Feasibility of Predicting Surgical Duration in Endometriosis Using Numerical Multi-Scoring System of Endometriosis (NMS-E).

BACKGROUND: Endometriosis is a multifaceted gynecological condition that poses diagnostic challenges and affects a significant number of women worldwide, leading to pain, infertility, and a reduction in patient quality of life (QoL). Traditional diagnostic methods, such as the revised American Society for Reproductive Medicine (r-ASRM) classification, have limitations, particularly in preoperative settings. The Numerical Multi-Scoring System of Endometriosis (NMS-E) has been proposed to address these shortcomings by providing a comprehensive preoperative diagnostic tool that integrates findings from pelvic examinations and transvaginal ultrasonography. METHODS: This retrospective study aims to validate the effectiveness of the NMS-E in predicting surgical outcomes and correlating with the severity of endometriosis. Data from 111 patients at Nippon Medical School Hospital were analyzed to determine the correlation between NMS-E scores, including E-score-a severity indicator-traditional scoring systems, surgical duration, blood loss, and clinical symptoms. This study also examined the need to refine parameters for deep endometriosis within the NMS-E to enhance its predictive accuracy for disease severity. RESULTS: The mean age of the patient cohort was 35.1 years, with the majority experiencing symptoms such as dysmenorrhea, dyspareunia, and chronic pelvic pain. A statistically significant positive correlation was observed between the NMS-E's E-score and the severity of endometriosis, particularly in predicting surgical duration (Spearman correlation coefficient: 0.724, p < 0.01) and blood loss (coefficient: 0.400, p < 0.01). The NMS-E E-score also correlated strongly with the r-ASRM scores (coefficient: 0.758, p < 0.01), exhibiting a slightly more excellent predictive value for surgical duration than the r-ASRM scores alone. Refinements in the methodology for scoring endometriotic nodules in uterine conditions improved the predictive accuracy for surgical duration (coefficient: 0.752, p < 0.01). CONCLUSIONS: Our findings suggest that the NMS-E represents a valuable preoperative diagnostic tool for endometriosis, effectively correlating with the disease's severity and surgical outcomes. Incorporating the NMS-E into clinical practice could significantly enhance the management of endometriosis by addressing current diagnostic limitations and guiding surgical planning.

A Machine Learning Model for the Prediction of COVID-19 Severity Using RNA-Seq, Clinical, and Co-Morbidity Data.

The premise for this study emanated from the need to understand SARS-CoV-2 infections at the molecular level and to develop predictive tools for managing COVID-19 severity. With the varied clinical outcomes observed among infected individuals, creating a reliable machine learning (ML) model for predicting the severity of COVID-19 became paramount. Despite the availability of large-scale genomic and clinical data, previous studies have not effectively utilized multi-modality data for disease severity prediction using data-driven approaches. Our primary goal is to predict COVID-19 severity using a machine-learning model trained on a combination of patients' gene expression, clinical features, and co-morbidity data. Employing various ML algorithms, including Logistic Regression (LR), XGBoost (XG), Naïve Bayes (NB), and Support Vector Machine (SVM), alongside feature selection methods, we sought to identify the best-performing model for disease severity prediction. The results highlighted XG as the superior classifier, with 95% accuracy and a 0.99 AUC (Area Under the Curve), for distinguishing severity groups. Additionally, the SHAP analysis revealed vital features contributing to prediction, including several genes such as COX14, LAMB2, DOLK, SDCBP2, RHBDL1, and IER3-AS1. Notably, two clinical features, the absolute neutrophil count and Viremia Categories, emerged as top contributors. Integrating multiple data modalities has significantly improved the accuracy of disease severity prediction compared to using any single modality. The identified features could serve as biomarkers for COVID-19 prognosis and patient care, allowing clinicians to optimize treatment strategies and refine clinical decision-making processes for enhanced patient outcomes.

Integrating Explainable Machine Learning in Clinical Decision Support Systems: Study Involving a Modified Design Thinking Approach.

BACKGROUND: Though there has been considerable effort to implement machine learning (ML) methods for health care, clinical implementation has lagged. Incorporating explainable machine learning (XML) methods through the development of a decision support tool using a design thinking approach is expected to lead to greater uptake of such tools. OBJECTIVE: This work aimed to explore how constant engagement of clinician end users can address the lack of adoption of ML tools in clinical contexts due to their lack of transparency and address challenges related to presenting explainability in a decision support interface. METHODS: We used a design thinking approach augmented with additional theoretical frameworks to provide more robust approaches to different phases of design. In particular, in the problem definition phase, we incorporated the nonadoption, abandonment, scale-up, spread, and sustainability of technology in health care (NASSS) framework to assess these aspects in a health care network. This process helped focus on the development of a prognostic tool that predicted the likelihood of admission to an intensive care ward based on disease severity in chest x-ray images. In the ideate, prototype, and test phases, we incorporated a metric framework to assess physician trust in artificial intelligence (AI) tools. This allowed us to compare physicians' assessments of the domain representation, action ability, and consistency of the tool. RESULTS: Physicians found the design of the prototype elegant, and domain appropriate representation of data was displayed in the tool. They appreciated the simplified explainability overlay, which only displayed the most predictive patches that cumulatively explained 90% of the final admission risk score. Finally, in terms of consistency, physicians unanimously appreciated the capacity to compare multiple x-ray images in the same view. They also appreciated the ability to toggle the explainability overlay so that both options made it easier for them to assess how consistently the tool was identifying elements of the x-ray image they felt would contribute to overall disease severity. CONCLUSIONS: The adopted approach is situated in an evolving space concerned with incorporating XML or AI technologies into health care software. We addressed the alignment of AI as it relates to clinician trust, describing an approach to wire framing and prototyping, which incorporates the use of a theoretical framework for trust in the design process itself. Moreover, we proposed that alignment of AI is dependent upon integration of end users throughout the larger design process. Our work shows the importance and value of engaging end users prior to tool development. We believe that the described approach is a unique and valuable contribution that outlines a direction for ML experts, user experience designers, and clinician end users on how to collaborate in the creation of trustworthy and usable XML-based clinical decision support tools.

Thrombospondin 1 enhances systemic inflammation and disease severity in acute-on-chronic liver failure.

BACKGROUND: The key role of thrombospondin 1 (THBS1) in the pathogenesis of acute-on-chronic liver failure (ACLF) is unclear. Here, we present a transcriptome approach to evaluate THBS1 as a potential biomarker in ACLF disease pathogenesis. METHODS: Biobanked peripheral blood mononuclear cells (PBMCs) from 330 subjects with hepatitis B virus (HBV)-related etiologies, including HBV-ACLF, liver cirrhosis (LC), and chronic hepatitis B (CHB), and normal controls (NC) randomly selected from the Chinese Group on the Study of Severe Hepatitis B (COSSH) prospective multicenter cohort underwent transcriptome analyses (ACLF = 20; LC = 10; CHB = 10; NC = 15); the findings were externally validated in participants from COSSH cohort, an ACLF rat model and hepatocyte-specific THBS1 knockout mice. RESULTS: THBS1 was the top significantly differentially expressed gene in the PBMC transcriptome, with the most significant upregulation in ACLF, and quantitative polymerase chain reaction (ACLF = 110; LC = 60; CHB = 60; NC = 45) was used to verify that THBS1 expression corresponded to ACLF disease severity outcome, including inflammation and hepatocellular apoptosis. THBS1 showed good predictive ability for ACLF short-term mortality, with an area under the receiver operating characteristic curve (AUROC) of 0.8438 and 0.7778 at 28 and 90 days, respectively. Enzyme-linked immunosorbent assay validation of the plasma THBS1 using an expanded COSSH cohort subjects (ACLF = 198; LC = 50; CHB = 50; NC = 50) showed significant correlation between THBS1 with ALT and γ-GT (P = 0.01), and offered a similarly good prognostication predictive ability (AUROC = 0.7445 and 0.7175) at 28 and 90 days, respectively. ACLF patients with high-risk short-term mortality were identified based on plasma THBS1 optimal cut-off value (< 28 µg/ml). External validation in ACLF rat serum and livers confirmed the functional association between THBS1, the immune response and hepatocellular apoptosis. Hepatocyte-specific THBS1 knockout improved mouse survival, significantly repressed major inflammatory cytokines, enhanced the expression of several anti-inflammatory mediators and impeded hepatocellular apoptosis. CONCLUSIONS: THBS1 might be an ACLF disease development-related biomarker, promoting inflammatory responses and hepatocellular apoptosis, that could provide clinicians with a new molecular target for improving diagnostic and therapeutic strategies.

Severity-stratification of interstitial lung disease by deep learning enabled assessment and quantification of lesion indicators from HRCT images.

BACKGROUND: Interstitial lung disease (ILD) represents a group of chronic heterogeneous diseases, and current clinical practice in assessment of ILD severity and progression mainly rely on the radiologist-based visual screening, which greatly restricts the accuracy of disease assessment due to the high inter- and intra-subjective observer variability. OBJECTIVE: To solve these problems, in this work, we propose a deep learning driven framework that can assess and quantify lesion indicators and outcome the prediction of severity of ILD. METHODS: In detail, we first present a convolutional neural network that can segment and quantify five types of lesions including HC, RO, GGO, CONS, and EMPH from HRCT of ILD patients, and then we conduct quantitative analysis to select the features related to ILD based on the segmented lesions and clinical data. Finally, a multivariate prediction model based on nomogram to predict the severity of ILD is established by combining multiple typical lesions. RESULTS: Experimental results showed that three lesions of HC, RO, and GGO could accurately predict ILD staging independently or combined with other HRCT features. Based on the HRCT, the used multivariate model can achieve the highest AUC value of 0.755 for HC, and the lowest AUC value of 0.701 for RO in stage I, and obtain the highest AUC value of 0.803 for HC, and the lowest AUC value of 0.733 for RO in stage II. Additionally, our ILD scoring model could achieve an average accuracy of 0.812 (0.736 - 0.888) in predicting the severity of ILD via cross-validation. CONCLUSIONS: In summary, our proposed method provides effective segmentation of ILD lesions by a comprehensive deep-learning approach and confirms its potential effectiveness in improving diagnostic accuracy for clinicians.

Construction and Validation of a Nomogram Model to Predict the Severity of Mycoplasma pneumoniae Pneumonia in Children.

Background: This study aimed to develop a nomogram model for early prediction of the severe Mycoplasma pneumoniae pneumonia (MPP) in children. Methods: A retrospective analysis was conducted on children with MPP, classifying them into severe and general MPP groups. The risk factors for severe MPP were identified using Logistic Stepwise Regression Analysis, followed by Multivariate Regression Analysis to construct the nomogram model. The model's discrimination was evaluated using a receiver operating characteristic curve, its calibration with a calibration curve, and the results were visualized using the Hosmer-Lemeshow goodness-of-fit test. Results: Univariate analysis revealed that age, duration of fever, length of hospital-stay, decreased sounds of breathing, respiratory rate, hypokalemia, and incidence of co-infection were significantly different between severe and general MPP. Significant differences (p < 0.05) were also observed in C-reactive protein, procalcitonin, peripheral blood lymphocyte count, neutrophil-to-lymphocyte ratio, ferritin, lactate dehydrogenase, alanine aminotransferase, interleukin-6, immunoglobulin A, and CD4+ T cells between the two groups. Logistic Stepwise Regression Analysis showed that age, decreased sounds of breathing, respiratory rate, duration of fever (OR = 1.131; 95% CI: 1.060-1.207), length of hospital-stay (OR = 1.415; 95% CI: 1.287-1.555), incidence of co-infection (OR = 1.480; 95% CI: 1.001-2.189), ferritin level (OR = 1.003; 95% CI: 1.001-1.006), and LDH level (OR = 1.003; 95% CI: 1.001-1.005) were identified as risk factors for the development of severe MPP (p < 0.05 in all). The above factors were applied in constructing a nomogram model that was subsequently tested with 0.862 of the area under the ROC curve. Conclusion: Age, decreased sound of breathing, respiratory rate, duration of fever, length of hospital-stay, co-infection with other pathogen(s), ferritin level, and LDH level were the significant contributors for the establishment of a nomogram model to predict the severity of MPP in children.

Automatic Identification and Severity Classification of Retinal Biomarkers in SD-OCT Using Dilated Depthwise Separable Convolution ResNet with SVM Classifier.

PURPOSE: Diagnosis of Uveitic Macular Edema (UME) using Spectral Domain OCT (SD-OCT) is a promising method for early detection and monitoring of sight-threatening visual impairment. Viewing multiple B-scans and identifying biomarkers is challenging and time-consuming for clinical practitioners. To overcome these challenges, this paper proposes an image classification hybrid framework for predicting the presence of biomarkers such as intraretinal cysts (IRC), hyperreflective foci (HRF), hard exudates (HE) and neurosensory detachment (NSD) in OCT B-scans along with their severity. METHODS: A dataset of 10880 B-scans from 85 Uveitic patients is collected and graded by two board-certified ophthalmologists for the presence of biomarkers. A novel image classification framework, Dilated Depthwise Separable Convolution ResNet (DDSC-RN) with SVM classifier, is developed to achieve network compression with a larger receptive field that captures both low and high-level features of the biomarkers without loss of classification accuracy. The severity level of each biomarker is predicted from the feature map, extracted by the proposed DDSC-RN network. RESULTS: The proposed hybrid model is evaluated using ground truth labels from the hospital. The deep learning model initially, identified the presence of biomarkers in B-scans. It achieved an overall accuracy of 98.64%, which is comparable to the performance of other state-of-the-art models, such as DRN-C-42 and ResNet-34. The SVM classifier then predicted the severity of each biomarker, achieving an overall accuracy of 89.3%. CONCLUSIONS: A new hybrid model accurately identifies four retinal biomarkers on a tissue map and predicts their severity. The model outperforms other methods for identifying multiple biomarkers in complex OCT B-scans. This helps clinicians to screen multiple B-scans of UME more effectively, leading to better treatment outcomes.

The National Early Warning Score 2 with Age and Body Mass Index (NEWS2 Plus) to Determine Patients with Severe COVID-19 Pneumonia.

(1) Background: Early identification of severe coronavirus disease 2019 (COVID-19) pneumonia at the initial phase of hospitalization is very crucial. To address this, we validated and updated the National Early Warning Score 2 (NEWS2) for this purpose. (2) Methods: We conducted a study on adult patients with COVID-19 infection in Chiang Mai, Thailand, between May 2021 and October 2021. (3) Results: From a total of 725 COVID-19 adult patients, 350 (48.3%) patients suffered severe COVID-19 pneumonia. In determining severe COVID-19 pneumonia, NEWS2 and NEWS2 + Age + BMI (NEWS2 Plus) showed the C-statistic values of 0.798 (95% CI, 0.767-0.830) and 0.821 (95% CI, 0.791-0.850), respectively. The C-statistic values of NEWS2 Plus were significantly improved compared to those of NEWS2 alone (p = 0.012). Utilizing a cut-off point of five, NEWS2 Plus exhibited better sensitivity and negative predictive value than the traditional NEWS2, with values of 99.7% vs. 83.7% and 98.9% vs. 80.7%, respectively. (4) Conclusions: The incorporation of age and BMI into the traditional NEWS2 score enhanced the efficacy of determining severe COVID-19 pneumonia. Physicians can rely on NEWS2 Plus (NEWS2 + Age + BMI) as a more effective decision-making tool for triaging COVID-19 patients during early hospitalization.

Prediction of the severity of exceeding design traffic loads on highway bridges.

Being a driver of failure consequences, forecasting the severity of events where design traffic load limits on bridges have been exceeded (DLEEs) is fundamental for road safety. Previous research has focused on estimating failure consequences by direct and indirect cost metrics. Only recently has research assessed severity unconventionally, in which the type of DLEEs was predicted by applying econometric models through Binomial Logistic Regression (BLR). Since machine learning models using Artificial Neural Networks (ANN) have not yet been explored, this study will enhance the literature as follows. First, two different 'severity' models were set up as a function of bridge-side, temporal-context, and traffic load hazard variables. Whilst the former relied on a BLR, the latter used an ANN. Second, the performance of these models was assessed using confusion matrixes, some performance indicators, and a cross-entropy parameter. Raw Weigh-In-Motion data on 7.4 M+ individual vehicle transits on a bridge along a primary roadway in Brescia (Italy) were processed. Although a similarly strong performance was achieved for BLR and ANN, the results indicated that ANN was able to predict severity records with a higher level of confidence than BLR on the case study dataset, with the cross-entropy of the ANN less than one third of that of the BLR. These analyses can support road authority traffic management to safeguard bridges from traffic load hazards. Finally, this study recommends future developments, such as considering the structural effects of traffic loads in the modelling, prioritizing traffic management actions among bridges at network level, and exploring the impact of ANN models in risk assessment.

Evaluating transport conditions of conventional, widely used EDTA blood tubes for gene expression analysis in comparison to expensive, specialized PAXgene tubes in preparedness for radiological and nuclear events.

PURPOSE: Gene expression (GE) analysis of a radio-sensitive gene set (FDXR, DDB2, WNT3, POU2AF1) has been introduced in the last decade as an early and high-throughput prediction tool of later developing acute hematologic radiation syndrome (H-ARS) severity. The use of special tubes for RNA extraction from peripheral whole blood (PAXgene) represent an established standard in GE studies, although uncommonly used in clinics and not immediately available in the quantities needed in radiological/nuclear (R/N) incidents. On the other hand, EDTA blood tubes are widely utilized in clinical practice. MATERIAL AND METHODS: Using blood samples from eleven healthy donors, we investigated GE changes associated with delayed processing of EDTA tubes up to 4 h at room temperature (RT) after venipuncture (simulating delays caused by daily clinical routine), followed by a subsequent transport time of 24 h at RT, 4 °C, and -20 °C. Differential gene expression (DGE) of the target genes was further examined after X-irradiation with 0 Gy and 4 Gy under optimal transport conditions. RESULTS: No significant changes in DGE were observed when storing EDTA whole blood samples up to 4 h at RT and subsequently kept at 4 °C for 24 h which is in line with expected DGE. However, other storage conditions, such as -20 °C or RT, decreased RNA quality and/or (significantly) caused changes in DGE exceeding the known methodological variance of the qRT-PCR. CONCLUSION: Our data indicate that the use of EDTA whole blood tubes for GE-based H-ARS severity prediction is comparable to the quality of PAXgene tubes, when processed ≤ 4 h after venipuncture and the sample is transported within 24 hours at 4 °C.

Severe Acute Pancreatitis Prediction: A Model Derived From a Prospective Registry Cohort.

Background Severe acute pancreatitis (SAP) has a mortality rate as high as 40%. Early identification of SAP is required to appropriately triage and direct initial therapies. The purpose of this study was to develop a prognostic model that identifies patients at risk for developing SAP of patients managed according to a guideline-based standardized early medical management (EMM) protocol. Methods This single-center study included all patients diagnosed with acute pancreatitis (AP) and managed with the EMM protocol Methodist Acute Pancreatitis Protocol (MAPP) between April 2017 and September 2022. Classification and regression tree (CART®; Professional Extended Edition, version 8.0; Salford Systems, San Diego, CA), univariate, and logistic regression analyses were performed to develop a scoring system for AP severity prediction. The accuracy of the scoring system was measured by the area under the receiver operating characteristic curve. Results A total of 516 patients with mild (n=436) or moderately severe and severe (n=80) AP were analyzed. CART analysis identified the cutoff values: creatinine (CR) (1.15 mg/dL), white blood cells (WBC) (10.5 × 109/L), procalcitonin (PCT) (0.155 ng/mL), and systemic inflammatory response system (SIRS). The prediction model was built with a multivariable logistic regression analysis, which identified CR, WBC, PCT, and SIRS as the main predictors of severity. When CR and only one other predictor value (WBC, PCT, or SIRS) met thresholds, then the probability of predicting SAP was >30%. The probability of predicting SAP was 72% (95%CI: 0.59-0.82) if all four of the main predictors were greater than the cutoff values. Conclusions Baseline laboratory cutoff values were identified and a logistic regression-based prognostic model was developed to identify patients treated with a standardized EMM who were at risk for SAP.

Acute pancreatitis: A review of diagnosis, severity prediction and prognosis assessment from imaging technology, scoring system and artificial intelligence.

Acute pancreatitis (AP) is a potentially life-threatening inflammatory disease of the pancreas, with clinical management determined by the severity of the disease. Diagnosis, severity prediction, and prognosis assessment of AP typically involve the use of imaging technologies, such as computed tomography, magnetic resonance imaging, and ultrasound, and scoring systems, including Ranson, Acute Physiology and Chronic Health Evaluation II, and Bedside Index for Severity in AP scores. Computed tomography is considered the gold standard imaging modality for AP due to its high sensitivity and specificity, while magnetic resonance imaging and ultrasound can provide additional information on biliary obstruction and vascular complications. Scoring systems utilize clinical and laboratory parameters to classify AP patients into mild, moderate, or severe categories, guiding treatment decisions, such as intensive care unit admission, early enteral feeding, and antibiotic use. Despite the central role of imaging technologies and scoring systems in AP management, these methods have limitations in terms of accuracy, reproducibility, practicality and economics. Recent advancements of artificial intelligence (AI) provide new opportunities to enhance their performance by analyzing vast amounts of clinical and imaging data. AI algorithms can analyze large amounts of clinical and imaging data, identify scoring system patterns, and predict the clinical course of disease. AI-based models have shown promising results in predicting the severity and mortality of AP, but further validation and standardization are required before widespread clinical application. In addition, understanding the correlation between these three technologies will aid in developing new methods that can accurately, sensitively, and specifically be used in the diagnosis, severity prediction, and prognosis assessment of AP through complementary advantages.

On Scene Injury Severity Prediction (OSISP) model for trauma developed using the Swedish Trauma Registry.

BACKGROUND: Providing optimal care for trauma, the leading cause of death for young adults, remains a challenge e.g., due to field triage limitations in assessing a patient's condition and deciding on transport destination. Data-driven On Scene Injury Severity Prediction (OSISP) models for motor vehicle crashes have shown potential for providing real-time decision support. The objective of this study is therefore to evaluate if an Artificial Intelligence (AI) based clinical decision support system can identify severely injured trauma patients in the prehospital setting. METHODS: The Swedish Trauma Registry was used to train and validate five models - Logistic Regression, Random Forest, XGBoost, Support Vector Machine and Artificial Neural Network - in a stratified 10-fold cross validation setting and hold-out analysis. The models performed binary classification of the New Injury Severity Score and were evaluated using accuracy metrics, area under the receiver operating characteristic curve (AUC) and Precision-Recall curve (AUCPR), and under- and overtriage rates. RESULTS: There were 75,602 registrations between 2013-2020 and 47,357 (62.6%) remained after eligibility criteria were applied. Models were based on 21 predictors, including injury location. From the clinical outcome, about 40% of patients were undertriaged and 46% were overtriaged. Models demonstrated potential for improved triaging and yielded AUC between 0.80-0.89 and AUCPR between 0.43-0.62. CONCLUSIONS: AI based OSISP models have potential to provide support during assessment of injury severity. The findings may be used for developing tools to complement field triage protocols, with potential to improve prehospital trauma care and thereby reduce morbidity and mortality for a large patient population.

Prediction of oxygen supplementation by a deep-learning model integrating clinical parameters and chest CT images in COVID-19.

PURPOSE: As of March 2023, the number of patients with COVID-19 worldwide is declining, but the early diagnosis of patients requiring inpatient treatment and the appropriate allocation of limited healthcare resources remain unresolved issues. In this study we constructed a deep-learning (DL) model to predict the need for oxygen supplementation using clinical information and chest CT images of patients with COVID-19. MATERIALS AND METHODS: We retrospectively enrolled 738 patients with COVID-19 for whom clinical information (patient background, clinical symptoms, and blood test findings) was available and chest CT imaging was performed. The initial data set was divided into 591 training and 147 evaluation data. We developed a DL model that predicted oxygen supplementation by integrating clinical information and CT images. The model was validated at two other facilities (n = 191 and n = 230). In addition, the importance of clinical information for prediction was assessed. RESULTS: The proposed DL model showed an area under the curve (AUC) of 89.9% for predicting oxygen supplementation. Validation from the two other facilities showed an AUC > 80%. With respect to interpretation of the model, the contribution of dyspnea and the lactate dehydrogenase level was higher in the model. CONCLUSIONS: The DL model integrating clinical information and chest CT images had high predictive accuracy. DL-based prediction of disease severity might be helpful in the clinical management of patients with COVID-19.

Clinical and laboratory characteristics of COVID-19 in pregnant women.

This article discusses the distinct characteristics of COVID-19 in pregnant women and investigates potential early predictors of disease severity in this specific patient population. The study included 116 pregnant women with a confirmed diagnosis of COVID-19 in different trimesters of pregnancy. In addition to clinical features, we evaluated general clinical research methods, biochemical parameters (procalcitonin, C-reactive protein, D-dimer), and the leukocyte index of endogenous intoxication and lymphocytic index to identify potential early predictors of disease severity. All pregnant women were divided into two study groups: Group I - pregnant women with mild course, and Group II - pregnant women with moderate and severe course of COVID-19. Most pregnant women (72.4%) experienced a non-severe course characterized by catarrhal symptoms and moderate intoxication. However, pulmonary manifestations and pregnancy-related complications were detected in pregnant women from Group 2. The levels of C-reactive protein and procalcitonin in both study groups were significantly increased compared to the control group. In pregnant women with moderate and severe COVID-19, indicators of endogenous intoxication were significantly pronounced. Establishing associations between leukocyte indices and biomarkers, such as procalcitonin and C-reactive protein, enables the utilization of routine complete blood counts as a primary screening tool for predicting the severity of COVID-19 in pregnant women.

Data-driven crash prediction by injury severity using a recurrent neural network model based on Keras framework.

With the development of big data technology and the improvement of deep learning technology, data-driven and machine learning application have been widely employed. By adopting the data-driven machine learning method, with the help of clustering processing of data sets, a recurrent neural network (RNN) model based on Keras framework is proposed to predict the injury severity in urban areas. First, with crash data from 2014 to 2017 in Nevada, OPTICS clustering algorithm is employed to extract the crash injury in Las Vegas. Next, by virtue of Keras' high efficiency and strong scalability, the parameters of loss function, activation function and optimizer of the deep learning model are determined to realize the training of the model and the visualization of the training results, and the RNN model is constructed. Finally, on the basis of training and testing data, the model can predict the injury severity with high accuracy and high training speed. The results provide an alternative and some potential insights on the injury severity prediction.

An immune-protein score combining TRAIL, IP-10 and CRP for predicting severe COVID-19 disease.

COVID-19 patients are oftentimes over- or under-treated due to a deficit in predictive management tools. This study reports derivation of an algorithm that integrates the host levels of TRAIL, IP-10, and CRP into a single numeric score that is an early indicator of severe outcome for COVID-19 patients and can identify patients at-risk to deteriorate. 394 COVID-19 patients were eligible; 29% meeting a severe outcome (intensive care unit admission/non-invasive or invasive ventilation/death). The score's area under the receiver operating characteristic curve (AUC) was 0.86, superior to IL-6 (AUC 0.77; p = 0.033) and CRP (AUC 0.78; p < 0.001). Likelihood of severe outcome increased significantly (p < 0.001) with higher scores. The score differentiated severe patients who further deteriorated from those who improved (p = 0.004) and projected 14-day survival probabilities (p < 0.001). The score accurately predicted COVID-19 patients at-risk for severe outcome, and therefore has potential to facilitate timely care escalation and de-escalation and appropriate resource allocation.

COVID-19 Severity Prediction from Chest X-ray Images Using an Anatomy-Aware Deep Learning Model.

The COVID-19 pandemic has been adversely affecting the patient management systems in hospitals around the world. Radiological imaging, especially chest x-ray and lung Computed Tomography (CT) scans, plays a vital role in the severity analysis of hospitalized COVID-19 patients. However, with an increasing number of patients and a lack of skilled radiologists, automated assessment of COVID-19 severity using medical image analysis has become increasingly important. Chest x-ray (CXR) imaging plays a significant role in assessing the severity of pneumonia, especially in low-resource hospitals, and is the most frequently used diagnostic imaging in the world. Previous methods that automatically predict the severity of COVID-19 pneumonia mainly focus on feature pooling from pre-trained CXR models without explicitly considering the underlying human anatomical attributes. This paper proposes an anatomy-aware (AA) deep learning model that learns the generic features from x-ray images considering the underlying anatomical information. Utilizing a pre-trained model and lung segmentation masks, the model generates a feature vector including disease-level features and lung involvement scores. We have used four different open-source datasets, along with an in-house annotated test set for training and evaluation of the proposed method. The proposed method improves the geographical extent score by 11% in terms of mean squared error (MSE) while preserving the benchmark result in lung opacity score. The results demonstrate the effectiveness of the proposed AA model in COVID-19 severity prediction from chest X-ray images. The algorithm can be used in low-resource setting hospitals for COVID-19 severity prediction, especially where there is a lack of skilled radiologists.

Evaluating the one-time chair stand test for predicting the coronavirus disease severity in patients during hospital admission: a cohort study in Japan.

BACKGROUND: This study aimed to understand whether the one-time chair stand test (CS-1) is useful for predicting the severity of coronavirus disease (COVID-19) in 101 patients admitted to the hospital with acute respiratory failure. METHODS: This single-centered, prospective observational cohort study enrolled 101 critically ill adult patients hospitalized with COVID-19 who underwent the CS-1 as a dynamic evaluation tool in clinical practice between late April 2020 and October 2021. Data on demographic characteristics, symptoms, laboratory values, computed tomography findings, and clinical course after admission were collected. Furthermore, the data was compared, and the association between the intubation and non-intubation groups was determined. We also calculated the cutoff point, area under the curve (AUC), and 95% confidence interval (CI) of the change in oxygen saturation (ΔSpO2) during the CS-1. RESULTS: Thirty-three out of 101 patients (33%) were intubated during hospitalization. There was no significant difference in the resting SpO2 (93.3% versus 95.2%, P = 0.22), but there was a significant difference in ΔSpO2 during the CS-1 between the intubation and non-intubation groups (10.8% versus 5.5%, P < 0.01). In addition, there was a significant correlation between hospitalization and ΔSpO2 during the CS-1 (ρ = 0.60, P < 0.01). The generated cutoff point was calculated as 9.5% (AUC = 0.94, 95% CI = 0.88-1.00). CONCLUSION: For COVID-19 patients with acute respiratory failure, the CS-1 performed on admission was useful for predicting the severity of COVID-19. Furthermore, the CS-1 can be utilized as a remote and simple evaluation parameter. Thus, it could have potential clinical applications in the future.

Benchmarking of Machine Learning classifiers on plasma proteomic for COVID-19 severity prediction through interpretable artificial intelligence.

The SARS-CoV-2 pandemic highlighted the need for software tools that could facilitate patient triage regarding potential disease severity or even death. In this article, an ensemble of Machine Learning (ML) algorithms is evaluated in terms of predicting the severity of their condition using plasma proteomics and clinical data as input. An overview of AI-based technical developments to support COVID-19 patient management is presented outlining the landscape of relevant technical developments. Based on this review, the use of an ensemble of ML algorithms that analyze clinical and biological data (i.e., plasma proteomics) of COVID-19 patients is designed and deployed to evaluate the potential use of AI for early COVID-19 patient triage. The proposed pipeline is evaluated using three publicly available datasets for training and testing. Three ML "tasks" are defined, and several algorithms are tested through a hyperparameter tuning method to identify the highest-performance models. As overfitting is one of the typical pitfalls for such approaches (mainly due to the size of the training/validation datasets), a variety of evaluation metrics are used to mitigate this risk. In the evaluation procedure, recall scores ranged from 0.6 to 0.74 and F1-score from 0.62 to 0.75. The best performance is observed via Multi-Layer Perceptron (MLP) and Support Vector Machines (SVM) algorithms. Additionally, input data (proteomics and clinical data) were ranked based on corresponding Shapley additive explanation (SHAP) values and evaluated for their prognosticated capacity and immuno-biological credence. This "interpretable" approach revealed that our ML models could discern critical COVID-19 cases predominantly based on patient's age and plasma proteins on B cell dysfunction, hyper-activation of inflammatory pathways like Toll-like receptors, and hypo-activation of developmental and immune pathways like SCF/c-Kit signaling. Finally, the herein computational workflow is corroborated in an independent dataset and MLP superiority along with the implication of the abovementioned predictive biological pathways are corroborated. Regarding limitations of the presented ML pipeline, the datasets used in this study contain less than 1000 observations and a significant number of input features hence constituting a high-dimensional low-sample (HDLS) dataset which could be sensitive to overfitting. An advantage of the proposed pipeline is that it combines biological data (plasma proteomics) with clinical-phenotypic data. Thus, in principle, the presented approach could enable patient triage in a timely fashion if used on already trained models. However, larger datasets and further systematic validation are needed to confirm the potential clinical value of this approach. The code is available on Github: https://github.com/inab-certh/Predicting-COVID-19-severity-through-interpretable-AI-analysis-of-plasma-proteomics.