Radiological and Biochemical Parameters in Assessing Acute Pancreatitis Severity: A Comprehensive Review.

Acute pancreatitis is a dynamic inflammatory condition of the pancreas with a spectrum ranging from mild to severe. Early and accurate assessment of disease severity is crucial for guiding clinical management and improving patient outcomes. This comprehensive review explores the role of radiological and biochemical parameters in assessing the severity of acute pancreatitis. Radiological imaging modalities, including computed tomography (CT), magnetic resonance imaging (MRI), and ultrasound (US), play a pivotal role in identifying key features, such as pancreatic necrosis and peripancreatic fluid collections, indicative of severe disease. Additionally, serum markers such as amylase, lipase, and C-reactive protein (CRP) provide valuable prognostic information and aid in risk stratification. Integrating radiological and biochemical parameters allows for a multidimensional evaluation of disease severity, enabling clinicians to make informed decisions regarding patient management. Early identification of severe cases facilitates timely interventions, including intensive care monitoring, nutritional support, and potential surgical interventions. Despite significant advancements in the field, there remain areas for further research, including the validation of emerging imaging techniques and biomarkers and the exploration of personalized management approaches. Addressing these research gaps can enhance our understanding of acute pancreatitis and ultimately improve patient care and outcomes.

Exploring dose-response variability and relative severity assessment in STZ-induced diabetes male NSG mice.

NSG mice are among the most immunodeficient mouse model being used in various scientific branches. In diabetelogical research diabetic NSG mice are an important asset as a xenotransplantation model for human pancreatic islets or pluripotent stem cell-derived islets. The treatment with the beta cell toxin streptozotocin is the standard procedure for triggering a chemically induced diabetes. Surprisingly, little data has been published about the reproducibility, stress and animal suffering in these NSG mice during diabetes induction. The 3R rules, however, are a constant reminder that existing methods can be further refined to minimize suffering. In this pilot study the dose-response relationship of STZ in male NSG mice was investigated and additionally animal suffering was charted by applying the novel 'Relative Severity Assessment' algorithm. By this we successfully explored an STZ dose that reliably induced diabetes while reduced stress and pain to the animals to a minimum using evidence-based and objective parameters rather than criteria that might be influenced by human bias.

Causality, Severity, Preventability and Predictability Assessments Scales for Adverse Drug Reactions: A Review.

The pharmacovigilance program of India (PvPI), after its inception, has been reliably acquiring force in bringing issues to light among the masses, healthcare professionals, the pharma industry, and clinical staff at hospitals. Adverse drug reactions are unintended events that occur after exposure to a drug, biological product, or medical device, and they may result in morbidity and mortality. It is critical to monitor the safety of drugs during the post-marketing phase to find long-term and rare ADRs, as well as ADRs in special populations and patients with co-morbidities that are not usually included during clinical trials. The definitive objective of pharmacovigilance is to collate data and analyze it. Assessing the causality between ADRs and drugs is necessary to decrease the occurrence of ADRs and to reduce the risk of drug-related ADRs. ADRs may lead to increased morbidity, increased hospital stays, and increased cost of treatment, resulting in compromised patient safety. Causality assessment is the evaluation of the likelihood that a particular treatment is the cause of an observed adverse event and establishing a causal association between a drug and a drug reaction is necessary to prevent further recurrences. Numerous methods available for establishing a causal association between the drug and adverse events have been broadly classified into clinical judgment or global introspection, algorithms, and probabilistic methods. These include the Swedish method, World Health Organization-Uppsala Monitoring Centre (WHO-UMC) scale, Naranjo's algorithm, Kramer algorithm, Jones algorithm, Karch algorithm, Bégaud algorithm, Adverse Drug Reactions Advisory Committee guidelines, Bayesian Adverse Reaction Diagnostic Instrument, and so on. Despite various methods available, none of the causality assessment tools have been universally accepted as the gold standard. Naranjo's algorithm and WHO-UMC scales are, however, the most commonly used. Similarly, for preventability and severity assessment of ADRs, the Schumock and Thornton scale and Hartwig and Siegel's scale are most commonly used. Hence, we reviewed different tools and methods available to assess the causality, preventability, and severity of ADRs.

Choice-based severity scale (CSS): assessing the relative severity of procedures from a laboratory animal's perspective.

One primary goal of laboratory animal welfare science is to provide a comprehensive severity assessment of the experimental and husbandry procedures or conditions these animals experience. The severity, or degree of suffering, of these conditions experienced by animals are typically scored based on anthropocentric assumptions. We propose to (a) assess an animal's subjective experience of condition severity, and (b) not only rank but scale different conditions in relation to one another using choice-based preference testing. The Choice-based Severity Scale (CSS) utilizes animals' relative preferences for different conditions, which are compared by how much reward is needed to outweigh the perceived severity of a given condition. Thus, this animal-centric approach provides a common scale for condition severity based on the animal's perspective. To assess and test the CSS concept, we offered three opportunistically selected male rhesus macaques (Macaca mulatta) choices between two conditions: performing a cognitive task in a typical neuroscience laboratory setup (laboratory condition) versus the monkey's home environment (cage condition). Our data show a shift in one individual's preference for the cage condition to the laboratory condition when we changed the type of reward provided in the task. Two additional monkeys strongly preferred the cage condition over the laboratory condition, irrespective of reward amount and type. We tested the CSS concept further by showing that monkeys' choices between tasks varying in trial duration can be influenced by the amount of reward provided. Altogether, the CSS concept is built upon laboratory animals' subjective experiences and has the potential to de-anthropomorphize severity assessments, refine experimental protocols, and provide a common framework to assess animal welfare across different domains.

Exploration and Evaluation of Adverse Drug Reactions Documented in a Tertiary-Care Hospital in Chennai: An In-Depth Retrospective Observational Study.

INTRODUCTION:  While drugs are intended to benefit patients, adverse drug reactions (ADRs) represent a significant negative outcome of drug consumption. They rank as the sixth leading cause of death among hospitalized patients. Many harmful effects are preventable and can reduce morbidity, mortality, and hospitalization duration. This study is a valuable resource for physicians, aiding in the safe and optimal use of medications. METHODOLOGY:  This retrospective observational study, conducted at the Pharmacovigilance Center of Saveetha Medical College and Hospital, Chennai, India, received approval from the Institutional Ethics Committee. All adverse drug interactions reported in our hospital from January 2019 to February 2024 were included after screening for inclusion and exclusion criteria. The collected reactions were analyzed, assessed, and evaluated between February 2024 and April 2024. Data on the drugs causing adverse reactions, the types of reactions, and the treatments administered were collected and documented. The reactions were categorized using the Rawlins and Thompson classification, while causality and severity were assessed using the standard Naranjo causality and modified Hartwig and Siegel severity assessment scales. RESULTS:  During the study, 252 ADRs were documented by the Central Drugs Standard Control Organization. The gender distribution showed 123 cases (48.8%) in males and 129 cases (51.2%) in females, with a higher prevalence in the 20-40 age group. The departmentwise distribution revealed the highest number of ADRs in Obstetrics and Gynecology (60 cases, 24%), followed by General Surgery (52 cases, 21%), General Medicine (44 cases, 17%), Pediatrics (22 cases, 9%), and Emergency Medicine (20 cases, 8%). Antimicrobial drugs constituted the majority of ADRs (149 cases, 59.1%), followed by vitamins and mineral supplements (21 cases, 13.8%), contrast dye (15 cases, 6%), antituberculosis drugs (15 cases, 6%), analgesics (13 cases, 5.2%), and gastrointestinal (GIT) drugs (8 cases, 3.2%). Cefotaxime was the most commonly reported antibiotic (42 cases, 28.2%), followed by Ciprofloxacin (41 cases, 27.5%). Among vitamins and mineral supplements, iron sucrose was implicated in the highest number of ADRs (15 cases, 71.4%). The parenteral route of drug administration showed the highest incidence of ADRs (229 cases, 91%), followed by oral (20 cases, 8%) and topical routes (3 cases, 1%). Dermatological manifestations were most frequently reported (196 cases, 77.8%), followed by GIT symptoms (27 cases, 10.7%), and other manifestations such as shivering, fever, seizures, and dyspnea (29 cases, 11.5%). Based on the Naranjo causality assessment scale, 179 ADRs (71%) were categorized as probable, 55 (22%) as possible, 10 (4%) as certain, and 8 (3%) as doubtful. Approximately 47.2% of ADRs were self-limiting, while 44.1% required symptomatic treatment and 8.7% necessitated aggressive treatment, leading to a prolonged hospital stay or admission to the intensive care unit. CONCLUSION:  The pattern of ADRs in our hospital aligns with findings from other studies. While many of these reactions are unpredictable and mild, they underscore the importance of raising awareness among clinicians and regulatory authorities to promote safe medication use and prevent potentially serious outcomes.

Damage Severity Assessment of Multi-Layer Complex Structures Based on a Damage Information Extraction Method with Ladder Feature Mining.

Multi-layer complex structures are widely used in large-scale engineering structures because of their diverse combinations of properties and excellent overall performance. However, multi-layer complex structures are prone to interlaminar debonding damage during use. Therefore, it is necessary to monitor debonding damage in engineering applications to determine structural integrity. In this paper, a damage information extraction method with ladder feature mining for Lamb waves is proposed. The method is able to optimize and screen effective damage information through ladder-type damage extraction. It is suitable for evaluating the severity of debonding damage in aluminum-foamed silicone rubber, a novel multi-layer complex structure. The proposed method contains ladder feature mining stages of damage information selection and damage feature fusion, realizing a multi-level damage information extraction process from coarse to fine. The results show that the accuracy of damage severity assessment by the damage information extraction method with ladder feature mining is improved by more than 5% compared to other methods. The effectiveness and accuracy of the method in assessing the damage severity of multi-layer complex structures are demonstrated, providing a new perspective and solution for damage monitoring of multi-layer complex structures.

Diagnosis and Severity Assessment of COPD Using a Novel Fast-Response Capnometer and Interpretable Machine Learning.

INTRODUCTION: Spirometry is the gold standard for COPD diagnosis and severity determination, but is technique-dependent, nonspecific, and requires administration by a trained healthcare professional. There is a need for a fast, reliable, and precise alternative diagnostic test. This study's aim was to use interpretable machine learning to diagnose COPD and assess severity using 75-second carbon dioxide (CO2) breath records captured with TidalSense's N-TidalTM capnometer. METHOD: For COPD diagnosis, machine learning algorithms were trained and evaluated on 294 COPD (including GOLD stages 1-4) and 705 non-COPD participants. A logistic regression model was also trained to distinguish GOLD 1 from GOLD 4 COPD with the output probability used as an index of severity. RESULTS: The best diagnostic model achieved an AUROC of 0.890, sensitivity of 0.771, specificity of 0.850 and positive predictive value (PPV) of 0.834. Evaluating performance on all test capnograms that were confidently ruled in or out yielded PPV of 0.930 and NPV of 0.890. The severity determination model yielded an AUROC of 0.980, sensitivity of 0.958, specificity of 0.961 and PPV of 0.958 in distinguishing GOLD 1 from GOLD 4. Output probabilities from the severity determination model produced a correlation of 0.71 with percentage predicted FEV1. CONCLUSION: The N-TidalTM device could be used alongside interpretable machine learning as an accurate, point-of-care diagnostic test for COPD, particularly in primary care as a rapid rule-in or rule-out test. N-TidalTM also could be effective in monitoring disease progression, providing a possible alternative to spirometry for disease monitoring.

Automatic quantitative stroke severity assessment based on Chinese clinical named entity recognition with domain-adaptive pre-trained large language model.

BACKGROUND: Stroke is a prevalent disease with a significant global impact. Effective assessment of stroke severity is vital for an accurate diagnosis, appropriate treatment, and optimal clinical outcomes. The National Institutes of Health Stroke Scale (NIHSS) is a widely used scale for quantitatively assessing stroke severity. However, the current manual scoring of NIHSS is labor-intensive, time-consuming, and sometimes unreliable. Applying artificial intelligence (AI) techniques to automate the quantitative assessment of stroke on vast amounts of electronic health records (EHRs) has attracted much interest. OBJECTIVE: This study aims to develop an automatic, quantitative stroke severity assessment framework through automating the entire NIHSS scoring process on Chinese clinical EHRs. METHODS: Our approach consists of two major parts: Chinese clinical named entity recognition (CNER) with a domain-adaptive pre-trained large language model (LLM) and automated NIHSS scoring. To build a high-performing CNER model, we first construct a stroke-specific, densely annotated dataset "Chinese Stroke Clinical Records" (CSCR) from EHRs provided by our partner hospital, based on a stroke ontology that defines semantically related entities for stroke assessment. We then pre-train a Chinese clinical LLM coined "CliRoberta" through domain-adaptive transfer learning and construct a deep learning-based CNER model that can accurately extract entities directly from Chinese EHRs. Finally, an automated, end-to-end NIHSS scoring pipeline is proposed by mapping the extracted entities to relevant NIHSS items and values, to quantitatively assess the stroke severity. RESULTS: Results obtained on a benchmark dataset CCKS2019 and our newly created CSCR dataset demonstrate the superior performance of our domain-adaptive pre-trained LLM and the CNER model, compared with the existing benchmark LLMs and CNER models. The high F1 score of 0.990 ensures the reliability of our model in accurately extracting the entities for the subsequent automatic NIHSS scoring. Subsequently, our automated, end-to-end NIHSS scoring approach achieved excellent inter-rater agreement (0.823) and intraclass consistency (0.986) with the ground truth and significantly reduced the processing time from minutes to a few seconds. CONCLUSION: Our proposed automatic and quantitative framework for assessing stroke severity demonstrates exceptional performance and reliability through directly scoring the NIHSS from diagnostic notes in Chinese clinical EHRs. Moreover, this study also contributes a new clinical dataset, a pre-trained clinical LLM, and an effective deep learning-based CNER model. The deployment of these advanced algorithms can improve the accuracy and efficiency of clinical assessment, and help improve the quality, affordability and productivity of healthcare services.

Comparison of a Novel Score "NOD-ACLF" to Other Established Prognostic Scores for Prediction of Mortality in APASL-ACLF Patients: A Cohort Study from a Tertiary Care Center of North India.

Background: Commonly used prognostic scores for acute on-chronic liver failure (ACLF) have complex calculations. We tried to compare the simple counting of numbers and types of organ dysfunction to these scores, to predict mortality in ACLF patients. Methods: In this prospective cohort study, ACLF patients diagnosed on the basis of Asia Pacific Association for Study of the Liver (APASL) definition were included. Severity scores were calculated. Prognostic factors for outcome were analysed. A new score, the Number of Organ Dysfunctions in Acute-on-Chronic Liver Failure (NOD-ACLF) score was developed. Results: Among 80 ACLF patients, 74 (92.5%) were male, and 6 were female (7.5%). The mean age was 41.0±10.7 (18-70) years. Profile of acute insult was; alcohol 48 (60%), sepsis 30 (37.5%), variceal bleeding 22 (27.5%), viral 8 (10%), and drug-induced 3 (3.8%). Profiles of chronic insults were alcohol 61 (76.3%), viral 20 (25%), autoimmune 3 (3.8%), and non-alcoholic steatohepatitis 2 (2.5%). Thirty-eight (47.5%) were discharged, and 42 (52.5%) expired. The mean number of organ dysfunction (NOD-ACLF score) was ->4.5, simple organ failure count (SOFC) score was >2.5, APASL ACLF Research Consortium score was >11.5, Model for End-Stage Liver Disease-Lactate (MELD-LA) score was >21.5, and presence of cardiovascular and respiratory dysfunctions were significantly associated with mortality. NOD-ACLF and SOFC scores had the highest area under the receiver operating characteristic to predict mortality among all these. Conclusion: The NOD-ACLF score is easy to calculate bedside and is a good predictor of mortality in ACLF patients performing similar or better to other scores.

CoSev: Data-Driven Optimizations for COVID-19 Severity Assessment in Low-Sample Regimes.

Given the pronounced impact COVID-19 continues to have on society-infecting 700 million reported individuals and causing 6.96 million deaths-many deep learning works have recently focused on the virus's diagnosis. However, assessing severity has remained an open and challenging problem due to a lack of large datasets, the large dimensionality of images for which to find weights, and the compute limitations of modern graphics processing units (GPUs). In this paper, a new, iterative application of transfer learning is demonstrated on the understudied field of 3D CT scans for COVID-19 severity analysis. This methodology allows for enhanced performance on the MosMed Dataset, which is a small and challenging dataset containing 1130 images of patients for five levels of COVID-19 severity (Zero, Mild, Moderate, Severe, and Critical). Specifically, given the large dimensionality of the input images, we create several custom shallow convolutional neural network (CNN) architectures and iteratively refine and optimize them, paying attention to learning rates, layer types, normalization types, filter sizes, dropout values, and more. After a preliminary architecture design, the models are systematically trained on a simplified version of the dataset-building models for two-class, then three-class, then four-class, and finally five-class classification. The simplified problem structure allows the model to start learning preliminary features, which can then be further modified for more difficult classification tasks. Our final model CoSev boosts classification accuracies from below 60% at first to 81.57% with the optimizations, reaching similar performance to the state-of-the-art on the dataset, with much simpler setup procedures. In addition to COVID-19 severity diagnosis, the explored methodology can be applied to general image-based disease detection. Overall, this work highlights innovative methodologies that advance current computer vision practices for high-dimension, low-sample data as well as the practicality of data-driven machine learning and the importance of feature design for training, which can then be implemented for improvements in clinical practices.

Assessment of oral methotrexate intolerance in Japanese adult patients with rheumatoid arthritis.

AIM: The objective of this study was to assess the gastrointestinal side (GI) effects of oral methotrexate (MTX) in Japanese adult patients with rheumatoid arthritis (RA). METHODS: In this single-center retrospective study, 112 Japanese adult patients (over 18 years old) with RA were examined by Methotrexate Intolerance and Severity assessment in Adults (MISA) questionnaire. RESULTS: Forty-five (40.2%) of patients were MTX intolerant (MISA score ≥1). Twelve patients (11.2%) were moderate-to-severe MTX intolerant (MISA cross-product score ≥4). The most common GI side effects of MTX were gastric discomfort (26.8%), followed by loss of appetite or dysgeusia (14.3%), fatigue and lethargy (12.5%), and nausea (10.7%). CONCLUSIONS: Japanese adult patients with RA showed a high prevalence of MTX intolerance even in low-dose oral MTX. The MISA questionnaire was practical for finding patients with MTX intolerance.

Platelet distribution width as an useful indicator of influenza severity in children.

PURPOSE: The present study aims to investigate the potential of platelet distribution width as an useful parameter to assess the severity of influenza in children. METHODS: Baseline characteristics and laboratory results were collected and analyzed. Receiver operating characteristic (ROC) curve analysis was used to joint detection of inflammatory markers for influenza positive children, and the scatter-dot plots were used to compare the differences between severe and non-severe group. RESULTS: Influenza B positive children had more bronchitis and pneumonia (P < 0.05), influenza A infected children had more other serious symptoms (P = 0.007). Neutrophil count, lymphocyte count, neutrophil-to-lymphocyte ratio (NLR), and platelet parameters performed differently among < 4 years and ≥ 4 years children with influenza. Combined detection of platelet parameters and other indicators could better separate healthy children from influenza infected children than single indicator detection. The levels of platelet distribution width of children with severe influenza (A and B) infection was significantly dropped, compared with non-severe group (P < 0.05). CONCLUSIONS: Platelet distribution width could be a very useful and economic indicator in distinction and severity assessment for children with influenza.

Association of elastic power in mechanical ventilation with the severity of acute respiratory distress syndrome: a retrospective study.

BACKGROUND: Mechanical power (MP) is the total energy released into the entire respiratory system per minute which mainly comprises three components: elastic static power, Elastic dynamic power and resistive power. However, the energy to overcome resistance to the gas flow is not the key factor in causing lung injury, but the elastic power (EP) which generates the baseline stretch of the lung fibers and overcomes respiratory system elastance may be closely related to the ARDS severity. Thus, this study aimed to investigate whether EP is superior to other ventilator variables for predicting the severity of lung injury in ARDS patients. METHODS: We retrieved patient data from the Medical Information Mart for Intensive Care III (MIMIC-III) database. The retrieved data involved adults (≥ 18 years) diagnosed with ARDS and subjected to invasive mechanical ventilation for ≥ 48 h. We employed univariate and multivariate logistic regression analyses to investigate the correlation between EP and development of moderate-severe ARDS. Furthermore, we utilized restricted cubic spline models to assess whether there is a linear association between EP and incidence of moderate-severe ARDS. In addition, we employed a stratified linear regression model and likelihood ratio test in subgroups to identify potential modifications and interactions. RESULTS: Moderate-severe ARDS occurred in 73.4% (296/403) of the patients analyzed. EP and MP were significantly associated with moderate-severe ARDS (odds ratio [OR] 1.21, 95% confidence interval [CI] 1.15-1.28, p < 0.001; and OR 1.15, 95%CI 1.11-1.20, p < 0.001; respectively), but EP showed a higher area-under-curve (95%CI 0.72-0.82, p < 0.001) than plateau pressure, driving pressure, and static lung compliance in predicting ARDS severity. The optimal cutoff value for EP was 14.6 J/min with a sensitivity of 75% and specificity of 66%. Quartile analysis revealed that the relationship between EP and ARDS severity remained robust and reliable in subgroup analysis. CONCLUSION: EP is a good ventilator variable associated with ARDS severity and can be used for grading ARDS severity. Close monitoring of EP is advised in patients undergoing mechanical ventilation. Additional experimental trials are needed to investigate whether adjusting ventilator variables according to EP can yield significant improvements in clinical outcomes.

Coarctation duration and severity predict risk of hypertension precursors in a preclinical model and hypertensive status among patients.

Background: Coarctation of the aorta (CoA) often leads to hypertension (HTN) post-treatment. Evidence is lacking for the current >20 mmHg peak-to-peak blood pressure gradient (BPGpp) guideline, which can cause aortic thickening, stiffening and dysfunction. This study sought to find the BPGpp severity and duration that avoid persistent dysfunction in a preclinical model, and test if predictors translate to HTN status in CoA patients. Methods: Rabbits (N=75; 5-12/group) were exposed to mild, intermediate or severe CoA (≤12, 13-19, ≥20 mmHg BPGpp) for ~1, 3 or 22 weeks using dissolvable and permanent sutures with thickening, stiffening, contraction and endothelial function evaluated via multivariate regression. Relevance to CoA patients (N=239; age=0.01-46 years; median 3.7 months) was tested by retrospective review of predictors (preoperative BPGpp, surgical age, etc.) vs follow-up HTN status. Results: CoA duration and severity were predictive of aortic remodeling and active dysfunction in rabbits, and HTN in CoA patients. Interaction between patient age and BPGpp at surgery contributed significantly to HTN, similar to rabbits, suggesting preclinical findings translate to patients. Machine learning decision tree analysis uncovered that pre-operative BPGpp and surgical age predict risk of HTN along with residual post-operative BPGpp. Conclusions: These findings suggest the current BPGpp threshold determined decades ago is likely too high to prevent adverse coarctation-induced aortic remodeling. The results and decision tree analysis provide a foundation for revising CoA treatment guidelines considering the interaction between CoA severity and duration to limit the risk of HTN.

Automated MRI Lung Segmentation and 3D Morphologic Features for Quantification of Neonatal Lung Disease.

Purpose: To analyze the performance of deep learning (DL) models for segmentation of the neonatal lung in MRI and investigate the use of automated MRI-based features for assessment of neonatal lung disease. Materials and Methods: Quiet-breathing MRI was prospectively performed in two independent cohorts of preterm infants (median gestational age, 26.57 weeks; IQR, 25.3-28.6 weeks; 55 female and 48 male infants) with (n = 86) and without (n = 21) chronic lung disease (bronchopulmonary dysplasia [BPD]). Convolutional neural networks were developed for lung segmentation, and a three-dimensional reconstruction was used to calculate MRI features for lung volume, shape, pixel intensity, and surface. These features were explored as indicators of BPD and disease-associated lung structural remodeling through correlation with lung injury scores and multinomial models for BPD severity stratification. Results: The lung segmentation model reached a volumetric Dice coefficient of 0.908 in cross-validation and 0.880 on the independent test dataset, matching expert-level performance across disease grades. MRI lung features demonstrated significant correlations with lung injury scores and added structural information for the separation of neonates with BPD (BPD vs no BPD: average area under the receiver operating characteristic curve [AUC], 0.92 ± 0.02 [SD]; no or mild BPD vs moderate or severe BPD: average AUC, 0.84 ± 0.03). Conclusion: This study demonstrated high performance of DL models for MRI neonatal lung segmentation and showed the potential of automated MRI features for diagnostic assessment of neonatal lung disease while avoiding radiation exposure.Keywords: Bronchopulmonary Dysplasia, Chronic Lung Disease, Preterm Infant, Lung Segmentation, Lung MRI, BPD Severity Assessment, Deep Learning, Lung Imaging Biomarkers, Lung Topology Supplemental material is available for this article. Published under a CC BY 4.0 license.See also the commentary by Parraga and Sharma in this issue.

Combination of Urinary Neutrophil Gelatinase-associated Lipocalin, Kidney Injury Molecular-1, and Angiotensinogen for the Early Diagnosis and Mortality Prediction of Septic Acute Kidney Injury.

BACKGROUND: Acute kidney injury (AKI) is one of the most severe complications of sepsis. This study was conducted to analyze the role of urinary neutrophil gelatinase-associated lipocalin (uNGAL), urinary kidney injury molecular-1 (uKIM-1), and urinary angiotensinogen (uAGT) in the early diagnosis and mortality prediction of septic AKI. METHODS: The prospective study enrolled 80 sepsis patients in the ICU and 100 healthy individuals and divided patients into an AKI group and a non-AKI group. uNGAL, uKIM-1, uAGT, serum creatinine/procalcitonin/C-reaction protein, and other indicators were determined, and clinical prediction scores were recorded. The sensitivity and specificity of uNGAL, uKIM-1, and uAGT in diagnosis and mortality prediction were analyzed by the receiver operator characteristic (ROC) curve and the area under the curve (AUC). RESULTS: uNGAL, uKIM-1, and uAGT levels were higher in sepsis patients than healthy controls, higher in AKI patients than non-AKI patients, and higher in AKI-2 and AKI-3 patients than AKI-1 patients. At 0 h after admission, the combined efficacy of three indicators in septic AKI diagnosis (ROC-AUC: 0.770; sensitivity: 82.5%; specificity: 70.0%) was better than a single indicator. At 24 h, uNGAL, uKIM-1, and uAGT levels were higher in sepsis non-survivals than survivals and higher in septic AKI non-survivals than septic AKI survivals. The combined efficacy of three indicators in the prediction of sepsis/septic AKI mortality (ROC-AUC: 0.828/0.847; sensitivity: 71.4%/100.0%; specificity: 82.7%/66.7%) was better than a single indicator. CONCLUSION: uNGAL, uKIM-1, and uAGT levels were increased in septic AKI, and their combination helped the early diagnosis and mortality prediction.

A novel plantar pressure analysis method to signify gait dynamics in Parkinson's disease.

Plantar pressure can signify the gait performance of patients with Parkinson's disease (PD). This study proposed a plantar pressure analysis method with the dynamics feature of the sub-regions plantar pressure signals. Specifically, each side's plantar pressure signals were divided into five sub-regions. Moreover, a dynamics feature extractor (DFE) was designed to extract features of the sub-regions signals. The radial basis function neural network (RBFNN) was used to learn and store gait dynamics. And a classification mechanism based on the output error in RBFNN was proposed. The classification accuracy of the proposed method achieved 100.00% in PD diagnosis and 95.89% in severity assessment on the online dataset, and 96.00% in severity assessment on our dataset. The experimental results suggested that the proposed method had the capability to signify the gait dynamics of PD patients.

Application of national early warning score in assessing postoperative illness severity in elderly patients with gastrointestinal illnesses.

BACKGROUND: Population aging is a social problem that is being faced in most countries. OBJECTIVE: To apply the National Early Warning Score (NEWS) for an early warning on the vital signs and consciousness of elderly patients who are hospitalized in the gastrointestinal surgical department and to provide a reference for early detection of changes in illness severity in elderly patients by studying the correlation between NEWS value and changes in illness severity. METHODS: We enrolled 528 elderly patients who were hospitalized in the gastrointestinal surgical department of a tertiary grade A hospital in Guizhou Province between June 2020 and May 2021, to analyze how NEWS max value correlates with illness severity and obtain the optimal NEWS cutoff value for both potentially critically ill and critically ill elderly patients using the receiver operating characteristic (ROC) curve. RESULTS: There were statistically significant differences in NEWS values between elderly patients with various illness severities (P< 0.05). NEWS values correlated positively with illness severity (r= 0.605, P< 0.001). Based on the ROC curve, early warning trigger values for NEWS to identify potentially critically ill, critically ill and terminally ill elderly patients were 6, 7 and 8, respectively. The area under the curve (AUC) for potentially critically ill, critically ill and terminally ill elderly patients was 0.907, 0.921 and 0.939, respectively. NEWS performed better in detecting patient illness severity than Modified Early Warning Score (MEWS) in AUC, sensitivity, specificity, and Youden's index, with statistically significant differences (P< 0.05). CONCLUSION: An early warning on the vital signs and consciousness of hospitalized elderly patients using NEWS can facilitate advanced detection of changes in illness severity of elderly patients by medical staff and enable timely treatment, thus significantly lowering the risks of illness deterioration.

Improved Prediction of Knee Osteoarthritis by the Machine Learning Model XGBoost.

Objectives: The accurate prediction of osteoarthritis (OA) severity in patients can be helpful to make the proper decision of intervention. This study aims to build up a powerful model to assess predictive risk factors and severity of knee osteoarthritis (KOA) in the clinical scenario. Methods: A total of 4796 KOA cases and 1205 features were selected by feature selections from the public OA database, Osteoarthritis Initiative (OAI). Six machine learning-based models were constructed and compared for the accuracy of OA prediction. The gradient-boosting decision tree was used to identify important prediction features in the extreme gradient boosting (XGBoost) model. The performance of models was evaluated by F1-score. Results: Twenty features were determined as predictors for KOA risk and severity, including the subject characteristics, knee symptoms/risk factors and physical exam. The XGBoost model demonstrated 100% prediction accuracy for 54.7% of examined samples, and the remaining 45.3% of samples showed Kellgren and Lawrence (KL) gradings very close to the actual levels. It showed the highest prediction accuracy with an F1-score of 0.553 among the tested six models. Conclusions: We demonstrate that the XGBoost is the best model for the prediction of KOA severity in the six examined models. In addition, 20 risk features were determined as the essential predictors of KOA, including the physical exam, knee symptoms/risk factors and subject characteristics, which may be useful for the identification of high-risk KOA cases and for making appropriate treatment decisions as well.