Multimodal data fusion using sparse canonical correlation analysis and cooperative learning: a COVID-19 cohort study.

Through technological innovations, patient cohorts can be examined from multiple views with high-dimensional, multiscale biomedical data to classify clinical phenotypes and predict outcomes. Here, we aim to present our approach for analyzing multimodal data using unsupervised and supervised sparse linear methods in a COVID-19 patient cohort. This prospective cohort study of 149 adult patients was conducted in a tertiary care academic center. First, we used sparse canonical correlation analysis (CCA) to identify and quantify relationships across different data modalities, including viral genome sequencing, imaging, clinical data, and laboratory results. Then, we used cooperative learning to predict the clinical outcome of COVID-19 patients: Intensive care unit admission. We show that serum biomarkers representing severe disease and acute phase response correlate with original and wavelet radiomics features in the LLL frequency channel (cor(Xu1, Zv1) = 0.596, p value < 0.001). Among radiomics features, histogram-based first-order features reporting the skewness, kurtosis, and uniformity have the lowest negative, whereas entropy-related features have the highest positive coefficients. Moreover, unsupervised analysis of clinical data and laboratory results gives insights into distinct clinical phenotypes. Leveraging the availability of global viral genome databases, we demonstrate that the Word2Vec natural language processing model can be used for viral genome encoding. It not only separates major SARS-CoV-2 variants but also allows the preservation of phylogenetic relationships among them. Our quadruple model using Word2Vec encoding achieves better prediction results in the supervised task. The model yields area under the curve (AUC) and accuracy values of 0.87 and 0.77, respectively. Our study illustrates that sparse CCA analysis and cooperative learning are powerful techniques for handling high-dimensional, multimodal data to investigate multivariate associations in unsupervised and supervised tasks.

Multimodal Biomedical Data Fusion Using Sparse Canonical Correlation Analysis and Cooperative Learning: A Cohort Study on COVID-19.

Through technological innovations, patient cohorts can be examined from multiple views with high-dimensional, multiscale biomedical data to classify clinical phenotypes and predict outcomes. Here, we aim to present our approach for analyzing multimodal data using unsupervised and supervised sparse linear methods in a COVID-19 patient cohort. This prospective cohort study of 149 adult patients was conducted in a tertiary care academic center. First, we used sparse canonical correlation analysis (CCA) to identify and quantify relationships across different data modalities, including viral genome sequencing, imaging, clinical data, and laboratory results. Then, we used cooperative learning to predict the clinical outcome of COVID-19 patients. We show that serum biomarkers representing severe disease and acute phase response correlate with original and wavelet radiomics features in the LLL frequency channel (corr(Xu1, Zv1) = 0.596, p-value < 0.001). Among radiomics features, histogram-based first-order features reporting the skewness, kurtosis, and uniformity have the lowest negative, whereas entropy-related features have the highest positive coefficients. Moreover, unsupervised analysis of clinical data and laboratory results gives insights into distinct clinical phenotypes. Leveraging the availability of global viral genome databases, we demonstrate that the Word2Vec natural language processing model can be used for viral genome encoding. It not only separates major SARS-CoV-2 variants but also allows the preservation of phylogenetic relationships among them. Our quadruple model using Word2Vec encoding achieves better prediction results in the supervised task. The model yields area under the curve (AUC) and accuracy values of 0.87 and 0.77, respectively. Our study illustrates that sparse CCA analysis and cooperative learning are powerful techniques for handling high-dimensional, multimodal data to investigate multivariate associations in unsupervised and supervised tasks.

Diagnostic performance and longitudinal analysis of fungal biomarkers in COVID-19 associated pulmonary aspergillosis.

Objectives: Galactomannan lateral flow assay (GM-LFA) is a reliable test for COVID-19 associated pulmonary aspergillosis (CAPA) diagnosis. We aimed to assess the diagnostic performance of GM-LFA with different case definitions, the association between the longitudinal measurements of serum GM-ELISA, GM-LFA, and the risk of death. Methods: Serum and nondirected bronchial lavage (NBL) samples were periodically collected. The sensitivity and specificity analysis for GM-LFA was done in different time periods. Longitudinal analysis was done with the joint model framework. Results: A total of 207 patients were evaluated. On the day of CAPA diagnosis, serum GM-LFA had a sensitivity of 42 % (95 % CI: 23-63) and specificity of 82 % (95 % CI: 78-84), while NBL GM-LFA had a sensitivity of 73 % (95 % CI: 45-92), specificity of 85 % (95 % CI: 76-91) for CAPA. Sensitivity decreased through the following days in both samples. Univariate joint model analysis showed that increasing GM-LFA and GM-ELISA levels were associated with increased mortality, and that effect remained same with serum GM-ELISA in multivariate joint model analysis. Conclusion: GM-LFA, particularly in NBL samples, seems to be a reliable method for CAPA diagnosis. For detecting patients with higher risk of mortality, longitudinal measurement of serum GM-ELISA can be useful.

A case of Legionnaires' disease with severe rhabdomyolysis misdiagnosed as COVID-19.

Background: COVID-19 case numbers have begun to rise with the recently reported Omicron variant. In the last two years, COVID-19 is the first diagnosis that comes to mind when a patient is admitted with respiratory symptoms and pulmonary ground-glass opacities. However, other causes should be kept in mind as well. Here we present a case of Legionnaires' disease misdiagnosed as COVID-19. Case presentation: A 48-year-old male was admitted with complaints of dry cough and dyspnea. Chest computed-tomography revealed bilateral ground-glass opacities; therefore, a preliminary diagnosis of COVID-19 was made. However, two consecutive COVID PCR tests were negative and the patient deteriorated rapidly. As severe rhabdomyolysis and acute renal failure were present, Legionnaires' disease was suspected. Urine antigen test for Legionella and Legionella pneumophila PCR turned out to be positive. The patient responded dramatically to intravenous levofloxacin and was discharged successfully. Discussion: Legionnaires' disease and COVID-19 may present with similar signs and symptoms. They also share common risk factors and radiological findings. Conclusions: Shared clinical and radiological features between COVID-19 and other causes of acute respiratory failure pose a challenge in diagnosis. Other causes such as Legionnaires' disease must be kept in mind and appropriate diagnostic tests should be performed accordingly.

Community-acquired pneumonia - An EFIM guideline critical appraisal adaptation for internists.

BACKGROUND: In real-life settings, guidelines frequently cannot be followed since many patients are multimorbid and/or elderly or have other complicating conditions which carry an increased risk of drug-drug interactions. This document aimed to adapt recommendations from existing clinical practice guidelines (CPGs) to assist physicians' decision-making processes concerning specific and complex scenarios related to acute CAP. METHODS: The process for the adaptation procedure started with the identification of unsolved clinical questions (PICOs) in patients with CAP and continued with critically appraising the updated existing CPGs and choosing the recommendations, which are most applicable to these specific scenarios. RESULTS: Seventeen CPGs were appraised to address five PICOs. Twenty-seven recommendations were endorsed based on 7 high, 9 moderate, 10 low, and 1 very low-quality evidence. The most valid recommendations applicable to the clinical practice were the following ones: Respiratory virus testing is strongly recommended during periods of increased respiratory virus activity. Assessing the severity with a validated prediction rule to discriminate where to treat the patient is strongly recommended along with reassessing the patient periodically for improvement as expected. In adults with multiple comorbidities, polypharmacy, or advanced age, it is strongly recommended to check for possible drug interactions before starting treatment. Strong graded recommendations exist on antibiotic treatment and its duration. Recommendations on the use of biomarkers such as C-reactive protein or procalcitonin to improve severity assessment are reported. CONCLUSION: This document provides a simple and reliable updated guide for clinical decision-making in the management of complex patients with multimorbidity and CAP in the real-life setting.

A screening study for COVID-19-associated pulmonary aspergillosis in critically ill patients during the third wave of the pandemic.

BACKGROUND: COVID-19-associated pulmonary aspergillosis (CAPA) has been reported as an important cause of mortality in critically ill patients with an incidence rate ranging from 5% to 35% during the first and second pandemic waves. OBJECTIVES: We aimed to evaluate the incidence, risk factors for CAPA by a screening protocol and outcome in the critically ill patients during the third wave of the pandemic. PATIENTS/METHODS: This prospective cohort study was conducted in two intensive care units (ICU) designated for patients with COVID-19 in a tertiary care university hospital between 18 November 2020 and 24 April 2021. SARS-CoV-2 PCR-positive adult patients admitted to the ICU with respiratory failure were included in the study. Serum and respiratory samples were collected periodically from ICU admission up to CAPA diagnosis, patient discharge or death. ECMM/ISHAM consensus criteria were used to diagnose and classify CAPA cases. RESULTS: A total of 302 patients were admitted to the two ICUs during the study period, and 213 were included in the study. CAPA was diagnosed in 43 (20.1%) patients (12.2% probable, 7.9% possible). In regression analysis, male sex, higher SOFA scores at ICU admission, invasive mechanical ventilation and longer ICU stay were significantly associated with CAPA development. Overall ICU mortality rate was higher significantly in CAPA group compared to those with no CAPA (67.4% vs 29.4%, p < .001). CONCLUSIONS: One fifth of critically ill patients in COVID-19 ICUs developed CAPA, and this was associated with a high mortality.

Prediction of COVID-19 deterioration in high-risk patients at diagnosis: an early warning score for advanced COVID-19 developed by machine learning.

PURPOSE: While more advanced COVID-19 necessitates medical interventions and hospitalization, patients with mild COVID-19 do not require this. Identifying patients at risk of progressing to advanced COVID-19 might guide treatment decisions, particularly for better prioritizing patients in need for hospitalization. METHODS: We developed a machine learning-based predictor for deriving a clinical score identifying patients with asymptomatic/mild COVID-19 at risk of progressing to advanced COVID-19. Clinical data from SARS-CoV-2 positive patients from the multicenter Lean European Open Survey on SARS-CoV-2 Infected Patients (LEOSS) were used for discovery (2020-03-16 to 2020-07-14) and validation (data from 2020-07-15 to 2021-02-16). RESULTS: The LEOSS dataset contains 473 baseline patient parameters measured at the first patient contact. After training the predictor model on a training dataset comprising 1233 patients, 20 of the 473 parameters were selected for the predictor model. From the predictor model, we delineated a composite predictive score (SACOV-19, Score for the prediction of an Advanced stage of COVID-19) with eleven variables. In the validation cohort (n = 2264 patients), we observed good prediction performance with an area under the curve (AUC) of 0.73 ± 0.01. Besides temperature, age, body mass index and smoking habit, variables indicating pulmonary involvement (respiration rate, oxygen saturation, dyspnea), inflammation (CRP, LDH, lymphocyte counts), and acute kidney injury at diagnosis were identified. For better interpretability, the predictor was translated into a web interface. CONCLUSION: We present a machine learning-based predictor model and a clinical score for identifying patients at risk of developing advanced COVID-19.

A rare case of necrotizing fasciitis of the abdominal wall due to Hungatella effluvii and Streptococcus constellatus.

We report a rare case of necrotizing fasciitis of the abdominal wall caused by Hungatella effluvii and Streptococcus constellatus. Necrotizing fasciitis has high mortality, so early diagnosis and aggressive treatment are essential for good clinical outcome. Identification of the microbial contribution to these infections is crucial for targeted antibiotic treatment.

Projecting the course of COVID-19 in Turkey: A probabilistic modeling approach

Background/aim: The COVID-19 pandemic originated in Wuhan, China, in December 2019 and became one of the worst global health crises ever. While struggling with the unknown nature of this novel coronavirus, many researchers and groups attempted to project the progress of the pandemic using empirical or mechanistic models, each one having its drawbacks. The first confirmed cases were announced early in March, and since then, serious containment measures have taken place in Turkey. Materials and methods: Here, we present a different approach, a Bayesian negative binomial multilevel model with mixed effects, for the projection of the COVID-19 pandemic and we apply this model to the Turkish case. The model source code is available at https:// github.com/kansil/covid-19. We predicted the confirmed daily cases and cumulative numbers from June 6th to June 26th with 80%, 95%, and 99% prediction intervals (PI). Results: Our projections showed that if we continued to comply with the measures and no drastic changes were seen in diagnosis or management protocols, the epidemic curve would tend to decrease in this time interval. Also, the predictive validity analysis suggests that the proposed model projections should have a PI around 95% for the first 12 days of the projections. Conclusion: We expect that drastic changes in the course of COVID-19 in Turkey will cause the model to suffer in predictive validity, and this can be used to monitor the epidemic. We hope that the discussion on these projections and the limitations of the epidemiological forecasting will be beneficial to the medical community, and policy makers.

Predictive value of cytokine/chemokine responses for the disease severity and management in children and adult cases with COVID-19.

The disease course of children with coronavirus disease 2019 (COVID-19) seems milder as compared with adults, however, actual reason of the pathogenesis still remains unclear. There is a growing interest on possible relationship between pathogenicity or disease severity and biomarkers including cytokines or chemokines. We wondered whether these biomarkers could be used for the prediction of the prognosis of COVID-19 and improving our understanding on the variations between pediatric and adult cases with COVID-19. The acute phase serum levels of 25 cytokines and chemokines in the serum samples from 60 COVID-19 pediatric (n = 30) and adult cases (n = 30) including 20 severe or critically ill, 25 moderate and 15 mild patients and 30 healthy pediatric (n = 15) and adult (n = 15) volunteers were measured using commercially available fluorescent bead immunoassay and analyzed in combination with clinical data. Interferon gamma-induced protein 10 (IP-10) and macrophage inflammatory protein (MIP)-3ß levels were significantly higher in patient cohort including pediatric and adult cases with COVID-19 when compared with all healthy volunteers (p ≤ .001 in each) and whereas IP-10 levels were significantly higher in both pediatric and adult cases with severe disease course, MIP-3ß were significantly lower in healthy controls. Additionally, IP-10 is an independent predictor for disease severity, particularly in children and interleukin-6 seems a relatively good predictor for disease severity in adults. IP-10 and MIP-3ß seem good research candidates to understand severity of COVID-19 in both pediatric and adult population and to investigate possible pathophysiological mechanism of COVID-19.