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

Development and validation of a prediction model based on comorbidities to estimate the risk of in-hospital death in patients with COVID-19

Background

Most existing prognostic models of COVID-19 require imaging manifestations and laboratory results as predictors, which are only available in the post-hospitalization period. Therefore, we aimed to develop and validate a prognostic model to assess the in-hospital death risk in COVID-19 patients using routinely available predictors at hospital admission.

Methods

We conducted a retrospective cohort study of patients with COVID-19 using the Healthcare Cost and Utilization Project State Inpatient Database in 2020. Patients hospitalized in Eastern United States (Florida, Michigan, Kentucky, and Maryland) were included in the training set, and those hospitalized in Western United States (Nevada) were included in the validation set. Discrimination, calibration, and clinical utility were evaluated to assess the model's performance.

Results

A total of 17 954 in-hospital deaths occurred in the training set (n = 168 137), and 1,352 in-hospital deaths occurred in the validation set (n = 12 577). The final prediction model included 15 variables readily available at hospital admission, including age, sex, and 13 comorbidities. This prediction model showed moderate discrimination with an area under the curve (AUC) of 0.726 (95% confidence interval [CI]: 0.722-0.729) and good calibration (Brier score = 0.090, slope = 1, intercept = 0) in the training set; a similar predictive ability was observed in the validation set.

Conclusion

An easy-to-use prognostic model based on predictors readily available at hospital admission was developed and validated for the early identification of COVID-19 patients with a high risk of in-hospital death. This model can be a clinical decision-support tool to triage patients and optimize resource allocation.

Artificial Intelligence in the Intensive Care Unit: Present and Future in the COVID-19 Era

The development of artificial intelligence (AI) allows for the construction of technologies capable of implementing functions that represent the human mind, senses, and problem-solving skills, leading to automation, rapid data analysis, and acceleration of tasks. These solutions has been initially implemented in medical fields relying on image analysis; however, technological development and interdisciplinary collaboration allows for the introduction of AI-based enhancements to further medical specialties. During the COVID-19 pandemic, novel technologies established on big data analysis experienced a rapid expansion. Yet, despite the possibilities of advancements with these AI technologies, there are number of shortcomings that need to be resolved to assert the highest and the safest level of performance, especially in the setting of the intensive care unit (ICU). Within the ICU, numerous factors and data affect clinical decision making and work management that could be managed by AI-based technologies. Early detection of a patient's deterioration, identification of unknown prognostic parameters, or even improvement of work organization are a few of many areas where patients and medical personnel can benefit from solutions developed with AI.

Genetic determination of regional connectivity in modelling the spread of COVID-19 outbreak for more efficient mitigation strategies

For the COVID-19 pandemic, viral transmission has been documented in many historical and geographical contexts. Nevertheless, few studies have explicitly modeled the spatiotemporal flow based on genetic sequences, to develop mitigation strategies. Additionally, thousands of SARS-CoV-2 genomes have been sequenced with associated records, potentially providing a rich source for such spatiotemporal analysis, an unprecedented amount during a single outbreak. Here, in a case study of seven states, we model the first wave of the outbreak by determining regional connectivity from phylogenetic sequence information (i.e. "genetic connectivity"), in addition to traditional epidemiologic and demographic parameters. Our study shows nearly all of the initial outbreak can be traced to a few lineages, rather than disconnected outbreaks, indicative of a mostly continuous initial viral flow. While the geographic distance from hotspots is initially important in the modeling, genetic connectivity becomes increasingly significant later in the first wave. Moreover, our model predicts that isolated local strategies (e.g. relying on herd immunity) can negatively impact neighboring regions, suggesting more efficient mitigation is possible with unified, cross-border interventions. Finally, our results suggest that a few targeted interventions based on connectivity can have an effect similar to that of an overall lockdown. They also suggest that while successful lockdowns are very effective in mitigating an outbreak, less disciplined lockdowns quickly decrease in effectiveness. Our study provides a framework for combining phylodynamic and computational methods to identify targeted interventions.

COVID-19 Detection from Cough Recordings Using Bag-of-Words Classifiers

Reliable detection of COVID-19 from cough recordings is evaluated using bag-of-words classifiers. The effect of using four distinct feature extraction procedures and four different encoding strategies is evaluated in terms of the Area Under Curve (AUC), accuracy, sensitivity, and F1-score. Additional studies include assessing the effect of both input and output fusion approaches and a comparative analysis against 2D solutions using Convolutional Neural Networks. Extensive experiments conducted on the COUGHVID and COVID-19 Sounds datasets indicate that sparse encoding yields the best performances, showing robustness against various combinations of feature type, encoding strategy, and codebook dimension parameters.

An external validation of the QCOVID3 risk prediction algorithm for risk of hospitalisation and death from COVID-19: An observational, prospective cohort study of 1.66m vaccinated adults in Wales, UK

INTRODUCTION

At the start of the COVID-19 pandemic there was an urgent need to identify individuals at highest risk of severe outcomes, such as hospitalisation and death following infection. The QCOVID risk prediction algorithms emerged as key tools in facilitating this which were further developed during the second wave of the COVID-19 pandemic to identify groups of people at highest risk of severe COVID-19 related outcomes following one or two doses of vaccine.

OBJECTIVES

To externally validate the QCOVID3 algorithm based on primary and secondary care records for Wales, UK.

METHODS

We conducted an observational, prospective cohort based on electronic health care records for 1.66m vaccinated adults living in Wales on 8th December 2020, with follow-up until 15th June 2021. Follow-up started from day 14 post vaccination to allow the full effect of the vaccine.

RESULTS

The scores produced by the QCOVID3 risk algorithm showed high levels of discrimination for both COVID-19 related deaths and hospital admissions and good calibration (Harrell C statistic: ≥ 0.828).

CONCLUSION

This validation of the updated QCOVID3 risk algorithms in the adult vaccinated Welsh population has shown that the algorithms are valid for use in the Welsh population, and applicable on a population independent of the original study, which has not been previously reported. This study provides further evidence that the QCOVID algorithms can help inform public health risk management on the ongoing surveillance and intervention to manage COVID-19 related risks.

Artificial intelligence in medical device software and high-risk medical devices - a review of definitions, expert recommendations and regulatory initiatives

INTRODUCTION

Artificial intelligence (AI) encompasses a wide range of algorithms with risks when used to support decisions about diagnosis or treatment, so professional and regulatory bodies are recommending how they should be managed.

AREAS COVERED

AI systems may qualify as standalone medical device software (MDSW) or be embedded within a medical device. Within the European Union (EU) AI software must undergo a conformity assessment procedure to be approved as a medical device. The draft EU Regulation on AI proposes rules that will apply across industry sectors, while for devices the Medical Device Regulation also applies. In the CORE-MD project (Coordinating Research and Evidence for Medical Devices), we have surveyed definitions and summarize initiatives made by professional consensus groups, regulators, and standardization bodies.

EXPERT OPINION

The level of clinical evidence required should be determined according to each application and to legal and methodological factors that contribute to risk, including accountability, transparency, and interpretability. EU guidance for MDSW based on international recommendations does not yet describe the clinical evidence needed for medical AI software. Regulators, notified bodies, manufacturers, clinicians and patients would all benefit from common standards for the clinical evaluation of high-risk AI applications and transparency of their evidence and performance.

DeepCOVID-Fuse: A Multi-Modality Deep Learning Model Fusing Chest X-rays and Clinical Variables to Predict COVID-19 Risk Levels

The COVID-19 pandemic has posed unprecedented challenges to global healthcare systems, highlighting the need for accurate and timely risk prediction models that can prioritize patient care and allocate resources effectively. This study presents DeepCOVID-Fuse, a deep learning fusion model that predicts risk levels in patients with confirmed COVID-19 by combining chest radiographs (CXRs) and clinical variables. The study collected initial CXRs, clinical variables, and outcomes (i.e., mortality, intubation, hospital length of stay, Intensive care units (ICU) admission) from February to April 2020, with risk levels determined by the outcomes. The fusion model was trained on 1657 patients (Age: 58.30 ± 17.74; Female: 807) and validated on 428 patients (56.41 ± 17.03; 190) from the local healthcare system and tested on 439 patients (56.51 ± 17.78; 205) from a different holdout hospital. The performance of well-trained fusion models on full or partial modalities was compared using DeLong and McNemar tests. Results show that DeepCOVID-Fuse significantly (p < 0.05) outperformed models trained only on CXRs or clinical variables, with an accuracy of 0.658 and an area under the receiver operating characteristic curve (AUC) of 0.842. The fusion model achieves good outcome predictions even when only one of the modalities is used in testing, demonstrating its ability to learn better feature representations across different modalities during training.

Unraveling complex relationships between COVID-19 risk factors using machine learning based models for predicting mortality of hospitalized patients and identification of high-risk group: a large retrospective study

Background

At the end of 2019, the coronavirus disease 2019 (COVID-19) pandemic increased the hospital burden of COVID-19 caused by the SARS-Cov-2 and became the most significant health challenge for nations worldwide. The severity and high mortality of COVID-19 have been correlated with various demographic characteristics and clinical manifestations. Prediction of mortality rate, identification of risk factors, and classification of patients played a crucial role in managing COVID-19 patients. Our purpose was to develop machine learning (ML)-based models for the prediction of mortality and severity among patients with COVID-19. Identifying the most important predictors and unraveling their relationships by classification of patients to the low-, moderate- and high-risk groups might guide prioritizing treatment decisions and a better understanding of interactions between factors. A detailed evaluation of patient data is believed to be important since COVID-19 resurgence is underway in many countries.

Results

The findings of this study revealed that the ML-based statistically inspired modification of the partial least square (SIMPLS) method could predict the in-hospital mortality among COVID-19 patients. The prediction model was developed using 19 predictors including clinical variables, comorbidities, and blood markers with moderate predictability (Q² = 0.24) to separate survivors and non-survivors. Oxygen saturation level, loss of consciousness, and chronic kidney disease (CKD) were the top mortality predictors. Correlation analysis showed different correlation patterns among predictors for each non-survivor and survivor cohort separately. The main prediction model was verified using other ML-based analyses with a high area under the curve (AUC) (0.81-0.93) and specificity (0.94-0.99). The obtained data revealed that the mortality prediction model can be different for males and females with diverse predictors. Patients were classified into four clusters of mortality risk and identified the patients at the highest risk of mortality, which accentuated the most significant predictors correlating with mortality.

Conclusion

An ML model for predicting mortality among hospitalized COVID-19 patients was developed considering the interactions between factors that may reduce the complexity of clinical decision-making processes. The most predictive factors related to patient mortality were identified by assessing and classifying patients into different groups based on their sex and mortality risk (low-, moderate-, and high-risk groups).

Association of blood viscosity and device-free days among hospitalized patients with COVID-19

BACKGROUND

Increased estimated whole blood viscosity (eWBV) predicts higher mortality in patients hospitalized for coronavirus disease 2019 (COVID-19). This study assesses whether eWBV is an early predictor of non-fatal outcomes among patients hospitalized for acute COVID-19 infection.

METHODS

This retrospective cohort study included 9278 hospitalized COVID-19 patients diagnosed within 48 h of admission between February 27, 2020 to November 20, 2021 within the Mount Sinai Health System in New York City. Patients with missing values for major covariates, discharge information, and those who failed to meet the criteria for the non-Newtonian blood model were excluded. 5621 participants were included in the main analysis. Additional analyses were performed separately for 4352 participants who had measurements of white blood cell count, C-reactive protein and D-dimer. Participants were divided into quartiles based on estimated high-shear blood viscosity (eHSBV) and estimated low-shear blood viscosity (eLSBV). Blood viscosity was calculated using the Walburn-Schneck model. The primary outcome was evaluated as an ordinal scale indicating the number of days free of respiratory organ support through day 21, and those who died in-hospital were assigned a value of -1. Multivariate cumulative logistic regression was conducted to evaluate the association between quartiles of eWBV and events.

RESULTS

Among 5621 participants, 3459 (61.5%) were male with mean age of 63.2 (SD 17.1) years. The linear modeling yielded an adjusted odds ratio (aOR) of 0.68 (95% CI 0.59-0.79, p value < 0.001) per 1 centipoise increase in eHSBV.

CONCLUSIONS

Among hospitalized patients with COVID-19, elevated eHSBV and eLSBV at presentation were associated with an increased need for respiratory organ support at 21 days. These findings are highly relevant, as they demonstrate the utility of eWBV in identifying hospitalized patients with acute COVID-19 infection at increased risk for non-fatal outcomes in early stages of the disease.

Harnessing Machine Learning in Early COVID-19 Detection and Prognosis: A Comprehensive Systematic Review

During the early phase of the COVID-19 pandemic, reverse transcriptase-polymerase chain reaction (RT-PCR) testing faced limitations, prompting the exploration of machine learning (ML) alternatives for diagnosis and prognosis. Providing a comprehensive appraisal of such decision support systems and their use in COVID-19 management can aid the medical community in making informed decisions during the risk assessment of their patients, especially in low-resource settings. Therefore, the objective of this study was to systematically review the studies that predicted the diagnosis of COVID-19 or the severity of the disease using ML. Following the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA), we conducted a literature search of MEDLINE (OVID), Scopus, EMBASE, and IEEE Xplore from January 1 to June 31, 2020. The outcomes were COVID-19 diagnosis or prognostic measures such as death, need for mechanical ventilation, admission, and acute respiratory distress syndrome. We included peer-reviewed observational studies, clinical trials, research letters, case series, and reports. We extracted data about the study's country, setting, sample size, data source, dataset, diagnostic or prognostic outcomes, prediction measures, type of ML model, and measures of diagnostic accuracy. Bias was assessed using the Prediction model Risk Of Bias ASsessment Tool (PROBAST). This study was registered in the International Prospective Register of Systematic Reviews (PROSPERO), with the number CRD42020197109. The final records included for data extraction were 66. Forty-three (64%) studies used secondary data. The majority of studies were from Chinese authors (30%). Most of the literature (79%) relied on chest imaging for prediction, while the remainder used various laboratory indicators, including hematological, biochemical, and immunological markers. Thirteen studies explored predicting COVID-19 severity, while the rest predicted diagnosis. Seventy percent of the articles used deep learning models, while 30% used traditional ML algorithms. Most studies reported high sensitivity, specificity, and accuracy for the ML models (exceeding 90%). The overall concern about the risk of bias was "unclear" in 56% of the studies. This was mainly due to concerns about selection bias. ML may help identify COVID-19 patients in the early phase of the pandemic, particularly in the context of chest imaging. Although these studies reflect that these ML models exhibit high accuracy, the novelty of these models and the biases in dataset selection make using them as a replacement for the clinicians' cognitive decision-making questionable. Continued research is needed to enhance the robustness and reliability of ML systems in COVID-19 diagnosis and prognosis.

Overinterpretation of findings in machine learning prediction model studies in oncology: a systematic review

OBJECTIVES

In biomedical research, spin is the overinterpretation of findings, and it is a growing concern. To date, the presence of spin has not been evaluated in prognostic model research in oncology, including studies developing and validating models for individualized risk prediction.

STUDY DESIGN AND SETTING

We conducted a systematic review, searching MEDLINE and EMBASE for oncology-related studies that developed and validated a prognostic model using machine learning published between 1st January, 2019, and 5th September, 2019. We used existing spin frameworks and described areas of highly suggestive spin practices.

RESULTS

We included 62 publications (including 152 developed models; 37 validated models). Reporting was inconsistent between methods and the results in 27% of studies due to additional analysis and selective reporting. Thirty-two studies (out of 36 applicable studies) reported comparisons between developed models in their discussion and predominantly used discrimination measures to support their claims (78%). Thirty-five studies (56%) used an overly strong or leading word in their title, abstract, results, discussion, or conclusion.

CONCLUSION

The potential for spin needs to be considered when reading, interpreting, and using studies that developed and validated prognostic models in oncology. Researchers should carefully report their prognostic model research using words that reflect their actual results and strength of evidence.

Structural under-reporting of informed consent, data handling and sharing, ethical approval, and application of Open Science principles as proxies for study quality conduct in COVID-19 research: a systematic scoping review

BACKGROUND

The COVID-19 pandemic required science to provide answers rapidly to combat the outbreak. Hence, the reproducibility and quality of conducting research may have been threatened, particularly regarding privacy and data protection, in varying ways around the globe. The objective was to investigate aspects of reporting informed consent and data handling as proxies for study quality conduct.

METHODS

A systematic scoping review was performed by searching PubMed and Embase. The search was performed on November 8th, 2020. Studies with hospitalised patients diagnosed with COVID-19 over 18 years old were eligible for inclusion. With a focus on informed consent, data were extracted on the study design, prestudy protocol registration, ethical approval, data anonymisation, data sharing and data transfer as proxies for study quality. For reasons of comparison, data regarding country income level, study location and journal impact factor were also collected.

RESULTS

972 studies were included. 21.3% of studies reported informed consent, 42.6% reported waivers of consent, 31.4% did not report consent information and 4.7% mentioned other types of consent. Informed consent reporting was highest in clinical trials (94.6%) and lowest in retrospective cohort studies (15.0%). The reporting of consent versus no consent did not differ significantly by journal impact factor (p=0.159). 16.8% of studies reported a prestudy protocol registration or design. Ethical approval was described in 90.9% of studies. Information on anonymisation was provided in 17.0% of studies. In 257 multicentre studies, 1.2% reported on data sharing agreements, and none reported on Findable, Accessible, Interoperable and Reusable data principles. 1.2% reported on open data. Consent was most often reported in the Middle East (42.4%) and least often in North America (4.7%). Only one report originated from a low-income country.

DISCUSSION

Informed consent and aspects of data handling and sharing were under-reported in publications concerning COVID-19 and differed between countries, which strains study quality conduct when in dire need of answers.

Machine learning does not outperform traditional statistical modelling for kidney allograft failure prediction

Machine learning (ML) models have recently shown potential for predicting kidney allograft outcomes. However, their ability to outperform traditional approaches remains poorly investigated. Therefore, using large cohorts of kidney transplant recipients from 14 centers worldwide, we developed ML-based prediction models for kidney allograft survival and compared their prediction performances to those achieved by a validated Cox-Based Prognostication System (CBPS). In a French derivation cohort of 4000 patients, candidate determinants of allograft failure including donor, recipient and transplant-related parameters were used as predictors to develop tree-based models (RSF, RSF-ERT, CIF), Support Vector Machine models (LK-SVM, AK-SVM) and a gradient boosting model (XGBoost). Models were externally validated with cohorts of 2214 patients from Europe, 1537 from North America, and 671 from South America. Among these 8422 kidney transplant recipients, 1081 (12.84%) lost their grafts after a median post-transplant follow-up time of 6.25 years (Inter Quartile Range 4.33-8.73). At seven years post-risk evaluation, the ML models achieved a C-index of 0.788 (95% bootstrap percentile confidence interval 0.736-0.833), 0.779 (0.724-0.825), 0.786 (0.735-0.832), 0.527 (0.456-0.602), 0.704 (0.648-0.759) and 0.767 (0.711-0.815) for RSF, RSF-ERT, CIF, LK-SVM, AK-SVM and XGBoost respectively, compared with 0.808 (0.792-0.829) for the CBPS. In validation cohorts, ML models' discrimination performances were in a similar range of those of the CBPS. Calibrations of the ML models were similar or less accurate than those of the CBPS. Thus, when using a transparent methodological pipeline in validated international cohorts, ML models, despite overall good performances, do not outperform a traditional CBPS in predicting kidney allograft failure. Hence, our current study supports the continued use of traditional statistical approaches for kidney graft prognostication.

Translating AI to Clinical Practice: Overcoming Data Shift with Explainability

To translate artificial intelligence (AI) algorithms into clinical practice requires generalizability of models to real-world data. One of the main obstacles to generalizability is data shift, a data distribution mismatch between model training and real environments. Explainable AI techniques offer tools to detect and mitigate the data shift problem and develop reliable AI for clinical practice. Most medical AI is trained with datasets gathered from limited environments, such as restricted disease populations and center-dependent acquisition conditions. The data shift that commonly exists in the limited training set often causes a significant performance decrease in the deployment environment. To develop a medical application, it is important to detect potential data shift and its impact on clinical translation. During AI training stages, from premodel analysis to in-model and post hoc explanations, explainability can play a key role in detecting model susceptibility to data shift, which is otherwise hidden because the test data have the same biased distribution as the training data. Performance-based model assessments cannot effectively distinguish the model overfitting to training data bias without enriched test sets from external environments. In the absence of such external data, explainability techniques can aid in translating AI to clinical practice as a tool to detect and mitigate potential failures due to data shift. ©RSNA, 2023 Quiz questions for this article are available in the supplemental material.

Validation of the qSOFA and CRB-65 in SARS-CoV-2-infected community-acquired pneumonia

Rationale

Prognostic accuracy of the quick sequential organ failure assessment (qSOFA) and CRB-65 (confusion, respiratory rate, blood pressure and age (≥65 years)) risk scores have not been widely evaluated in patients with SARS-CoV-2-positive compared to SARS-CoV-2-negative community-acquired pneumonia (CAP). The aim of the present study was to validate the qSOFA(-65) and CRB-65 scores in a large cohort of SARS-CoV-2-positive and SARS-CoV-2-negative CAP patients.

Methods

We included all cases with CAP hospitalised in 2020 from the German nationwide mandatory quality assurance programme and compared cases with SARS-CoV-2 infection to cases without. We excluded cases with unclear SARS-CoV-2 infection state, transferred to another hospital or on mechanical ventilation during admission. Predefined outcomes were hospital mortality and need for mechanical ventilation.

Results

Among 68 594 SARS-CoV-2-positive patients, hospital mortality (22.7%) and mechanical ventilation (14.9%) were significantly higher when compared to 167 880 SARS-CoV-2-negative patients (15.7% and 9.2%, respectively). All CRB-65 and qSOFA criteria were associated with both outcomes, and age dominated mortality prediction in SARS-CoV-2 (risk ratio >9). Scores including the age criterion had higher area under the curve (AUCs) for mortality in SARS-CoV-2-positive patients (e.g. CRB-65 AUC 0.76) compared to SARS-CoV-2 negative patients (AUC 0.68), and negative predictive value was highest for qSOFA-65=0 (98.2%). Sensitivity for mechanical ventilation prediction was poor with all scores (AUCs 0.59-0.62), and negative predictive values were insufficient (qSOFA-65=0 missed 1490 out of 10 198 patients (∼15%) with mechanical ventilation). Results were similar when excluding frail and palliative patients.

Conclusions

Hospital mortality and mechanical ventilation rates were higher in SARS-CoV-2-positive than SARS-CoV-2-negative CAP. For SARS-CoV-2-positive CAP, the CRB-65 and qSOFA-65 scores showed adequate prediction of mortality but not of mechanical ventilation.

On-admission and dynamic trend of laboratory profiles as prognostic biomarkers in COVID-19 inpatients

This large-scale study aimed to investigate the trend of laboratory tests of patients with COVID-19. Hospitalized confirmed and probable COVID-19 patients in three general hospitals were examined from March 20, 2020, to June 18, 2021. The confirmed and probable COVID-19 patients with known outcomes and valid laboratory results were included. The least absolute shrinkage and selection operator (LASSO) and Cox regression were used to select admittance prognostic features. Parallel Pairwise Comparison of mortality versus survival was used to examine the trend of markers. In the final cohort, 11,944 patients were enrolled, with an in-hospital mortality rate of 21.8%, mean age of 59.4 ± 18.0, and a male-to-female ratio of 1.3. Abnormal admittance level of white blood cells, neutrophils, lymphocytes, mean cellular volume, urea, creatinine, bilirubin, creatine kinase-myoglobin binding, lactate dehydrogenase (LDH), Troponin, c-reactive protein (CRP), potassium, and creatinine phosphokinase reduced the survival of COVID-19 inpatients. Moreover, the trend analysis showed lymphocytes, platelet, urea, CRP, alanine transaminase (ALT), and LDH have a dissimilar trend in non-survivors compared to survived patients. This study proposed a novel approach to find serial laboratory markers. Serial examination of platelet count, creatinine, CRP, LDH, and ALT can guide healthcare professionals in finding patients at risk of deterioration.

Severe/critical COVID-19 early warning system based on machine learning algorithms using novel imaging scores

BACKGROUND

Early identification of severe/critical coronavirus disease 2019 (COVID-19) is crucial for timely treatment and intervention. Chest computed tomography (CT) score has been shown to be a significant factor in the diagnosis and treatment of pneumonia, however, there is currently a lack of effective early warning systems for severe/critical COVID-19 based on dynamic CT evolution.

AIM

To develop a severe/critical COVID-19 prediction model using a combination of imaging scores, clinical features, and biomarker levels.

METHODS

This study used an improved scoring system to extract and describe the chest CT characteristics of COVID-19 patients. The study also took into consideration the general clinical indicators such as dyspnea, oxygen saturation, alternative lengthening of telomeres (ALT), and androgen suppression treatment (AST), which are commonly associated with severe/critical COVID-19 cases. The study employed lasso regression to evaluate and rank the significance of different disease characteristics.

RESULTS

The results showed that blood oxygen saturation, ALT, IL-6/IL-10, combined score, ground glass opacity score, age, crazy paving mode score, qsofa, AST, and overall lung involvement score were key factors in predicting severe/critical COVID-19 cases. The study established a COVID-19 severe/critical early warning system using various machine learning algorithms, including XGBClassifier, Logistic Regression, MLPClassifier, RandomForestClassifier, and AdaBoost Classifier. The study concluded that the prediction model based on the improved CT score and machine learning algorithms is a feasible method for early detection of severe/critical COVID-19 evolution.

CONCLUSION

The findings of this study suggest that a prediction model based on improved CT scores and machine learning algorithms is effective in detecting the early warning signals of severe/critical COVID-19.

Electronic health record-based prediction models for in-hospital adverse drug event diagnosis or prognosis: a systematic review

OBJECTIVE

We conducted a systematic review to characterize and critically appraise developed prediction models based on structured electronic health record (EHR) data for adverse drug event (ADE) diagnosis and prognosis in adult hospitalized patients.

MATERIALS AND METHODS

We searched the Embase and Medline databases (from January 1, 1999, to July 4, 2022) for articles utilizing structured EHR data to develop ADE prediction models for adult inpatients. For our systematic evidence synthesis and critical appraisal, we applied the Checklist for Critical Appraisal and Data Extraction for Systematic Reviews of Prediction Modelling Studies (CHARMS).

RESULTS

Twenty-five articles were included. Studies often did not report crucial information such as patient characteristics or the method for handling missing data. In addition, studies frequently applied inappropriate methods, such as univariable screening for predictor selection. Furthermore, the majority of the studies utilized ADE labels that only described an adverse symptom while not assessing causality or utilizing a causal model. None of the models were externally validated.

CONCLUSIONS

Several challenges should be addressed before the models can be widely implemented, including the adherence to reporting standards and the adoption of best practice methods for model development and validation. In addition, we propose a reorientation of the ADE prediction modeling domain to include causality as a fundamental challenge that needs to be addressed in future studies, either through acquiring ADE labels via formal causality assessments or the usage of adverse event labels in combination with causal prediction modeling.

A new data integration framework for Covid-19 social media information

The Covid-19 pandemic presents a serious threat to people's health, resulting in over 250 million confirmed cases and over 5 million deaths globally. To reduce the burden on national health care systems and to mitigate the effects of the outbreak, accurate modelling and forecasting methods for short- and long-term health demand are needed to inform government interventions aiming at curbing the pandemic. Current research on Covid-19 is typically based on a single source of information, specifically on structured historical pandemic data. Other studies are exclusively focused on unstructured online retrieved insights, such as data available from social media. However, the combined use of structured and unstructured information is still uncharted. This paper aims at filling this gap, by leveraging historical and social media information with a novel data integration methodology. The proposed approach is based on vine copulas, which allow us to exploit the dependencies between different sources of information. We apply the methodology to combine structured datasets retrieved from official sources and a big unstructured dataset of information collected from social media. The results show that the combined use of official and online generated information contributes to yield a more accurate assessment of the evolution of the Covid-19 pandemic, compared to the sole use of official data.

A quantitative systems pharmacology model of the pathophysiology and treatment of COVID-19 predicts optimal timing of pharmacological interventions

A quantitative systems pharmacology (QSP) model of the pathogenesis and treatment of SARS-CoV-2 infection can streamline and accelerate the development of novel medicines to treat COVID-19. Simulation of clinical trials allows in silico exploration of the uncertainties of clinical trial design and can rapidly inform their protocols. We previously published a preliminary model of the immune response to SARS-CoV-2 infection. To further our understanding of COVID-19 and treatment, we significantly updated the model by matching a curated dataset spanning viral load and immune responses in plasma and lung. We identified a population of parameter sets to generate heterogeneity in pathophysiology and treatment and tested this model against published reports from interventional SARS-CoV-2 targeting mAb and antiviral trials. Upon generation and selection of a virtual population, we match both the placebo and treated responses in viral load in these trials. We extended the model to predict the rate of hospitalization or death within a population. Via comparison of the in silico predictions with clinical data, we hypothesize that the immune response to virus is log-linear over a wide range of viral load. To validate this approach, we show the model matches a published subgroup analysis, sorted by baseline viral load, of patients treated with neutralizing Abs. By simulating intervention at different time points post infection, the model predicts efficacy is not sensitive to interventions within five days of symptom onset, but efficacy is dramatically reduced if more than five days pass post symptom onset prior to treatment.

Prognosis Prediction in COVID-19 Patients through Deep Feature Space Reasoning

The COVID-19 pandemic has presented a unique challenge for physicians worldwide, as they grapple with limited data and uncertainty in diagnosing and predicting disease outcomes. In such dire circumstances, the need for innovative methods that can aid in making informed decisions with limited data is more critical than ever before. To allow prediction with limited COVID-19 data as a case study, we present a complete framework for progression and prognosis prediction in chest X-rays (CXR) through reasoning in a COVID-specific deep feature space. The proposed approach relies on a pre-trained deep learning model that has been fine-tuned specifically for COVID-19 CXRs to identify infection-sensitive features from chest radiographs. Using a neuronal attention-based mechanism, the proposed method determines dominant neural activations that lead to a feature subspace where neurons are more sensitive to COVID-related abnormalities. This process allows the input CXRs to be projected into a high-dimensional feature space where age and clinical attributes like comorbidities are associated with each CXR. The proposed method can accurately retrieve relevant cases from electronic health records (EHRs) using visual similarity, age group, and comorbidity similarities. These cases are then analyzed to gather evidence for reasoning, including diagnosis and treatment. By using a two-stage reasoning process based on the Dempster-Shafer theory of evidence, the proposed method can accurately predict the severity, progression, and prognosis of a COVID-19 patient when sufficient evidence is available. Experimental results on two large datasets show that the proposed method achieves 88% precision, 79% recall, and 83.7% F-score on the test sets.

A study protocol of external validation of eight COVID-19 prognostic models for predicting mortality risk in older populations in a hospital, primary care, and nursing home setting

BACKGROUND

The COVID-19 pandemic has a large impact worldwide and is known to particularly affect the older population. This paper outlines the protocol for external validation of prognostic models predicting mortality risk after presentation with COVID-19 in the older population. These prognostic models were originally developed in an adult population and will be validated in an older population (≥ 70 years of age) in three healthcare settings: the hospital setting, the primary care setting, and the nursing home setting.

METHODS

Based on a living systematic review of COVID-19 prediction models, we identified eight prognostic models predicting the risk of mortality in adults with a COVID-19 infection (five COVID-19 specific models: GAL-COVID-19 mortality, 4C Mortality Score, NEWS2 + model, Xie model, and Wang clinical model and three pre-existing prognostic scores: APACHE-II, CURB65, SOFA). These eight models will be validated in six different cohorts of the Dutch older population (three hospital cohorts, two primary care cohorts, and a nursing home cohort). All prognostic models will be validated in a hospital setting while the GAL-COVID-19 mortality model will be validated in hospital, primary care, and nursing home settings. The study will include individuals ≥ 70 years of age with a highly suspected or PCR-confirmed COVID-19 infection from March 2020 to December 2020 (and up to December 2021 in a sensitivity analysis). The predictive performance will be evaluated in terms of discrimination, calibration, and decision curves for each of the prognostic models in each cohort individually. For prognostic models with indications of miscalibration, an intercept update will be performed after which predictive performance will be re-evaluated.

DISCUSSION

Insight into the performance of existing prognostic models in one of the most vulnerable populations clarifies the extent to which tailoring of COVID-19 prognostic models is needed when models are applied to the older population. Such insight will be important for possible future waves of the COVID-19 pandemic or future pandemics.

Discharge summary hospital course summarisation of in patient Electronic Health Record text with clinical concept guided deep pre-trained Transformer models

Brief Hospital Course (BHC) summaries are succinct summaries of an entire hospital encounter, embedded within discharge summaries, written by senior clinicians responsible for the overall care of a patient. Methods to automatically produce summaries from inpatient documentation would be invaluable in reducing clinician manual burden of summarising documents under high time-pressure to admit and discharge patients. Automatically producing these summaries from the inpatient course, is a complex, multi-document summarisation task, as source notes are written from various perspectives (e.g. nursing, doctor, radiology), during the course of the hospitalisation. We demonstrate a range of methods for BHC summarisation demonstrating the performance of deep learning summarisation models across extractive and abstractive summarisation scenarios. We also test a novel ensemble extractive and abstractive summarisation model that incorporates a medical concept ontology (SNOMED) as a clinical guidance signal and shows superior performance in 2 real-world clinical data sets.

New compartment model for COVID-19

The SIR or susceptible-infected-recovered model is the standard compartment model for understanding epidemics and has been used all over the world for COVID-19. While the SIR model assumes that infected patients are identical to symptomatic and infectious patients, it is now known that in COVID-19 pre-symptomatic patients are infectious and there are significant number of asymptomatic patients who are infectious. In this paper, population is separated into five compartments for COVID-19; susceptible individuals (S), pre-symptomatic patients (P), asymptomatic patients (A), quarantined patients (Q) and recovered and/or dead patients (R). The time evolution of population in each compartment is described by a set of ordinary differential equations. Numerical solution to the set of differential equations shows that quarantining pre-symptomatic and asymptomatic patients is effective in controlling the pandemic.

Development and external validation of prediction models for critical outcomes of unvaccinated COVID-19 patients based on demographics, medical conditions and dental status

Background

Multiple prediction models were developed for critical outcomes of COVID-19. However, prediction models using predictors which can be easily obtained in clinical practice and on dental status are scarce.

Aim

The study aimed to develop and externally validate prediction models for critical outcomes of COVID-19 for unvaccinated adult patients in hospital settings based on demographics, medical conditions, and dental status.

Methods

A total of 285 and 352 patients from two hospitals in the Netherlands were retrospectively included as derivation and validation cohorts. Demographics, medical conditions, and dental status were considered potential predictors. The critical outcomes (death and ICU admission) were considered endpoints. Logistic regression analyses were used to develop two models: for death alone and for critical outcomes. The performance and clinical values of the models were determined in both cohorts.

Results

Age, number of teeth, chronic kidney disease, hypertension, diabetes, and chronic obstructive pulmonary diseases were the significant independent predictors. The models showed good to excellent calibration with observed: expected (O:E) ratios of 0.98 (95%CI: 0.76 to 1.25) and 1.00 (95%CI: 0.80 to 1.24), and discrimination with shrunken area under the curve (AUC) values of 0.85 and 0.79, based on the derivation cohort. In the validation cohort, the models showed good to excellent discrimination with AUC values of 0.85 (95%CI: 0.80 to 0.90) and 0.78 (95%CI: 0.73 to 0.83), but an overestimation in calibration with O:E ratios of 0.65 (95%CI: 0.49 to 0.85) and 0.67 (95%CI: 0.52 to 0.84).

Conclusion

The performance of the models was acceptable in both derivation and validation cohorts. Number of teeth was an additive important predictor of critical outcomes of COVID-19. It is an easy-to-apply tool in hospitals for risk stratification of COVID-19 prognosis.

Evaluating Racial/Ethnic Differences in Care Escalation Among COVID-19 Patients in a Home-Based Hospital

The novel coronavirus disease 2019 (COVID-19) has infected over 414 million people worldwide with 5.8 million deaths, as of February 2022. Telemedicine-based interventions to expand healthcare systems' capacity and reduce infection risk have rapidly increased during the pandemic, despite concerns regarding equitable access. Atrium Health Hospital at Home (AH-HaH) is a home-based program that provides advanced, hospital-level medical care and monitoring for patients who would otherwise be hospitalized in a traditional setting. Our retrospective cohort study of positive COVID-19 patients who were admitted to AH-HaH aims to investigate whether the rate of care escalation from AH-HaH to traditional hospitalization differed based on patients' racial/ethnic backgrounds. Logistic regression was used to examine the association between care escalation within 14 days from index AH-HaH admission and race/ethnicity. We found approximately one in five patients receiving care for COVID-19 in AH-HaH required care escalation within 14 days. Odds of care escalation were not significantly different for Hispanic or non-Hispanic Blacks compared to non-Hispanic Whites. However, secondary analyses showed that both Hispanic and non-Hispanic Black patients were younger and with fewer comorbidities than non-Hispanic Whites. The study highlights the need for new care models to vigilantly monitor for disparities, so that timely and tailored adaptations can be implemented for vulnerable populations.

Prognostic models in COVID-19 infection that predict severity: a systematic review

Current evidence on COVID-19 prognostic models is inconsistent and clinical applicability remains controversial. We performed a systematic review to summarize and critically appraise the available studies that have developed, assessed and/or validated prognostic models of COVID-19 predicting health outcomes. We searched six bibliographic databases to identify published articles that investigated univariable and multivariable prognostic models predicting adverse outcomes in adult COVID-19 patients, including intensive care unit (ICU) admission, intubation, high-flow nasal therapy (HFNT), extracorporeal membrane oxygenation (ECMO) and mortality. We identified and assessed 314 eligible articles from more than 40 countries, with 152 of these studies presenting mortality, 66 progression to severe or critical illness, 35 mortality and ICU admission combined, 17 ICU admission only, while the remaining 44 studies reported prediction models for mechanical ventilation (MV) or a combination of multiple outcomes. The sample size of included studies varied from 11 to 7,704,171 participants, with a mean age ranging from 18 to 93 years. There were 353 prognostic models investigated, with area under the curve (AUC) ranging from 0.44 to 0.99. A great proportion of studies (61.5%, 193 out of 314) performed internal or external validation or replication. In 312 (99.4%) studies, prognostic models were reported to be at high risk of bias due to uncertainties and challenges surrounding methodological rigor, sampling, handling of missing data, failure to deal with overfitting and heterogeneous definitions of COVID-19 and severity outcomes. While several clinical prognostic models for COVID-19 have been described in the literature, they are limited in generalizability and/or applicability due to deficiencies in addressing fundamental statistical and methodological concerns. Future large, multi-centric and well-designed prognostic prospective studies are needed to clarify remaining uncertainties.

Development of Prognostic Prediction Model to Estimate Mortality for Frail Oldest Old: Prospective Cohort Study

BACKGROUND

This study was performed to derive and validate a prognostic prediction model for individualized estimation of mortality risk among the frail oldest old (aged 80 years or older).

METHODS

This analysis was based on the prospective open cohort study from the Chinese Longevity and Health Longitudinal Survey. A total of 14 118 frail oldest old were included from the 2002 wave to 2014 waves; the study outcome was all-cause mortality. Available predictors included frailty, demographics, and social factors. Cox models were used to estimate the coefficients of the predictors and least absolute shrinkage and selection operator was used for selecting predictors. Model performance was measured by discrimination and calibration with internal validation by bootstrapping. We also developed a nomogram to visualize and predict the 3-year mortality risk based on the obtained prognostic prediction model.

RESULTS

During the 16-years follow-up, 10 410 (76.42%) deaths were identified. The final model comprises the following factors: frailty, age, sex, race, birthplace, education, occupation, marital status, residence, economic condition, number of children, and the question "who do you ask for help first when in trouble." The model has valid predictive ability as measured and validated by Harrell's C statistic (0.602) and calibration plots.

CONCLUSIONS

This study provides a basic prognostic prediction model to quantify absolute mortality risk for the frail oldest old. Future studies are needed, firstly, to update, adjust, and perform external validation of the present model by using phenotypic frailty, and secondly, to add biomarkers, environmental, and psychological factors to the prediction model.

Analysis of Publication Activity and Research Trends in the Field of AI Medical Applications: Network Approach

Artificial intelligence (AI) has revolutionized numerous industries, including medicine. In recent years, the integration of AI into medical practices has shown great promise in enhancing the accuracy and efficiency of diagnosing diseases, predicting patient outcomes, and personalizing treatment plans. This paper aims at the exploration of the AI-based medicine research using network approach and analysis of existing trends based on PubMed. Our findings are based on the results of PubMed search queries and analysis of the number of papers obtained by the different search queries. Our goal is to explore how are the AI-based methods used in healthcare research, which approaches and techniques are the most popular, and to discuss the potential reasoning behind the obtained results. Using analysis of the co-occurrence network constructed using VOSviewer software, we detected the main clusters of interest in AI-based healthcare research. Then, we proceeded with the thorough analysis of publication activity in various categories of medical AI research, including research on different AI-based methods applied to different types of medical data. We analyzed the results of query processing in the PubMed database over the past 5 years obtained via a specifically designed strategy for generating search queries based on the thorough selection of keywords from different categories of interest. We provide a comprehensive analysis of existing applications of AI-based methods to medical data of different modalities, including the context of various medical fields and specific diseases that carry the greatest danger to the human population.

Prioritization of COVID-19 risk factors in July 2020 and February 2021 in the UK

BACKGROUND

Risk for COVID-19 positivity and hospitalization due to diverse environmental and sociodemographic factors may change as the pandemic progresses.

METHODS

We investigated the association of 360 exposures sampled before COVID-19 outcomes for participants in the UK Biobank, including 9268 and 38,837 non-overlapping participants, sampled at July 17, 2020 and February 2, 2021, respectively. The 360 exposures included clinical biomarkers (e.g., BMI), health indicators (e.g., doctor-diagnosed diabetes), and environmental/behavioral variables (e.g., air pollution) measured 10-14 years before the COVID-19 time periods.

RESULTS

Here we show, for example, "participant having son and/or daughter in household" was associated with an increase in incidence from 20% to 32% (risk difference of 12%) between timepoints. Furthermore, we find age to be increasingly associated with COVID-19 positivity over time from Risk Ratio [RR] (per 10-year age increase) of 0.81 to 0.6 (hospitalization RR from 1.18 to 2.63, respectively).

CONCLUSIONS

Our data-driven approach demonstrates that time of pandemic plays a role in identifying risk factors associated with positivity and hospitalization.

Differential Neural Networks Prediction Using Slow and Fast Hybrid Learning: Application to Prognosis of Infectionsand Deaths of COVID-19 Dynamics

This essay discusses a potential method for predicting the behavior of various physical processes and uses the COVID-19 outbreak to demonstrate its applicability. This study assumes that the current data set reflects the output of a dynamic system that is governed by a nonlinear ordinary differential equation. This dynamic system may be described by a Differential Neural Network (DNN) with time-varying weights matrix parameters. A new hybrid learning scheme based on the decomposition of the signal to be predicted. The decomposition considers the slow and fast components of the signal which is more natural to signals such as the ones corresponding to the number of infected and deceased patients who suffered of COVID 2019 sickness. The paper results demonstrate the recommended method offers competitive performance (70 days of COVID prediction) in comparison to similar studies.

Development and Validation of a Clinical Risk Score to Predict Hospitalization Within 30 Days of Coronavirus Disease 2019 Diagnosis

INTRODUCTION

Early identification of patients with coronavirus disease 2019 (COVID-19) who are at risk for hospitalization may help to mitigate disease burden by allowing healthcare systems to conduct sufficient resource and logistical planning in the event of case surges. We sought to develop and validate a clinical risk score that uses readily accessible information at testing to predict individualized 30-day hospitalization risk following COVID-19 diagnosis.

METHODS

We assembled a retrospective cohort of U.S. Veterans Health Administration patients (age ≥ 18 years) diagnosed with COVID-19 between March 1, 2020, and December 31, 2020. We screened patient characteristics using Least Absolute Shrinkage and Selection Operator logistic regression and constructed the risk score using characteristics identified as most predictive for hospitalization. Patients diagnosed before November 1, 2020, comprised the development cohort, while those diagnosed on or after November 1, 2020, comprised the validation cohort. We assessed risk score discrimination by calculating the area under the receiver operating characteristic (AUROC) curve and calibration using the Hosmer-Lemeshow (HL) goodness-of-fit test. This study was approved by the Veteran's Institutional Review Board of Northern New England at the White River Junction Veterans Affairs Medical Center (Reference no.:1473972-1).

RESULTS

The development and validation cohorts comprised 11,473 and 12,970 patients, of whom 4,465 (38.9%) and 3,669 (28.3%) were hospitalized, respectively. The independent predictors for hospitalization included in the risk score were increasing age, male sex, non-white race, Hispanic ethnicity, homelessness, nursing home/long-term care residence, unemployed or retired status, fever, fatigue, diarrhea, nausea, cough, diabetes, chronic kidney disease, hypertension, and chronic obstructive pulmonary disease. Model discrimination and calibration was good for the development (AUROC = 0.80; HL P-value = .05) and validation (AUROC = 0.80; HL P-value = .31) cohorts.

CONCLUSIONS

The prediction tool developed in this study demonstrated that it could identify patients with COVID-19 who are at risk for hospitalization. This could potentially inform clinicians and policymakers of patients who may benefit most from early treatment interventions and help healthcare systems anticipate capacity surges.

Integrating real-world data from Brazil and Pakistan into the OMOP common data model and standardized health analytics framework to characterize COVID-19 in the Global South

OBJECTIVES

The aim of this work is to demonstrate the use of a standardized health informatics framework to generate reliable and reproducible real-world evidence from Latin America and South Asia towards characterizing coronavirus disease 2019 (COVID-19) in the Global South.

MATERIALS AND METHODS

Patient-level COVID-19 records collected in a patient self-reported notification system, hospital in-patient and out-patient records, and community diagnostic labs were harmonized to the Observational Medical Outcomes Partnership common data model and analyzed using a federated network analytics framework. Clinical characteristics of individuals tested for, diagnosed with or tested positive for, hospitalized with, admitted to intensive care unit with, or dying with COVID-19 were estimated.

RESULTS

Two COVID-19 databases covering 8.3 million people from Pakistan and 2.6 million people from Bahia, Brazil were analyzed. 109 504 (Pakistan) and 921 (Brazil) medical concepts were harmonized to Observational Medical Outcomes Partnership common data model. In total, 341 505 (4.1%) people in the Pakistan dataset and 1 312 832 (49.2%) people in the Brazilian dataset were tested for COVID-19 between January 1, 2020 and April 20, 2022, with a median [IQR] age of 36 [25, 76] and 38 (27, 50); 40.3% and 56.5% were female in Pakistan and Brazil, respectively. 1.2% percent individuals in the Pakistan dataset had Afghan ethnicity. In Brazil, 52.3% had mixed ethnicity. In agreement with international findings, COVID-19 outcomes were more severe in men, elderly, and those with underlying health conditions.

CONCLUSIONS

COVID-19 data from 2 large countries in the Global South were harmonized and analyzed using a standardized health informatics framework developed by an international community of health informaticians. This proof-of-concept study demonstrates a potential open science framework for global knowledge mobilization and clinical translation for timely response to healthcare needs in pandemics and beyond.

Long-term effects of COVID-19 on lungs and the clinical relevance: a 6-month prospective cohort study

Background: We aimed to explore the prevalence of prolonged symptoms, pulmonary impairments and residual disease on chest tomography (CT) in COVID-19 patients at 6 months after acute illness. Methods: In this prospective, single-center study, hospitalized patients with radiologically and laboratory-confirmed COVID-19 were included. Results: A high proportion of the 116 patients reported persistent symptoms (n = 54; 46.6%). On follow-up CT, 33 patients (28.4%) demonstrated residual disease. Multivariate analyses revealed that only neutrophil-to-lymphocyte ratio was an independent predictor for residual disease. Conclusion: Hospitalized patients with mild/moderate COVID-19 still had persistent symptoms and were prone to develop long-term pulmonary sequelae on chest CT. However, it did not have a significant effect on long-term pulmonary functions.

An artificial intelligence approach for predicting death or organ failure after hospitalization for COVID-19: development of a novel risk prediction tool and comparisons with ISARIC-4C, CURB-65, qSOFA, and MEWS scoring systems

BACKGROUND

We applied machine learning (ML) algorithms to generate a risk prediction tool [Collaboration for Risk Evaluation in COVID-19 (CORE-COVID-19)] for predicting the composite of 30-day endotracheal intubation, intravenous administration of vasopressors, or death after COVID-19 hospitalization and compared it with the existing risk scores.

METHODS

This is a retrospective study of adults hospitalized with COVID-19 from March 2020 to February 2021. Patients, each with 92 variables, and one composite outcome underwent feature selection process to identify the most predictive variables. Selected variables were modeled to build four ML algorithms (artificial neural network, support vector machine, gradient boosting machine, and Logistic regression) and an ensemble model to generate a CORE-COVID-19 model to predict the composite outcome and compared with existing risk prediction scores. The net benefit for clinical use of each model was assessed by decision curve analysis.

RESULTS

Of 1796 patients, 278 (15%) patients reached primary outcome. Six most predictive features were identified. Four ML algorithms achieved comparable discrimination (P > 0.827) with c-statistics ranged 0.849-0.856, calibration slopes 0.911-1.173, and Hosmer-Lemeshow P > 0.141 in validation dataset. These 6-variable fitted CORE-COVID-19 model revealed a c-statistic of 0.880, which was significantly (P < 0.04) higher than ISARIC-4C (0.751), CURB-65 (0.735), qSOFA (0.676), and MEWS (0.674) for outcome prediction. The net benefit of the CORE-COVID-19 model was greater than that of the existing risk scores.

CONCLUSION

The CORE-COVID-19 model accurately assigned 88% of patients who potentially progressed to 30-day composite events and revealed improved performance over existing risk scores, indicating its potential utility in clinical practice.

Evaluating disparities by social determinants in hospital admission decisions for patients with COVID-19 quaternary hospital early in the pandemic

The COVID-19 pandemic has highlighted significant disparities in hospital outcomes when focusing on social determinants of health. Better understanding the drivers of these disparities is not only critical for COVID-19 care but also to ensure equitable treatment more generally. In this paper, we look at how hospital admission patterns, both to the medical ward and the intensive care unit (ICU), may have differed by race, ethnicity, and social determinants of health. We conducted a retrospective chart review of all patients who presented to the Emergency Department of a large quaternary hospital between March 8 and June 3, 2020. We built logistic regression models to analyze how race, ethnicity, area deprivation index, English as a primary language, homelessness, and illicit substance use impacted the likelihood of admission while controlling for disease severity and timing of admission in relation to the start of data collection. We had 1302 recorded Emergency Department visits of patients diagnosed with SARS-CoV-2. White, Hispanic, and African American patients made up 39.2%, 37.5%, and 10.4% of the population respectively. Primary language was recorded as English for 41.2% and non-English for 30% of patients. Among the social determinants of health assessed, we found that illicit drug use significantly increased the likelihood for admission to the medical ward (odds ratio 4.4, confidence interval 1.1-17.1, P = .04), and that having a language other than English as a primary language significantly increased the likelihood of ICU admission (odds ratio 2.6, confidence interval 1.2-5.7, P = .02). Illicit drug use was associated with an increased likelihood of medical ward admission, potentially due to clinician concerns for complicated withdrawal or blood-stream infections from intravenous drug use. The increased likelihood of ICU admission associated with a primary language other than English may have been driven by communication difficulties or differences in disease severity that our model did not detect. Further work is required to better understand drivers of disparities in hospital COVID-19 care.

Risk Stratification Model for Severe COVID-19 Disease: A Retrospective Cohort Study

Background: Risk stratification models have been developed to identify patients that are at a higher risk of COVID-19 infection and severe illness. Objectives To develop and implement a scoring tool to identify COVID-19 patients that are at risk for severe illness during the Omicron wave. Methods: This is a retrospective cohort study that was conducted in Israel’s second-largest healthcare maintenance organization. All patients with a new episode of COVID-19 between 26 November 2021 and 18 January 2022 were included. A model was developed to predict severe illness (COVID-19-related hospitalization or death) based on one-third of the study population (the train group). The model was then applied to the remaining two-thirds of the study population (the test group). Risk score sensitivity, specificity, and positive predictive value rates, and receiver operating characteristics (ROC) were calculated to describe the performance of the model. Results: A total of 409,693 patients were diagnosed with COVID-19 over the two-month study period, of which 0.4% had severe illness. Factors that were associated with severe disease were age (age > 75, OR-70.4, 95% confidence interval [CI] 42.8–115.9), immunosuppression (OR-4.8, 95% CI 3.4–6.7), and pregnancy (5 months or more, OR-82.9, 95% CI 53–129.6). Factors that were associated with a reduced risk for severe disease were vaccination status (patients vaccinated in the previous six months OR-0.6, 95% CI 0.4–0.8) and a prior episode of COVID-19 (OR-0.3, 95% CI 0.2–0.5). According to the model, patients who were in the 10th percentile of the risk severity score were considered at an increased risk for severe disease. The model accuracy was 88.7%. Conclusions: This model has allowed us to prioritize patients requiring closer follow-up by their physicians and outreach services, as well as identify those that are most likely to benefit from anti-viral treatment during the fifth wave of infection in Israel, dominated by the Omicron variant.

Artificial intelligence centric scientific research on COVID-19: an analysis based on scientometrics data

With the spread of the deadly coronavirus disease throughout the geographies of the globe, expertise from every field has been sought to fight the impact of the virus. The use of Artificial Intelligence (AI), especially, has been the center of attention due to its capability to produce trustworthy results in a reasonable time. As a result, AI centric based research on coronavirus (or COVID-19) has been receiving growing attention from different domains ranging from medicine, virology, and psychiatry etc. We present this comprehensive study that closely monitors the impact of the pandemic on global research activities related exclusively to AI. In this article, we produce highly informative insights pertaining to publications, such as the best articles, research areas, most productive and influential journals, authors, and institutions. Studies are made on top 50 most cited articles to identify the most influential AI subcategories. We also study the outcome of research from different geographic areas while identifying the research collaborations that have had an impact. This study also compares the outcome of research from the different countries around the globe and produces insights on the same.

The impact of COVID-19 restrictions and care home strategies on residents with dementia as experienced by family carers in Italy

OBJECTIVES

The COVID-19 pandemic and public health measures caused serious consequences for several population cohorts, including people with dementia in care homes and their families. The aim of this study was to explore the impact of COVID-19 on care home residents with dementia as experienced by family carers in Italy. Specifically, strategies implemented to overcome the pandemic's constraints, their influence upon care, and consequences for everyday life of residents with dementia and carers were investigated.

METHODS

Semi-structured interviews explored participants' experiences of the pandemic, its restrictions and the services' status during lockdown. Transcripts were analysed via thematic analysis.

RESULTS

26 family carers were interviewed. Three themes emerged: (1) COVID-19 restrictions negatively affected both residents with dementia and family carers, (2) Changing policies in care homes during COVID-19, and (3) Technology use in care homes during COVID-19. COVID-19 restrictions severely affected care home residents with dementia, disrupted their daily living, and accelerated their cognitive decline. Consequently carers' emotional burdens increased. Care home response strategies (safe visiting and digital solutions) were critical, though they were not enough to compensate for the lack of close in-person contacts.

CONCLUSIONS

Mixed evidence emerged about the feasibility of care home strategies and their associated benefits. To meet arising needs and possible future pandemic waves, there is a need for updated health strategies. These should prioritise a continuity of therapeutic activities and minimize negative effects on residents' quality of life, whilst incorporating feasible and accessible digital solutions to provide remote communication and psychological support for family carers.

Clinical Artificial Intelligence: Design Principles and Fallacies

Clinical artificial intelligence (AI)/machine learning (ML) is anticipated to offer new abilities in clinical decision support, diagnostic reasoning, precision medicine, clinical operational support, and clinical research, but careful concern is needed to ensure these technologies work effectively in the clinic. Here, we detail the clinical ML/AI design process, identifying several key questions and detailing several common forms of issues that arise with ML tools, as motivated by real-world examples, such that clinicians and researchers can better anticipate and correct for such issues in their own use of ML/AI techniques.

Mortality patterns among COVID-19 patients in two Saudi hospitals: Demographics, etiology, and treatment

Background

Saudi Arabia (SA) reported its first case of COVID-19 on 2 March 2020. Mortality varied nationwide; by April 14, 2020, Medina had 16% of SA's total COVID-19 cases and 40% of all COVID-19 deaths. A team of epidemiologists investigated to identify factors impacting survival.

Methods

We reviewed medical records from two hospitals: Hospital A in Medina and Hospital B in Dammam. All patients with a registered COVID-related death between March and May 1, 2020, were included. We collected data on demographics, chronic health conditions, clinical presentation, and treatment. We analyzed data using SPSS.

Results

We identified 76 cases: 38 cases from each hospital. More fatalities were among non-Saudis at Hospital A (89%) versus Hospital B (82%, p < 0.001). Hypertension prevalence was higher among cases at Hospital B (42%) versus Hospital A (21%) (p < 0.05). We found statistically significant differences (p < 0.05) in symptoms at initial presentation among cases at Hospital B versus Hospital A, including body temperature (38°C vs. 37°C), heart rate (104 bpm vs. 89 bpm), and regular breathing rhythms (61% vs. 55%). Fewer cases (50%) at Hospital A received heparin versus Hospital B (97%, p-value < 0.001).

Conclusion

Patients who died typically presented with more severe illnesses and were more likely to have underlying health conditions. Migrant workers may be at increased risk due to poorer baseline health and reluctance to seek care. This highlights the importance of cross-cultural outreach to prevent deaths. Health education efforts should be multilingual and accommodate all literacy levels.

A radiomics model development via the associations with genomics features in predicting axillary lymph node metastasis of breast cancer: a study based on a public database and single-centre verification

AIM

To evaluate the predictive performance of the radiomics model in predicting axillary lymph node (ALN) metastasis through the associations between radiomics features and genomic features in patients with breast cancer.

MATERIALS AND METHODS

Patients with breast cancer were enrolled retrospectively from a public database (111 patients as training group) and one hospital (15 patients as external validation group). The genomics features from transcriptome data and radiomics features from dynamic contrast-enhanced magnetic resonance imaging (MRI) were collected. Firstly, overlapping genes were identified using the Kyoto Encyclopedia of Genes and Genomes and differentially expressed gene analysis, while radiomics features were reduced using a data-driven method. Then, the associations between overlapping genes and retained radiomics features were assessed to obtain key pairs of radiomics-genomics features. Furthermore, the least absolute shrinkage and selection operator (LASSO) algorithm was used to detect the key-pairs features. Finally, radiomics and genomics models were constructed to predict ALN metastasis.

RESULTS

After using the hybrid data- and gene-driven selection method, key pairs of features were detected, which consisted of six radiomic features associated with four genomic features. The radiomics model exhibited comparable performance to the genomics model in predicting ALN metastasis (radiomic model: area under the curve [AUC] = 0.71, sensitivity = 77%, specificity = 56%; genomic model: AUC = 0.72, sensitivity = 85%, specificity = 74%). The four genomic features were enriched in six pathways and related to metabolism and human diseases.

CONCLUSION

The radiomics model established using the gene-driven hybrid selection method could predict ALN metastasis in breast cancer, which showed comparable performance to the genomics model.

Tracking Covid-19 cases and deaths in the United States: metrics of pandemic progression derived from a queueing framework

We analyze the progression of COVID-19 in the United States over a nearly one-year period beginning March 1, 2020 with a novel metric motivated by queueing models, tracking partial-average day-of-event and cumulative probability distributions for events, where events are points in time when new cases and new deaths are reported. The partial average represents the average day of all events preceding a point of time, and is an indicator as to whether the pandemic is accelerating or decelerating in the context of the entire history of the pandemic. The measure supplements traditional metrics, and also enables direct comparisons of case and death histories on a common scale. We also compare methods for estimating actual infections and deaths to assess the timing and dynamics of the pandemic by location. Three example states are graphically compared as functions of date, as well as Hong Kong as an example that experienced a pronounced recent wave of the pandemic. In addition, statistics are compared for all 50 states. Over the period studied, average case day and average death day varied by two to five months among the 50 states, depending on data source, with the earliest averages in New York and surrounding states, as well as Louisiana.

Validation of a specialized evaluation system for COVID-19 in Japan: A retrospective, multicenter cohort study

INTRODUCTION

Evaluation of a severity grade (SG) is important to classify patients for efficient use of limited medical resources. This study validates two existing evaluation systems for the prevention of the coronavirus disease 2019 (COVID-19) in Japan: a criterion of SG and a list of 14 specialized underlying diseases (SUDs).

METHODS

A retrospective cohort was created using electronic medical records from 18 research institutes. The cohort includes 6,050 COVID-19 patients with two types of diagnosis information as follows: SG at hospitalization among mild, moderate I, moderate II, and severe and aggravation after hospitalization.

RESULTS

A crude mortality rate and an aggravation rate increased by the worsening of SG in the COVID-19 cohort. The transition of the aggravation rate was notable for COVID-19 patients with SUD. A conditional probability of the mortality given the aggravation in the COVID-19 cohort was 87.4% compared to mild or moderate patients (approximately 21%-45%) who have the possibility of the aggravation. An odds ratio of the mortality and aggravation information about the SUD list was higher than other variables.

CONCLUSIONS

We demonstrated the possibility of improving the criteria of SG by including the SUD list for more effective operation of the criteria of SG. Furthermore, we demonstrated the importance of the prevention of the aggravation based on the conditional probability, and the possibility of predicting the aggravation using the risk factors.

Implementation of a digital early warning score (NEWS2) in a cardiac specialist and general hospital settings in the COVID-19 pandemic: a qualitative study

OBJECTIVES

To evaluate implementation of digital National Early Warning Score 2 (NEWS2) in a cardiac care setting and a general hospital setting in the COVID-19 pandemic.

DESIGN

Thematic analysis of qualitative semistructured interviews using the non-adoption, abandonment, scale-up, spread, sustainability framework with purposefully sampled nurses and managers, as well as online surveys from March to December 2021.

SETTINGS

Specialist cardiac hospital (St Bartholomew's Hospital) and general teaching hospital (University College London Hospital, UCLH).

PARTICIPANTS

Eleven nurses and managers from cardiology, cardiac surgery, oncology and intensive care wards (St Bartholomew's) and medical, haematology and intensive care wards (UCLH) were interviewed and 67 were surveyed online.

RESULTS

Three main themes emerged: (1) implementing NEWS2 challenges and supports; (2) value of NEWS2 to alarm, escalate and during the pandemic; and (3) digitalisation: electronic health record (EHR) integration and automation. The value of NEWS2 was partly positive in escalation, yet there were concerns by nurses who undervalued NEWS2 particularly in cardiac care. Challenges, like clinicians' behaviours, lack of resources and training and the perception of NEWS2 value, limit the success of this implementation. Changes in guidelines in the pandemic have led to overlooking NEWS2. EHR integration and automated monitoring are improvement solutions that are not fully employed yet.

CONCLUSION

Whether in specialist or general medical settings, the health professionals implementing early warning score in healthcare face cultural and system-related challenges to adopting NEWS2 and digital solutions. The validity of NEWS2 in specialised settings and complex conditions is not yet apparent and requires comprehensive validation. EHR integration and automation are powerful tools to facilitate NEWS2 if its principles are reviewed and rectified, and resources and training are accessible. Further examination of implementation from the cultural and automation domains is needed.

Impact of days elapsed from the onset of symptoms to hospitalization in COVID-19 in-hospital mortality: time matters

BACKGROUND

COVID-19 shows different clinical and pathophysiological stages over time. The effect of days elapsed from the onset of symptoms (DEOS) to hospitalization on COVID-19 prognostic factors remains uncertain. We analyzed the impact on mortality of DEOS to hospitalization and how other independent prognostic factors perform when taking this time elapsed into account.

METHODS

This retrospective, nationwide cohort study, included patients with confirmed COVID-19 from February 20th and May 6th, 2020. The data was collected in a standardized online data capture registry. Univariate and multivariate COX-regression were performed in the general cohort and the final multivariate model was subjected to a sensitivity analysis in an early presenting (EP; <5 DEOS) and late presenting (LP; ≥5 DEOS) group.

RESULTS

7,915 COVID-19 patients were included in the analysis, 2,324 in the EP and 5,591 in the LP group. DEOS to hospitalization was an independent prognostic factor of in-hospital mortality in the multivariate Cox regression model along with other 9 variables. Each DEOS increment accounted for a 4,3% mortality risk reduction (HR 0.957; 95% CI 0.93 - 0.98). Regarding variations in other mortality predictors in the sensitivity analysis, the Charlson Comorbidity Index only remained significant in the EP group while D-dimer only remained significant in the LP group.

CONCLUSION

When caring for COVID-19 patients, DEOS to hospitalization should be considered as their need for early hospitalization confers a higher risk of mortality. Different prognostic factors vary over time and should be studied within a fixed timeframe of the disease.