COVID-19: Findings from the COMEPA Study

Magnesium (Mg) plays a key role in infections. However, its role in coronavirus disease 2019 (COVID-19) is still underexplored, particularly in long-term sequelae. The aim of the present study was to examine the prognostic value of serum Mg levels in older people affected by COVID-19. Patients were divided into those with serum Mg levels ≤1.96 vs. >1.96 mg/dL, according to the Youden index. A total of 260 participants (mean age 65 years, 53.8% males) had valid Mg measurements. Serum Mg had a good accuracy in predicting in-hospital mortality (area under the curve = 0.83; 95% CI: 0.74-0.91). Low serum Mg at admission significantly predicted in-hospital death (HR = 1.29; 95% CI: 1.03-2.68) after adjusting for several confounders. A value of Mg ≤ 1.96 mg/dL was associated with a longer mean length of stay compared to those with a serum Mg > 1.96 (15.2 vs. 12.7 days). Low serum Mg was associated with a higher incidence of long COVID symptomatology (OR = 2.14; 95% CI: 1.30-4.31), particularly post-traumatic stress disorder (OR = 2.00; 95% CI: 1.24-16.40). In conclusion, low serum Mg levels were significant predictors of mortality, length of stay, and onset of long COVID symptoms, indicating that measuring serum Mg in COVID-19 may be helpful in the prediction of complications related to the disease.

Differences in acoustic features of cough by pneumonia severity in patients with COVID-19: a cross-sectional study

Background

Acute respiratory syndrome due to coronavirus 2 (SARS-CoV-2) is characterised by heterogeneous levels of disease severity. It is not necessarily apparent whether a patient will develop a severe disease or not. This cross-sectional study explores whether acoustic properties of the cough sound of patients with coronavirus disease (COVID-19), the illness caused by SARS-CoV-2, correlate with their disease and pneumonia severity, with the aim of identifying patients with a severe disease.

Methods

Voluntary cough sounds were recorded using a smartphone in 70 COVID-19 patients within the first 24 h of their hospital arrival, between April 2020 and May 2021. Based on gas exchange abnormalities, patients were classified as mild, moderate, or severe. Time- and frequency-based variables were obtained from each cough effort and analysed using a linear mixed-effects modelling approach.

Results

Records from 62 patients (37% female) were eligible for inclusion in the analysis, with mild, moderate, and severe groups consisting of 31, 14 and 17 patients respectively. 5 of the parameters examined were found to be significantly different in the cough of patients at different disease levels of severity, with a further 2 parameters found to be affected differently by the disease severity in men and women.

Conclusions

We suggest that all these differences reflect the progressive pathophysiological alterations occurring in the respiratory system of COVID-19 patients, and potentially would provide an easy and cost-effective way to initially stratify patients, identifying those with more severe disease, and thereby most effectively allocate healthcare resources.

Chest X-ray-based opportunistic screening of sarcopenia using deep learning

BACKGROUND

Early detection and management of sarcopenia is of clinical importance. We aimed to develop a chest X-ray-based deep learning model to predict presence of sarcopenia.

METHODS

Data of participants who visited osteoporosis clinic at Severance Hospital, Seoul, South Korea, between January 2020 and June 2021 were used as derivation cohort as split to train, validation and test set (65:15:20). A community-based older adults cohort (KURE) was used as external test set. Sarcopenia was defined based on Asian Working Group 2019 guideline. A deep learning model was trained to predict appendicular lean mass (ALM), handgrip strength (HGS) and chair rise test performance from chest X-ray images; then the machine learning model (SARC-CXR score) was built using the age, sex, body mass index and chest X-ray predicted muscle parameters along with estimation uncertainty values.

RESULTS

Mean age of the derivation cohort (n = 926; women n = 700, 76%; sarcopenia n = 141, 15%) and the external test (n = 149; women n = 95, 64%; sarcopenia n = 18, 12%) cohort was 61.4 and 71.6 years, respectively. In the internal test set (a hold-out set, n = 189, from the derivation cohort) and the external test set (n = 149), the concordance correlation coefficient for ALM prediction was 0.80 and 0.76, with an average difference of 0.18 ± 2.71 and 0.21 ± 2.28, respectively. Gradient-weight class activation mapping for deep neural network models to predict ALM and HGS commonly showed highly weight pixel values at bilateral lung fields and part of the cardiac contour. SARC-CXR score showed good discriminatory performance for sarcopenia in both internal test set [area under the receiver-operating characteristics curve (AUROC) 0.813, area under the precision-recall curve (AUPRC) 0.380, sensitivity 0.844, specificity 0.739, F1-score 0.540] and external test set (AUROC 0.780, AUPRC 0.440, sensitivity 0.611, specificity 0.855, F1-score 0.458). Among SARC-CXR model features, predicted low ALM from chest X-ray was the most important predictor of sarcopenia based on SHapley Additive exPlanations values. Higher estimation uncertainty of HGS contributed to elevate the predicted risk of sarcopenia. In internal test set, SARC-CXR score showed better discriminatory performance than SARC-F score (AUROC 0.813 vs. 0.691, P = 0.029).

CONCLUSIONS

Chest X-ray-based deep leaning model improved detection of sarcopenia, which merits further investigation.

Minimal reporting improvement after peer review in reports of COVID-19 prediction models: systematic review

OBJECTIVES

To assess improvement in the completeness of reporting coronavirus (COVID-19) prediction models after the peer review process.

STUDY DESIGN AND SETTING

Studies included in a living systematic review of COVID-19 prediction models, with both preprint and peer-reviewed published versions available, were assessed. The primary outcome was the change in percentage adherence to the transparent reporting of a multivariable prediction model for individual prognosis or diagnosis (TRIPOD) reporting guidelines between pre-print and published manuscripts.

RESULTS

Nineteen studies were identified including seven (37%) model development studies, two external validations of existing models (11%), and 10 (53%) papers reporting on both development and external validation of the same model. Median percentage adherence among preprint versions was 33% (min-max: 10 to 68%). The percentage adherence of TRIPOD components increased from preprint to publication in 11/19 studies (58%), with adherence unchanged in the remaining eight studies. The median change in adherence was just 3 percentage points (pp, min-max: 0-14 pp) across all studies. No association was observed between the change in percentage adherence and preprint score, journal impact factor, or time between journal submission and acceptance.

CONCLUSIONS

The preprint reporting quality of COVID-19 prediction modeling studies is poor and did not improve much after peer review, suggesting peer review had a trivial effect on the completeness of reporting during the pandemic.

A multidimensional approach to older patients during COVID-19 pandemic: a position paper of the Special Interest Group on Comprehensive Geriatric Assessment of the European Geriatric Medicine Society (EuGMS)

PURPOSE

The COVID-19 pandemic has been a dramatic trigger that has challenged the intrinsic capacity of older adults and of society. Due to the consequences for the older population worldwide, the Special Interest Group on Comprehensive Geriatric Assessment (CGA) of the European Geriatric Medicine Society (EuGMS) took the initiative of collecting evidence on the usefulness of the CGA-based multidimensional approach to older people during the COVID-19 pandemic.

METHODS

A narrative review of the most relevant articles published between January 2020 and November 2022 that focused on the multidimensional assessment of older adults during the COVID-19 pandemic.

RESULTS

Current evidence supports the critical role of the multidimensional approach to identify older adults hospitalized with COVID-19 at higher risk of longer hospitalization, functional decline, and short-term mortality. This approach appears to also be pivotal for the adequate stratification and management of the post-COVID condition as well as for the adoption of preventive measures (e.g., vaccinations, healthy lifestyle) among non-infected individuals.

CONCLUSION

Collecting information on multiple health domains (e.g., functional, cognitive, nutritional, social status, mobility, comorbidities, and polypharmacy) provides a better understanding of the intrinsic capacities and resilience of older adults affected by SARS-CoV-2 infection. The EuGMS SIG on CGA endorses the adoption of the multidimensional approach to guide the clinical management of older adults during the COVID-19 pandemic.

Deep Learning-Based Time-to-Death Prediction Model for COVID-19 Patients Using Clinical Data and Chest Radiographs

Accurate estimation of mortality and time to death at admission for COVID-19 patients is important and several deep learning models have been created for this task. However, there are currently no prognostic models which use end-to-end deep learning to predict time to event for admitted COVID-19 patients using chest radiographs and clinical data. We retrospectively implemented a new artificial intelligence model combining DeepSurv (a multiple-perceptron implementation of the Cox proportional hazards model) and a convolutional neural network (CNN) using 1356 COVID-19 inpatients. For comparison, we also prepared DeepSurv only with clinical data, DeepSurv only with images (CNNSurv), and Cox proportional hazards models. Clinical data and chest radiographs at admission were used to estimate patient outcome (death or discharge) and duration to the outcome. The Harrel's concordance index (c-index) of the DeepSurv with CNN model was 0.82 (0.75-0.88) and this was significantly higher than the DeepSurv only with clinical data model (c-index = 0.77 (0.69-0.84), p = 0.011), CNNSurv (c-index = 0.70 (0.63-0.79), p = 0.001), and the Cox proportional hazards model (c-index = 0.71 (0.63-0.79), p = 0.001). These results suggest that the time-to-event prognosis model became more accurate when chest radiographs and clinical data were used together.

Real-World Practice of Gastric Cancer Prevention and Screening Calls for Practical Prediction Models

INTRODUCTION

Some gastric cancer prediction models have been published. Still, the value of these models for application in real-world practice remains unclear. We aim to summarize and appraise modeling studies for gastric cancer risk prediction and identify potential barriers to real-world use.

METHODS

This systematic review included studies that developed or validated gastric cancer prediction models in the general population.

RESULTS

A total of 4,223 studies were screened. We included 18 development studies for diagnostic models, 10 for prognostic models, and 1 external validation study. Diagnostic models commonly included biomarkers, such as Helicobacter pylori infection indicator, pepsinogen, hormone, and microRNA. Age, sex, smoking, body mass index, and family history of gastric cancer were frequently used in prognostic models. Most of the models were not validated. Only 25% of models evaluated the calibration. All studies had a high risk of bias, but over half had acceptable applicability. Besides, most studies failed to clearly report the application scenarios of prediction models.

DISCUSSION

Most gastric cancer prediction models showed common shortcomings in methods, validation, and reports. Model developers should further minimize the risk of bias, improve models' applicability, and report targeting application scenarios to promote real-world use.

Systematic review identifies the design and methodological conduct of studies on machine learning-based prediction models

BACKGROUND AND OBJECTIVES

We sought to summarize the study design, modelling strategies, and performance measures reported in studies on clinical prediction models developed using machine learning techniques.

METHODS

We search PubMed for articles published between 01/01/2018 and 31/12/2019, describing the development or the development with external validation of a multivariable prediction model using any supervised machine learning technique. No restrictions were made based on study design, data source, or predicted patient-related health outcomes.

RESULTS

We included 152 studies, 58 (38.2% [95% CI 30.8-46.1]) were diagnostic and 94 (61.8% [95% CI 53.9-69.2]) prognostic studies. Most studies reported only the development of prediction models (n = 133, 87.5% [95% CI 81.3-91.8]), focused on binary outcomes (n = 131, 86.2% [95% CI 79.8-90.8), and did not report a sample size calculation (n = 125, 82.2% [95% CI 75.4-87.5]). The most common algorithms used were support vector machine (n = 86/522, 16.5% [95% CI 13.5-19.9]) and random forest (n = 73/522, 14% [95% CI 11.3-17.2]). Values for area under the Receiver Operating Characteristic curve ranged from 0.45 to 1.00. Calibration metrics were often missed (n = 494/522, 94.6% [95% CI 92.4-96.3]).

CONCLUSION

Our review revealed that focus is required on handling of missing values, methods for internal validation, and reporting of calibration to improve the methodological conduct of studies on machine learning-based prediction models.

SYSTEMATIC REVIEW REGISTRATION

PROSPERO, CRD42019161764.

[Performance in prognostic capacity and efficiency of the Thoracic Care Suite GE AI tool applied to chest radiography of patients with COVID-19 pneumonia]

OBJECTIVE

Rapid progression of COVID-19 pneumonia may put patients at risk of requiring ventilatory support, such as non-invasive mechanical ventilation or endotracheal intubation. Implementing tools that detect COVID-19 pneumonia can improve the patient's healthcare. We aim to evaluate the efficacy and efficiency of the artificial intelligence (AI) tool GE Healthcare's Thoracic Care Suite (featuring Lunit INSIGHT CXR, TCS) to predict the ventilatory support need based on pneumonic progression of COVID-19 on consecutive chest X-rays.

METHODS

Outpatients with confirmed SARS-CoV-2 infection, with chest X-ray (CXR) findings probable or indeterminate for COVID-19 pneumonia, who required a second CXR due to unfavorable clinical course, were collected. The number of affected lung fields for the two CXRs was assessed using the AI tool.

RESULTS

One hundred fourteen patients (57.4 ± 14.2 years, 65 -57%- men) were retrospectively collected. Fifteen (13.2%) required ventilatory support. Progression of pneumonic extension ≥ 0.5 lung fields per day compared to pneumonia onset, detected using the TCS tool, increased the risk of requiring ventilatory support by 4-fold. Analyzing the AI output required 26 seconds of radiological time.

CONCLUSIONS

Applying the AI tool, Thoracic Care Suite, to CXR of patients with COVID-19 pneumonia allows us to anticipate ventilatory support requirements requiring less than half a minute.

Influence of social deprivation index on in-hospital outcomes of COVID-19

While it is known that social deprivation index (SDI) plays an important role on risk for acquiring Coronavirus Disease 2019 (COVID-19), the impact of SDI on in-hospital outcomes such as intubation and mortality are less well-characterized. We analyzed electronic health record data of adults hospitalized with confirmed COVID-19 between March 1, 2020 and February 8, 2021 from the INSIGHT Clinical Research Network (CRN). To compute the SDI (exposure variable), we linked clinical data using patient's residential zip-code with social data at zip-code tabulation area. SDI is a composite of seven socioeconomic characteristics determinants at the zip-code level. For this analysis, we categorized SDI into quintiles. The two outcomes of interest were in-hospital intubation and mortality. For each outcome, we examined logistic regression and random forests to determine incremental value of SDI in predicting outcomes. We studied 30,016 included COVID-19 patients. In a logistic regression model for intubation, a model including demographics, comorbidity, and vitals had an Area under the receiver operating characteristic curve (AUROC) = 0.73 (95% CI 0.70-0.75); the addition of SDI did not improve prediction [AUROC = 0.73 (95% CI 0.71-0.75)]. In a logistic regression model for in-hospital mortality, demographics, comorbidity, and vitals had an AUROC = 0.80 (95% CI 0.79-0.82); the addition of SDI in Model 2 did not improve prediction [AUROC = 0.81 (95% CI 0.79-0.82)]. Random forests revealed similar findings. SDI did not provide incremental improvement in predicting in-hospital intubation or mortality. SDI plays an important role on who acquires COVID-19 and its severity; but once hospitalized, SDI appears less important.

Impedimetric Sensing: An Emerging Tool for Combating the COVID-19 Pandemic

The COVID-19 pandemic revealed a pressing need for the development of sensitive and low-cost point-of-care sensors for disease diagnosis. The current standard of care for COVID-19 is quantitative reverse transcriptase polymerase chain reaction (qRT-PCR). This method is sensitive, but takes time, effort, and requires specialized equipment and reagents to be performed correctly. This make it unsuitable for widespread, rapid testing and causes poor individual and policy decision-making. Rapid antigen tests (RATs) are a widely used alternative that provide results quickly but have low sensitivity and are prone to false negatives, particularly in cases with lower viral burden. Electrochemical sensors have shown much promise in filling this technology gap, and impedance spectroscopy specifically has exciting potential in rapid screening of COVID-19. Due to the data-rich nature of impedance measurements performed at different frequencies, this method lends itself to machine-leaning (ML) algorithms for further data processing. This review summarizes the current state of impedance spectroscopy-based point-of-care sensors for the detection of the SARS-CoV-2 virus. This article also suggests future directions to address the technology's current limitations to move forward in this current pandemic and prepare for future outbreaks.

[Validation of the COVID-19-12O scale for predicting readmissions/revisits in patients with SARS-CoV-2 pneumonia discharged from the emergency department]

OBJECTIVE

The COVID-19-12O scale has been validated for determining the risk of respiratory failure in patients hospitalized due to COVID-19. This study aims to assess whether the scale is effective for predicting readmissions and revisits in patients with SARS-CoV-2 pneumonia discharged from a hospital emergency department (HED).

METHOD

This work is a retrospective cohort of consecutive patients with SARS-CoV-2 pneumonia discharged from the HED of a tertiary hospital from January 7 to February 17, 2021. The COVID-19-12O scale with a cut-off point of nine points was used to define the risk of admissions or revisits. The primary outcome variable was a revisit with or without hospital readmission after 30 days of discharge from the HED.

RESULTS

Seventy-seven patients were included. The median age was 59 years, 63.6% were men, and the Charlson Comorbidity Index was 2. A total of 9.1% had an emergency room revisit and 15.3% had a deferred hospital admission. The relative risk (RR) for an HED revisit was 0.46 (0.04-4.62, 95% CI p=0.452) and the RR for hospital readmission was 6.88 (1.20-39.49, 95% CI, p<0.005).

CONCLUSIONS

The COVID-19-12O scale is effective in determining the risk of hospital readmission in patients discharged from an HED with SARS-CoV-2 pneumonia, but is not useful for assessing the risk of revisit.

The prognostic value of the Barthel Index for mortality in patients with COVID-19: A cross-sectional study

Objective

This study aimed to analyze the association between the activity of daily living (ADL), coronavirus disease (COVID-19), and the value of the Barthel Index in predicting the prognosis of patients.

Methods

This study included 398 patients with COVID-19, whose ADL at admission to hospital were assessed with the Barthel Index. The relationship between the index and the mortality risk of the patients was analyzed. Several regression models and a decision tree were established to evaluate the prognostic value of the index in COVID-19 patients.

Results

The Barthel Index scores of deceased patients were significantly lower than that of discharged patients (median: 65 vs. 90, P < 0.001), and its decrease indicated an increased risk of mortality in patients (P < 0.001). After adjusting models for age, gender, temperature, pulse, respiratory rate, mean arterial pressure, oxygen saturation, etc., the Barthel Index could still independently predict prognosis (OR = 0.809; 95% CI: 0.750-0.872). The decision tree showed that patients with a Barthel Index of below 70 had a higher mortality rate (33.3-40.0%), while those above 90 were usually discharged (mortality: 2.7-7.2%).

Conclusion

The Barthel Index is of prognostic value for mortality in COVID-19 patients. According to their Barthel Index, COVID-19 patients can be divided into emergency, observation, and normal groups (0-70; 70-90; 90-100), with different treatment strategies.

Finite Element Analysis Model of Electronic Skin Based on Surface Acoustic Wave Sensor

In recent years, with the rapid development of flexible electronic devices, researchers have a great interest in the research of electronic skin (e-skin). Traditional e-skin, which is made of rigid integrated circuit chips, not only limits the overall flexibility, but also consumes a lot of power and poses certain security risks to the human body. In this paper, a wireless passive e-skin is designed based on the surface acoustic wave sensor (SAWS) of lithium niobate piezoelectric film. The e-skin has the advantages of small size, high precision, low power consumption, and good flexibility. With the multi-sensing function of stress, temperature, and sweat ion concentration, etc., the newly designed e-skin is a sensor platform for a wide range of external stimuli, and the measurement results can be directly presented in frequency. In order to explore the characteristic parameters and various application scenarios of the SAWS, finite element analysis is carried out using the simulation software; the relationship between the SAWS and various influencing factors is explored, and the related performance curve is obtained. These simulation results provide important reference and experimental guidance for the design and preparation of SAW e-skin.

The predictive markers of severity and mortality in hospitalized hemodialysis patients with COVID-19 during Omicron epidemic

INTRODUCTION

Predictive markers and prognosis remain unclear in hospitalized hemodialysis (HD) patients with coronavirus disease 2019 (COVID-19) during the Omicron epidemic.

METHODS

We evaluated characteristics, laboratory parameters, and outcomes in hospitalized HD patients with COVID-19 (n = 102) at two centers between January and April 2022.

RESULTS

The 30-day mortality rate was higher in moderate-critical group (n = 43) than mild group (n = 59) (16.3% vs. 1.7%; p = 0.007), and higher in patients with lower CC chemokine ligand 17 (CCL17) levels (<95.0 pg/mL) compared with normal CCL17 levels (19.0% versus 4.9%; p = 0.03). In multivariate analyses, a low CCL17 level (p = 0.003) was associated with moderate-critical conditions, and moderate-critical conditions (p = 0.04) were associated with 30-day mortality, whereas CCL17 was not associated with 30-day mortality.

CONCLUSIONS

COVID-19 remains a fatal complication, and CCL17 was a predictive marker of severity in hospitalized HD patients during the Omicron epidemic.

Rationing scarce healthcare capacity: A study of the ventilator allocation guidelines during the COVID-19 pandemic

In the United States, even though national guidelines for allocating scarce healthcare resources are lacking, 26 states have specific ventilator allocation guidelines to be invoked in case of a shortage. While several states developed their guidelines in response to the recent COVID-19 pandemic, New York State developed these guidelines in 2015 as "pandemic influenza is a foreseeable threat, one that we cannot ignore." The primary objective of this study is to assess the existing procedures and priority rules in place for allocating/rationing scarce ventilator capacity and propose alternative (and improved) priority schemes. We first build machine learning models using inpatient records of COVID-19 patients admitted to New York-Presbyterian/Columbia University Irving Medical Center and an affiliated community health center to predict survival probabilities as well as ventilator length-of-use. Then, we use the resulting point estimators and their uncertainties as inputs for a multiclass priority queueing model with abandonments to assess three priority schemes: (i) SOFA-P (Sequential Organ Failure Assessment based prioritization), which most closely mimics the existing practice by prioritizing patients with sufficiently low SOFA scores; (ii) ISP (incremental survival probability), which assigns priority based on patient-level survival predictions; and (iii) ISP-LU (incremental survival probability per length-of-use), which takes into account survival predictions and resource use duration. Our findings highlight that our proposed priority scheme, ISP-LU, achieves a demonstrable improvement over the other two alternatives. Specifically, the expected number of survivals increases and death risk while waiting for ventilator use decreases. We also show that ISP-LU is a robust priority scheme whose implementation yields a Pareto-improvement over both SOFA-P and ISP in terms of maximizing saved lives after mechanical ventilation while limiting racial disparity in access to the priority queue.

Assessment of Clinical Indicators Registered on Admission to the Hospital Related to Mortality Risk in Cancer Patients with COVID-19

BACKGROUND

Oncology patients are a particularly vulnerable group to the severe course of COVID-19 due to, e.g., the suppression of the immune system. The study aimed to find links between parameters registered on admission to the hospital and the risk of later death in cancer patients with COVID-19.

METHODS

The study included patients with a reported history of malignant tumor (n = 151) and a control group with no history of cancer (n = 151) hospitalized due to COVID-19 between March 2020 and August 2021. The variables registered on admission were divided into categories for which we calculated the multivariate Cox proportional hazards models.

RESULTS

Multivariate Cox proportional hazards models were successfully obtained for the following categories: Patient data, Comorbidities, Signs recorded on admission, Medications used before hospitalization and Laboratory results recorded on admission. With the models developed for oncology patients, we identified the following variables that registered on patients' admission were linked to significantly increased risk of death. They are: male sex, presence of metastases in neoplastic disease, impaired consciousness (somnolence or confusion), wheezes/rhonchi, the levels of white blood cells and neutrophils.

CONCLUSION

Early identification of the indicators of a poorer prognosis may serve clinicians in better tailoring surveillance or treatment among cancer patients with COVID-19.

Validation of the RIM Score-COVID in the Spanish SEMI-COVID-19 Registry

The significant impact of COVID-19 worldwide has made it necessary to develop tools to identify patients at high risk of severe disease and death. This work aims to validate the RIM Score-COVID in the SEMI-COVID-19 Registry. The RIM Score-COVID is a simple nomogram with high predictive capacity for in-hospital death due to COVID-19 designed using clinical and analytical parameters of patients diagnosed in the first wave of the pandemic. The nomogram uses five variables measured on arrival to the emergency department (ED): age, sex, oxygen saturation, C-reactive protein level, and neutrophil-to-platelet ratio. Validation was performed in the Spanish SEMI-COVID-19 Registry, which included consecutive patients hospitalized with confirmed COVID-19 in Spain. The cohort was divided into three time periods: T1 from February 1 to June 10, 2020 (first wave), T2 from June 11 to December 31, 2020 (second wave, pre-vaccination period), and T3 from January 1 to December 5, 2021 (vaccination period). The model's accuracy in predicting in-hospital COVID-19 mortality was assessed using the area under the receiver operating characteristics curve (AUROC). Clinical and laboratory data from 22,566 patients were analyzed: 15,976 (70.7%) from T1, 4,233 (18.7%) from T2, and 2,357 from T3 (10.4%). AUROC of the RIM Score-COVID in the entire SEMI-COVID-19 Registry was 0.823 (95%CI 0.819-0.827) and was 0.834 (95%CI 0.830-0.839) in T1, 0.792 (95%CI 0.781-0.803) in T2, and 0.799 (95%CI 0.785-0.813) in T3. The RIM Score-COVID is a simple, easy-to-use method for predicting in-hospital COVID-19 mortality that uses parameters measured in most EDs. This tool showed good predictive ability in successive disease waves.

A 178-clinical-center experiment of integrating AI solutions for lung pathology diagnosis

In 2020, an experiment testing AI solutions for lung X-ray analysis on a multi-hospital network was conducted. The multi-hospital network linked 178 Moscow state healthcare centers, where all chest X-rays from the network were redirected to a research facility, analyzed with AI, and returned to the centers. The experiment was formulated as a public competition with monetary awards for participating industrial and research teams. The task was to perform the binary detection of abnormalities from chest X-rays. For the objective real-life evaluation, no training X-rays were provided to the participants. This paper presents one of the top-performing AI frameworks from this experiment. First, the framework used two EfficientNets, histograms of gradients, Haar feature ensembles, and local binary patterns to recognize whether an input image represents an acceptable lung X-ray sample, meaning the X-ray is not grayscale inverted, is a frontal chest X-ray, and completely captures both lung fields. Second, the framework extracted the region with lung fields and then passed them to a multi-head DenseNet, where the heads recognized the patient's gender, age and the potential presence of abnormalities, and generated the heatmap with the abnormality regions highlighted. During one month of the experiment from 11.23.2020 to 12.25.2020, 17,888 cases have been analyzed by the framework with 11,902 cases having radiological reports with the reference diagnoses that were unequivocally parsed by the experiment organizers. The performance measured in terms of the area under receiving operator curve (AUC) was 0.77. The AUC for individual diseases ranged from 0.55 for herniation to 0.90 for pneumothorax.

Prediction Models for Tinnitus Presence and the Impact of Tinnitus on Daily Life: A Systematic Review

The presence of tinnitus does not necessarily imply associated suffering. Prediction models on the impact of tinnitus on daily life could aid medical professionals to direct specific medical resources to those (groups of) tinnitus patients with specific levels of impact. Models of tinnitus presence could possibly identify risk factors for tinnitus. We systematically searched the PubMed and EMBASE databases for articles published up to January 2021. We included all studies that reported on multivariable prediction models for tinnitus presence or the impact of tinnitus on daily life. Twenty-one development studies were included, with a total of 31 prediction models. Seventeen studies made a prediction model for the impact of tinnitus on daily life, three studies made a prediction model for tinnitus presence and one study made models for both. The risk of bias was high and reporting was poor in all studies. The most used predictors in the final impact on daily life models were depression- or anxiety-associated questionnaire scores. Demographic predictors were most common in final presence models. No models were internally or externally validated. All published prediction models were poorly reported and had a high risk of bias. This hinders the usability of the current prediction models. Methodological guidance is available for the development and validation of prediction models. Researchers should consider the importance and clinical relevance of the models they develop and should consider validation of existing models before developing new ones.

Lethality risk markers by sex and age-group for COVID-19 in Mexico: a cross-sectional study based on machine learning approach

BACKGROUND

Mexico ranks fifth worldwide in the number of deaths due to COVID-19. Identifying risk markers through easily accessible clinical data could help in the initial triage of COVID-19 patients and anticipate a fatal outcome, especially in the most socioeconomically disadvantaged regions. This study aims to identify markers that increase lethality risk in patients diagnosed with COVID-19, based on machine learning (ML) methods. Markers were differentiated by sex and age-group.

METHODS

A total of 11,564 cases of COVID-19 in Mexico were extracted from the Epidemiological Surveillance System for Viral Respiratory Disease. Four ML classification methods were trained to predict lethality, and an interpretability approach was used to identify those markers.

RESULTS

Models based on Extreme Gradient Boosting (XGBoost) yielded the best performance in a test set. This model achieved a sensitivity of 0.91, a specificity of 0.69, a positive predictive value of 0.344, and a negative predictive value of 0.965. For female patients, the leading markers are diabetes and arthralgia. For males, the main markers are chronic kidney disease (CKD) and chest pain. Dyspnea, hypertension, and polypnea increased the risk of death in both sexes.

CONCLUSIONS

ML-based models using an interpretability approach successfully identified risk markers for lethality by sex and age. Our results indicate that age is the strongest demographic factor for a fatal outcome, while all other markers were consistent with previous clinical trials conducted in a Mexican population. The markers identified here could be used as an initial triage, especially in geographic areas with limited resources.

Older People Hospitalized for COVID-19: Prognostic Role of Multidimensional Prognostic Index and Other Prognostic Scores

During the SARS-CoV-2 pandemic, frailty and patients’ poor outcomes seem to be closely related. However, there is no clear indication of the significance of this connection and the most adequate risk index in clinical practice. In this study, we compared a short version of MPI (multidimensional prognostic index) and other two prognostic scores for COVID-19 as potential predictors of poor patient outcomes. The patients were consecutively enrolled in the hospital of Palermo for COVID-19. The accuracy of Brief-MPI, 4C score and COVID-GRAM score in points was evaluated using the area under the curve (AUC) with 95% CI, taking mortality or sub-ICU admission as outcome. The study included 112 participants (mean age 77.6, 55.4% males). During a mean of 16 days of hospitalization, Brief-MPI significantly increased by 0.03 ± 0.14 (p = 0.04), whilst COVID-GRAM did not. Brief-MPI, 4C score and COVID-GRAM scores had good accuracy in predicting negative outcomes (AUC > 0.70 for all three scores). Brief-MPI was significantly associated with an increased mortality/ICU admission risk, indicating the importance of multidimensional impairment in clinical decision-making with an accuracy similar to other prognostic scores commonly used in COVID-19 study, providing information regarding domains for which interventions can be proposed.

Correlates of Coronavirus Disease 2019 Inpatient Mortality at a Southern California Community Hospital With a Predominantly Hispanic/Latino Adult Population

Background

Studies of inpatient coronavirus disease 2019 (COVID-19) mortality risk factors have mainly used data from academic medical centers or large multihospital databases and have not examined populations with large proportions of Hispanic/Latino patients. In a retrospective cohort study of 4881 consecutive adult COVID-19 hospitalizations at a single community hospital in Los Angeles County with a majority Hispanic/Latino population, we evaluated factors associated with mortality.

Methods

Data on demographic characteristics, comorbidities, laboratory and clinical results, and COVID-19 therapeutics were abstracted from the electronic medical record. Cox proportional hazards regression modeled statistically significant, independently associated predictors of hospital mortality.

Results

Age ≥65 years (hazard ratio [HR] = 2.66; 95% confidence interval [CI] = 1.90-3.72), male sex (HR = 1.31; 95% CI = 1.07-1.60), renal disease (HR = 1.52; 95% CI = 1.18-1.95), cardiovascular disease (HR = 1.45; 95% CI = 1.18-1.78), neurological disease (HR = 1.84; 95% CI = 1.41-2.39), D-dimer ≥500 ng/mL (HR = 2.07; 95% CI = 1.43-3.0), and pulse oxygen level <88% (HR = 1.39; 95% CI = 1.13-1.71) were independently associated with increased mortality. Patient household with (1) multiple COVID-19 cases and (2) Asian, Black, or Hispanic compared with White non-Hispanic race/ethnicity were associated with reduced mortality. In hypoxic COVID-19 inpatients, remdesivir, tocilizumab, and convalescent plasma were associated with reduced mortality, and corticosteroid use was associated with increased mortality.

Conclusions

We corroborate several previously identified mortality risk factors and find evidence that the combination of factors associated with mortality differ between populations.

Institutional Strategies to Maintain and Grow Imaging Research During the COVID-19 Pandemic

Understanding imaging research experiences, challenges, and strategies for academic radiology departments during and after COVID-19 is critical to prepare for future disruptive events. We summarize key insights and programmatic initiatives at major academic hospitals across the world, based on literature review and meetings of the Radiological Society of North America Vice Chairs of Research (RSNA VCR) group. Through expert discussion and case studies, we provide suggested guidelines to maintain and grow radiology research in the postpandemic era.

Systematic Review of Advanced AI Methods for Improving Healthcare Data Quality in Post COVID-19 Era

At the beginning of the COVID-19 pandemic, there was significant hype about the potential impact of artificial intelligence (AI) tools in combatting COVID-19 on diagnosis, prognosis, or surveillance. However, AI tools have not yet been widely successful. One of the key reason is the COVID-19 pandemic has demanded faster real-time development of AI-driven clinical and health support tools, including rapid data collection, algorithm development, validation, and deployment. However, there was not enough time for proper data quality control. Learning from the hard lessons in COVID-19, we summarize the important health data quality challenges during COVID-19 pandemic such as lack of data standardization, missing data, tabulation errors, and noise and artifact. Then we conduct a systematic investigation of computational methods that address these issues, including emerging novel advanced AI data quality control methods that achieve better data quality outcomes and, in some cases, simplify or automate the data cleaning process. We hope this article can assist healthcare community to improve health data quality going forward with novel AI development.

A snake venom-analog peptide that inhibits SARS-CoV-2 and papain-like protease displays antithrombotic activity in mice arterial thrombosis model, without interfering with bleeding time

BACKGROUND

(p-BthTX-I)₂ K, a dimeric analog peptide derived from the C-terminal region of phospholipase A2-like bothropstoxin-I (p-BthTX-I), is resistant to plasma proteolysis and inhibits severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) strains with weak cytotoxic effects. Complications of SARS-CoV-2 infection include vascular problems and increased risk of thrombosis; therefore, studies to identify new drugs for treating SARS-CoV-2 infections that also inhibit thrombosis and minimize the risk of bleeding are required.

OBJECTIVES

To determine whether (p-BthTX-I)₂ K affects the hemostatic system.

METHODS

Platelet aggregation was induced by collagen, arachidonic acid, and adenosine diphosphate (ADP) in the Chronolog Lumi-aggregometer. The coagulation activity was evaluated by determining activated partial thromboplastin clotting time (aPTT) and prothrombin time (PT) with (p-BthTX-I)₂ K (5.0-434.5 µg) or 0.9% NaCl. Arterial thrombosis was induced with a 540 nm laser and 3.5-20 mg kg^- 1 Rose Bengal in the carotid artery of male C57BL/6J mice using (p-BthTX-I)₂ K. Bleeding time was determined in mouse tails immersed in saline at 37 °C after (p-BthTX-I)₂ K (4.0 mg/kg and 8.0 mg/kg) or saline administration.

RESULTS

(p-BthTX-I)₂ K prolonged the aPTT and PT by blocking kallikrein and FXa-like activities. Moreover, (p-BthTX-I)₂ K inhibited ADP-, collagen-, and arachidonic acid-induced platelet aggregation in a dose-dependent manner. Further, low concentrations of (p-BthTX-I)₂ K extended the time to artery occlusion by the formed thrombus. However, (p-BthTX-I)₂ K did not prolong the bleeding time in the mouse model of arterial thrombosis.

CONCLUSION

These results demonstrate the antithrombotic activity of the peptide (p-BthTX-I)₂ K possibly by kallikrein inhibition, suggesting its strong biotechnological potential.

An IoT-enabled smart health care system for screening of COVID-19 with multi layers features fusion and selection

Advancement of smart medical sensors, devices, cloud computing, and health care technologies is getting remarkable attention from academia and the health care industry. As, Internet of things (IoT) has been recognized as one of the promising research topics in the domain of health care, particularly in medical image processing. Researchers utilized various machine and deep learning techniques along with artificial intelligence for analyzing medical images. These developed techniques are used to detect diseases that might assist medical experts in diagnosing diseases at early stages and providing accurate, consistent, effective, and speedy results, and decrease the mortality rate. Nowadays, Coronavirus (COVID-19) has been growing as one of the most rigorous and severe infections and spreading globally. Consequently, an intelligent automated system is required as an active diagnostic choice that might be used to prevent the spread of COVID-19. Thus, this work presented an IoT-enabled smart health care system for the automatic screening and classification of contagious diseases (Pneumonia, COVID-19) in Chest X-ray images. The developed system is based on two different deep learning architectures used with a multi-layers feature fusion and feature selection approach to classify X-ray images of infectious diseases. This work comprises the following steps: to enhance the diversity of the data set, data augmentation is performed, while for feature extraction, deep learning architectures, i.e., VGG-19 and Inception-V3, are used along with transfer learning. For the fusion of extracted features obtained from deep learning architectures, a parallel maximum covariance, and for feature selection, the multi-logistic regression controlled entropy variance approach is applied. For experimentation, a data set is customized containing Chest X-ray images using various publicly available resources. The system provides an overall classification accuracy of 97%.

Characteristics and Outcomes by Ceiling of Care of Subjects Hospitalized with COVID-19 During Four Waves of the Pandemic in a Metropolitan Area: A Multicenter Cohort Study

INTRODUCTION

The profiles of patients with COVID-19 have been widely studied, but little is known about differences in baseline characteristics and in outcomes between subjects with a ceiling of care assigned at hospital admission and subjects without a ceiling of care. The aim of this study is to compare, by ceiling of care, clinical features and outcomes of hospitalized subjects during four waves of COVID-19 in a metropolitan area in Catalonia.

METHODS

Observational study conducted during the first (March-April 2020), second (October-November 2020), third (January-February 2021), and fourth wave (July-August 2021) of COVID-19 in five centers of Catalonia. All subjects were adults (> 18 years old) hospitalized with a proven SARS-CoV-2 infection and with therapeutic ceiling of care assessed by the attending physician at hospital admission.

RESULTS

A total of 5813 subjects were analyzed. Subjects with a ceiling of care were mainly older (difference in median age of 20 years), with more comorbidities (Charlson index 3 points higher) and with fewer clinical signs at baseline than patients without a ceiling of care. Some features of their clinical profiles changed among waves. There were differences in treatments received during hospital admission across waves, but not between subjects with and without a ceiling of care. Subjects with a ceiling of care had a death incidence more than four times the death incidence of subjects a without a ceiling of care (risk ratio (RR) ranging from 3.5 in the first wave to almost 6 in the third and fourth). Incidence of severe pneumonia and complications for subjects with a ceiling of care was around 1.5 times the incidence in subjects without a ceiling of care.

DISCUSSION

Analysis of hospitalized subjects with SARS-CoV-2 infection should be stratified according to therapeutic ceiling of care to avoid bias and outcome misestimation.

Construction and validation of a deterioration model for elderly COVID-19 Sub-variant BA.2 patients

Rationale

COVID-19 pandemic has imposed tremendous stress and burden on the economy and society worldwide. There is an urgent demand to find a new model to estimate the deterioration of patients inflicted by Omicron variants.

Objective

This study aims to develop a model to predict the deterioration of elderly patients inflicted by Omicron Sub-variant BA.2.

Methods

COVID-19 patients were randomly divided into the training and the validation cohorts. Both Lasso and Logistic regression analyses were performed to identify prediction factors, which were then selected to build a deterioration model in the training cohort. This model was validated in the validation cohort.

Measurements and main results

The deterioration model of COVID-19 was constructed with five indices, including C-reactive protein, neutrophil count/lymphocyte count (NLR), albumin/globulin ratio (A/G), international normalized ratio (INR), and blood urea nitrogen (BUN). The area under the ROC curve (AUC) showed that this model displayed a high accuracy in predicting deterioration, which was 0.85 in the training cohort and 0.85 in the validation cohort. The nomogram provided an easy way to calculate the possibility of deterioration, and the decision curve analysis (DCA) and clinical impact curve analysis (CICA)showed good clinical net profit using this model.

Conclusion

The model we constructed can identify and predict the risk of deterioration (requirement for ventilatory support or death) in elderly patients and it is clinically practical, which will facilitate medical decision making and allocating medical resources to those with critical conditions.

Guidelines for Triage of COVID-19 Patients Presenting With Multisystemic Symptoms

BACKGROUND AND OBJECTIVES

This article describes how multisystemic symptoms, both respiratory and nonrespiratory, can be used to differentiate coronavirus disease-2019 (COVID-19) from other diseases at the point of patient triage in the community. The article also shows how combinations of symptoms could be used to predict the probability of a patient having COVID-19.

METHODS

We first used a scoping literature review to identify symptoms of COVID-19 reported during the first year of the global pandemic. We then surveyed individuals with reported symptoms and recent reverse transcription polymerase chain reaction (RT-PCR) test results to assess the accuracy of diagnosing COVID-19 from reported symptoms. The scoping literature review, which included 81 scientific articles published by February 2021, identified 7 respiratory, 9 neurological, 4 gastrointestinal, 4 inflammatory, and 5 general symptoms associated with COVID-19 diagnosis. The likelihood ratio associated with each symptom was estimated from sensitivity and specificity of symptoms reported in the literature. A total of 483 individuals were then surveyed to validate the accuracy of predicting COVID-19 diagnosis based on patient symptoms using the likelihood ratios calculated from the literature review. Survey results were weighted to reflect age, gender, and race of the US population. The accuracy of predicting COVID-19 diagnosis from patient-reported symptoms was assessed using area under the receiver operating curve (AROC).

RESULTS

In the community, cough, sore throat, runny nose, dyspnea, and hypoxia, by themselves, were not good predictors of COVID-19 diagnosis. A combination of cough and fever was also a poor predictor of COVID-19 diagnosis (AROC = 0.56). The accuracy of diagnosing COVID-19 based on symptoms was highest when individuals presented with symptoms from different body systems (AROC of 0.74-0.81); the lowest accuracy was when individuals presented with only respiratory symptoms (AROC = 0.48).

CONCLUSIONS

There are no simple rules that clinicians can use to diagnose COVID-19 in the community when diagnostic tests are unavailable or untimely. However, triage of patients to appropriate care and treatment can be improved by reviewing the combinations of certain types of symptoms across body systems.

Epidemic dynamics in census-calibrated modular contact network

Network-based models are apt for understanding epidemic dynamics due to their inherent ability to model the heterogeneity of interactions in the contemporary world of intense human connectivity. We propose a framework to create a wire-frame that mimics the social contact network of the population in a geography by lacing it with demographic information. The framework results in a modular network with small-world topology that accommodates density variations and emulates human interactions in family, social, and work spaces. When loaded with suitable economic, social, and urban data shaping patterns of human connectance, the network emerges as a potent decision-making instrument for urban planners, demographers, and social scientists. We employ synthetic networks to experiment in a controlled environment and study the impact of zoning, density variations, and population mobility on the epidemic variables using a variant of the SEIR model. Our results reveal that these demographic factors have a characteristic influence on social contact patterns, manifesting as distinct epidemic dynamics. Subsequently, we present a real-world COVID-19 case study for three Indian states by creating corresponding surrogate social contact networks using available census data. The case study validates that the demography-laced modular contact network reduces errors in the estimates of epidemic variables.

Modeling the progression of COVID-19 deaths using Kalman Filter and AutoML

The COVID-19 pandemic continues to have a destructive effect on the health and well-being of the global population. A vital step in the battle against it is the successful screening of infected patients, together with one of the effective screening methods being radiology examination using chest radiography. Recognition of epidemic growth patterns across temporal and social factors can improve our capability to create epidemic transmission designs, including the critical job of predicting the estimated intensity of the outbreak morbidity or mortality impact at the end. The study's primary motivation is to be able to estimate with a certain level of accuracy the number of deaths due to COVID-19, managing to model the progression of the pandemic. Predicting the number of possible deaths from COVID-19 can provide governments and decision-makers with indicators for purchasing respirators and pandemic prevention policies. Thus, this work presents itself as an essential contribution to combating the pandemic. Kalman Filter is a widely used method for tracking and navigation and filtering and time series. Designing and tuning machine learning methods are a labor- and time-intensive task that requires extensive experience. The field of automated machine learning Auto Machine Learning relies on automating this task. Auto Machine Learning tools enable novice users to create useful machine learning units, while experts can use them to free up valuable time for other tasks. This paper presents an objective method of forecasting the COVID-19 outbreak using Kalman Filter and Auto Machine Learning. We use a COVID-19 dataset of Ceará, one of the 27 federative units in Brazil. Ceará has more than 235,222 confirmed cases of COVID-19 and 8850 deaths due to the disease. The TPOT automobile model showed the best result with a 0.99 of R 2 score.