Machine learning predictive models for acute pancreatitis: A systematic review

Machine learning methods in predicting the risk of malignant transformation of oral potentially malignant disorders: A systematic review

BACKGROUND

Oral Potentially Malignant Disorders (OPMDs) refer to a heterogenous group of clinical presentations with heightened rate of malignant transformation. Identification of risk levels in OPMDs is crucial to determine the need for active intervention in high-risk patients and routine follow-up in low-risk ones. Machine learning models has shown tremendous potential in several areas of dentistry that strongly suggest its application to estimate rate of malignant transformation of precancerous lesions.

METHODS

A comprehensive literature search was performed on Pubmed/MEDLINE, Web of Science, Scopus, Embase, Cochrane Library database to identify articles including machine learning models and algorithms to predict malignant transformation in OPMDs. Relevant bibliographic data, study characteristics, and outcomes were extracted for eligible studies. Quality of the included studies was assessed through the IJMEDI checklist.

RESULTS

Fifteen articles were found suitable for the review as per the PECOS criteria. Amongst all studies, highest sensitivity (100%) was recorded for U-net architecture, Peaks Random forest model, and Partial least squares discriminant analysis (PLSDA). Highest specificity (100%) was noted for PLSDA. Range of overall accuracy in risk prediction was between 95.4% and 74%.

CONCLUSION

Machine learning proved to be a viable tool in risk prediction, demonstrating heightened sensitivity, automation, and improved accuracy for predicting transformation of OPMDs. It presents an effective approach for incorporating multiple variables to monitor the progression of OPMDs and predict their malignant potential. However, its sensitivity to dataset characteristics necessitates the optimization of input parameters to maximize the efficiency of the classifiers.

Predictive value of machine learning for the severity of acute pancreatitis: A systematic review and meta-analysis

Background

Predicting the severity of acute pancreatitis (AP) early poses a challenge in clinical practice. While there are well-established clinical scoring tools, their actual predictive performance remains uncertain. Various studies have explored the application of machine-learning methods for early AP prediction. However, a more comprehensive evidence-based assessment is needed to determine their predictive accuracy. Hence, this systematic review and meta-analysis aimed to evaluate the predictive accuracy of machine learning in assessing the severity of AP.

Methods

PubMed, EMBASE, Cochrane Library, and Web of Science were systematically searched until December 5, 2023. The risk of bias in eligible studies was assessed using the Prediction Model Risk of Bias Assessment Tool (PROBAST). Subgroup analyses, based on different machine learning types, were performed. Additionally, the predictive accuracy of mainstream scoring tools was summarized.

Results

This systematic review ultimately included 33 original studies. The pooled c-index in both the training and validation sets was 0.87 (95 % CI: 0.84-0.89) and 0.88 (95 % CI: 0.86-0.90), respectively. The sensitivity in the training set was 0.81 (95 % CI: 0.77-0.84), and in the validation set, it was 0.79 (95 % CI: 0.71-0.85). The specificity in the training set was 0.84 (95 % CI: 0.78-0.89), and in the validation set, it was 0.90 (95 % CI: 0.86-0.93). The primary model incorporated was logistic regression; however, its predictive accuracy was found to be inferior to that of neural networks, random forests, and xgboost. The pooled c-index of the APACHE II, BISAP, and Ranson were 0.74 (95 % CI: 0.68-0.80), 0.77 (95 % CI: 0.70-0.85), and 0.74 (95 % CI: 0.68-0.79), respectively.

Conclusions

Machine learning demonstrates excellent accuracy in predicting the severity of AP, providing a reference for updating or developing a straightforward clinical prediction tool.

Critical appraisal of machine learning prognostic models for acute pancreatitis: protocol for a systematic review

Acute pancreatitis (AP) is an acute inflammatory disorder that is common, costly, and is increasing in incidence worldwide with over 300,000 hospitalizations occurring yearly in the United States alone. As its course and outcomes vary widely, a critical knowledge gap in the field has been a lack of accurate prognostic tools to forecast AP patients' outcomes. Despite several published studies in the last three decades, the predictive performance of published prognostic models has been found to be suboptimal. Recently, non-regression machine learning models (ML) have garnered intense interest in medicine for their potential for better predictive performance. Each year, an increasing number of AP models are being published. However, their methodologic quality relating to transparent reporting and risk of bias in study design has never been systematically appraised. Therefore, through collaboration between a group of clinicians and data scientists with appropriate content expertise, we will perform a systematic review of papers published between January 2021 and December 2023 containing artificial intelligence prognostic models in AP. To systematically assess these studies, the authors will leverage the CHARMS checklist, PROBAST tool for risk of bias assessment, and the most current version of the TRIPOD-AI. (Research Registry ( http://www.reviewregistry1727 .).

Development and validation of a multimodal model in predicting severe acute pancreatitis based on radiomics and deep learning

OBJECTIVE

Aim to establish a multimodal model for predicting severe acute pancreatitis (SAP) using machine learning (ML) and deep learning (DL).

METHODS

In this multicentre retrospective study, patients diagnosed with acute pancreatitis at admission were enrolled from January 2017 to December 2021. Clinical information within 24 h and CT scans within 72 h of admission were collected. First, we trained Model α based on clinical features selected by least absolute shrinkage and selection operator analysis. Second, radiomics features were extracted from 3D-CT scans and Model β was developed on the features after dimensionality reduction using principal component analysis. Third, Model γ was trained on 2D-CT images. Lastly, a multimodal model, namely PrismSAP, was constructed based on aforementioned features in the training set. The predictive accuracy of PrismSAP was verified in the validation and internal test sets and further validated in the external test set. Model performance was evaluated using area under the curve (AUC), accuracy, sensitivity, specificity, recall, precision and F1-score.

RESULTS

A total of 1,221 eligible patients were randomly split into a training set (n = 864), a validation set (n = 209) and an internal test set (n = 148). Data of 266 patients were for external testing. In the external test set, PrismSAP performed best with the highest AUC of 0.916 (0.873-0.960) among all models [Model α: 0.709 (0.618-0.800); Model β: 0.749 (0.675-0.824); Model γ: 0.687 (0.592-0.782); MCTSI: 0.778 (0.698-0.857); RANSON: 0.642 (0.559-0.725); BISAP: 0.751 (0.668-0.833); SABP: 0.710 (0.621-0.798)].

CONCLUSION

The proposed multimodal model outperformed any single-modality models and traditional scoring systems.

Automated machine learning for early prediction of acute kidney injury in acute pancreatitis

BACKGROUND

Acute kidney injury (AKI) represents a frequent and grave complication associated with acute pancreatitis (AP), substantially elevating both mortality rates and the financial burden of hospitalization. The aim of our study is to construct a predictive model utilizing automated machine learning (AutoML) algorithms for the early prediction of AKI in patients with AP.

METHODS

We retrospectively analyzed patients who were diagnosed with AP in our hospital from January 2017 to December 2021. These patients were randomly allocated into a training set and a validation set at a ratio of 7:3. To develop predictive models for each set, we employed the least absolute shrinkage and selection operator (LASSO) algorithm along with AutoML. A nomogram was developed based on multivariate logistic regression analysis outcomes. The model's efficacy was assessed using receiver operating characteristic (ROC) curves, calibration curves, and decision curve analysis (DCA). Additionally, the performance of the model constructed via AutoML was evaluated using decision curve analysis (DCA), feature importance, SHapley Additive exPlanations (SHAP) plots, and locally interpretable model-agnostic explanations (LIME).

RESULTS

This study incorporated a total of 437 patients who met the inclusion criteria. Out of these, 313 were assigned to the training cohort and 124 to the validation cohort. In the training and validation cohorts, AKI occurred in 68 (21.7%) and 29(23.4%) patients, respectively. Comparative analysis revealed that the AutoML models exhibited enhanced performance over traditional logistic regression (LR). Furthermore, the deep learning (DL) model demonstrated superior predictive accuracy, evidenced by an area under the ROC curve of 0.963 in the training set and 0.830 in the validation set, surpassing other comparative models. The key variables identified as significant in the DL model within the training dataset included creatinine (Cr), urea (Urea), international normalized ratio (INR), etiology, smoking, alanine aminotransferase (ALT), hypertension, prothrombin time (PT), lactate dehydrogenase (LDH), and diabetes.

CONCLUSION

The AutoML model, utilizing DL algorithm, offers considerable clinical significance in the early detection of AKI among patients with AP.

Multi-dimensional metabolomic profiling reveals dysregulated ornithine metabolism hallmarks associated with a severe acute pancreatitis phenotype

To reveal dysregulated metabolism hallmark that was associated with a severe acute pancreatitis (SAP) phenotype. In this study, LC-MS/MS-based targeted metabolomics was used to analyze plasma samples from 106 acute pancreatitis (AP) patients (34 mild, 38 moderate, and 34 severe) admitted within 48 hours from abdominal pain onset and 41 healthy controls. Temporal metabolic profiling was performed on days 1, 3, and 7 after admission. A random forest (RF) was performed to significantly determine metabolite differences between SAP and non-SAP (NSAP) groups. Mass spectrometry imaging (MSI) and immunohistochemistry were conducted for the examination of pancreatic metabolite and metabolic enzyme alterations, respectively, on necrosis and paracancerous tissues. Simultaneously determination of serum and pancreatic tissue metabolic alterations using an L-ornithine-induced AP model to discover metabolic commonalities. Twenty-two significant differential metabolites screened by RF were selected to build an accurate model for the prediction of SAP from NSAP (AUC = 0.955). Six of 22 markers were found by MSI with significant alterations in pancreatic lesions, reduced ornithine-related metabolites were also identified. The abnormally expressed arginase2 and ornithine transcarboxylase were further discovered in combination with time-course metabolic profiling in the SAP animal models, the decreased ornithine catabolites were found at a late stage of inflammation, but ornithine-associated metabolic enzymes were activated during the inflammatory process. The plasma metabolome of AP patients is distinctive, which shows promise for early SAP diagnosis. AP aggravation is linked to the activated ornithine metabolic pathway and its inadequate levels of catabolites in in-situ lesion.

Research related to the diagnosis of prostate cancer based on machine learning medical images: A review

BACKGROUND

Prostate cancer is currently the second most prevalent cancer among men. Accurate diagnosis of prostate cancer can provide effective treatment for patients and greatly reduce mortality. The current medical imaging tools for screening prostate cancer are mainly MRI, CT and ultrasound. In the past 20 years, these medical imaging methods have made great progress with machine learning, especially the rise of deep learning has led to a wider application of artificial intelligence in the use of image-assisted diagnosis of prostate cancer.

METHOD

This review collected medical image processing methods, prostate and prostate cancer on MR images, CT images, and ultrasound images through search engines such as web of science, PubMed, and Google Scholar, including image pre-processing methods, segmentation of prostate gland on medical images, registration between prostate gland on different modal images, detection of prostate cancer lesions on the prostate.

CONCLUSION

Through these collated papers, it is found that the current research on the diagnosis and staging of prostate cancer using machine learning and deep learning is in its infancy, and most of the existing studies are on the diagnosis of prostate cancer and classification of lesions, and the accuracy is low, with the best results having an accuracy of less than 0.95. There are fewer studies on staging. The research is mainly focused on MR images and much less on CT images, ultrasound images.

DISCUSSION

Machine learning and deep learning combined with medical imaging have a broad application prospect for the diagnosis and staging of prostate cancer, but the research in this area still has more room for development.

Systematic reviews of machine learning in healthcare: a literature review

INTRODUCTION

The increasing availability of data and computing power has made machine learning (ML) a viable approach to faster, more efficient healthcare delivery.

METHODS

A systematic literature review (SLR) of published SLRs evaluating ML applications in healthcare settings published between1 January 2010 and 27 March 2023 was conducted.

RESULTS

In total 220 SLRs covering 10,462 ML algorithms were reviewed. The main application of AI in medicine related to the clinical prediction and disease prognosis in oncology and neurology with the use of imaging data. Accuracy, specificity, and sensitivity were provided in 56%, 28%, and 25% SLRs respectively. Internal and external validation was reported in 53% and less than 1% of the cases respectively. The most common modeling approach was neural networks (2,454 ML algorithms), followed by support vector machine and random forest/decision trees (1,578 and 1,522 ML algorithms, respectively).

EXPERT OPINION

The review indicated considerable reporting gaps in terms of the ML's performance, both internal and external validation. Greater accessibility to healthcare data for developers can ensure the faster adoption of ML algorithms into clinical practice.

Machine learning models to detect and predict patient safety events using electronic health records: A systematic review

INTRODUCTION

Identifying patient safety events using electronic health records (EHRs) and automated machine learning-based detection methods can help improve the efficiency and quality of healthcare service provision.

OBJECTIVE

This study aimed to systematically review machine learning-based methods and techniques, as well as their results for patient safety event management using EHRs.

METHODS

We reviewed the studies that focused on machine learning techniques, including automatic prediction and detection of patient safety events and medical errors through EHR analysis to manage patient safety events. The data were collected by searching Scopus, PubMed (Medline), Web of Science, EMBASE, and IEEE Xplore databases.

RESULTS

After screening, 41 papers were reviewed. Support vector machine (SVM), random forest, conditional random field (CRF), and bidirectional long short-term memory with conditional random field (BiLSTM-CRF) algorithms were mostly applied to predict, identify, and classify patient safety events using EHRs; however, they had different performances. BiLSTM-CRF was employed in most of the studies to extract and identify concepts, e.g., adverse drug events (ADEs) and adverse drug reactions (ADRs), as well as relationships between drug and severity, drug and ADEs, drug and ADRs. Recurrent neural networks (RNN) and BiLSTM-CRF had the best results in detecting ADEs compared to other patient safety events. Linear classifiers and Naive Bayes (NB) had the highest performance for ADR detection. Logistic regression had the best results in detecting surgical site infections. According to the findings, the quality of articles has non-significantly improved in recent years, but they had low average scores.

CONCLUSIONS

Machine learning can be useful in automatic detection and prediction of patient safety events. However, most of these algorithms have not yet been externally validated or prospectively tested. Therefore, further studies are required to improve the performance of these automated systems.

Machine learning for prediction of viral hepatitis: A systematic review and meta-analysis

BACKGROUND

Lack of accurate and timely diagnosis of hepatitis poses obstacles to effective treatment, disease progression prevention, complication reduction, and life-saving interventions of patients. Utilizing machine learning can greatly enhance the achievement of timely and precise disease diagnosis. Therefore, we carried out this systematic review and meta-analysis to explore the performance of machine learning algorithms in predicting viral hepatitis.

METHODS

Using an extensive literature search in PubMed, Scopus, and Web of Science databases until June 15, 2023, English publications on hepatitis prediction using machine learning algorithms were included. Two authors independently extracted pertinent information from the selected studies. The PRISMA 2020 checklist was followed for study selection and result reporting. The risk of bias was checked using the International Journal of Medical Informatics (IJMEDI) checklist. Data were analyzed using the 'metandi' command in Stata 17.

RESULTS

Twenty-one original studies were included, covering 82 algorithms. Sixteen studies utilized five algorithms to predict hepatitis B. Ten studies used five algorithms for hepatitis C prediction. For hepatitis B prediction, the SVM algorithms demonstrated the highest sensitivity (90.0%; 95% confidence interval (CI): 77.0%-96.0%), specificity (94%; 95% CI: 90.0%-97.0%), and a diagnostic odds ratio (DOR) of 145 (95% CI: 37.0-559.0). In the case of hepatitis C, the KNN algorithms exhibited the highest sensitivity (80%; 95% CI:30.0%-97.0%), specificity (95%; 95% CI: 58.0%-99.0%), and DOR (72; 95% CI: 3.0-1644.0) for prediction.

CONCLUSION

SVM and KNN demonstrated superior performance in predicting hepatitis. The proper algorithm along with clinical practice could improve hepatitis prediction and management.

Predicting acute pancreatitis severity with enhanced computed tomography scans using convolutional neural networks

This study aimed to evaluate acute pancreatitis (AP) severity using convolutional neural network (CNN) models with enhanced computed tomography (CT) scans. Three-dimensional DenseNet CNN models were developed and trained using the enhanced CT scans labeled with two severity assessment methods: the computed tomography severity index (CTSI) and Atlanta classification. Each labeling method was used independently for model training and validation. Model performance was evaluated using confusion matrices, areas under the receiver operating characteristic curve (AUC-ROC), accuracy, precision, recall, F1 score, and respective macro-average metrics. A total of 1,798 enhanced CT scans met the inclusion criteria were included in this study. The dataset was randomly divided into a training dataset (n = 1618) and a test dataset (n = 180) with a ratio of 9:1. The DenseNet model demonstrated promising predictions for both CTSI and Atlanta classification-labeled CT scans, with accuracy greater than 0.7 and AUC-ROC greater than 0.8. Specifically, when trained with CT scans labeled using CTSI, the DenseNet model achieved good performance, with a macro-average F1 score of 0.835 and a macro-average AUC-ROC of 0.980. The findings of this study affirm the feasibility of employing CNN models to predict the severity of AP using enhanced CT scans.

Construction and validation of machine learning models for sepsis prediction in patients with acute pancreatitis

BACKGROUND

This study aimed to construct predictive models for the risk of sepsis in patients with Acute pancreatitis (AP) using machine learning methods and compared optimal one with the logistic regression (LR) model and scoring systems.

METHODS

In this retrospective cohort study, data were collected from the Medical Information Mart for Intensive Care III (MIMIC III) database between 2001 and 2012 and the MIMIC IV database between 2008 and 2019. Patients were randomly divided into training and test sets (8:2). The least absolute shrinkage and selection operator (LASSO) regression plus 5-fold cross-validation were used to screen and confirm the predictive factors. Based on the selected predictive factors, 6 machine learning models were constructed, including support vector machine (SVM), K-nearest neighbour (KNN), multi-layer perceptron (MLP), LR, gradient boosting decision tree (GBDT) and adaptive enhancement algorithm (AdaBoost). The models and scoring systems were evaluated and compared using sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, and the area under the curve (AUC).

RESULTS

A total of 1, 672 patients were eligible for participation. In the training set, 261 AP patients (19.51%) were diagnosed with sepsis. The predictive factors for the risk of sepsis in AP patients included age, insurance, vasopressors, mechanical ventilation, Glasgow Coma Scale (GCS), heart rate, respiratory rate, temperature, SpO2, platelet, red blood cell distribution width (RDW), International Normalized Ratio (INR), and blood urea nitrogen (BUN). The AUC of the GBDT model for sepsis prediction in the AP patients in the testing set was 0.985. The GBDT model showed better performance in sepsis prediction than the LR, systemic inflammatory response syndrome (SIRS) score, bedside index for severity in acute pancreatitis (BISAP) score, sequential organ failure assessment (SOFA) score, quick-SOFA (qSOFA), and simplified acute physiology score II (SAPS II).

CONCLUSION

The present findings suggest that compared to the classical LR model and SOFA, qSOFA, SAPS II, SIRS, and BISAP scores, the machine learning model-GBDT model had a better performance in predicting sepsis in the AP patients, which is a useful tool for early identification of high-risk patients and timely clinical interventions.

The role of artificial neural networks in prediction of severe acute pancreatitis associated acute respiratory distress syndrome: A retrospective study

Early identification and intervention of acute respiratory distress syndrome (ARDS) are particularly important. This study aimed to construct predictive models for ARDS following severe acute pancreatitis (SAP) by artificial neural networks and logistic regression. The artificial neural networks model was constructed using clinical data from 214 SAP patients. The patient cohort was randomly divided into a training set and a test set, with 149 patients allocated to the training set and 65 patients assigned to the test set. The artificial neural networks and logistic regression models were trained by the training set, and then the performance of both models was evaluated using the test set. The sensitivity, specificity, PPV, NPV, accuracy, and AUC value of artificial neural networks model were 68.0%, 87.5%, 77.3%, 81.4%, 80.0%, 0.853 ± 0.054 (95% CI: 0.749-0.958). The sensitivity, specificity, PPV, NPV, accuracy and AUC value of logistic regression model were 48.7%, 85.3%, 65.5%, 74.4%, 72.0%, 0.799 ± 0.045 (95% CI: 0.710-0.888). There were no significant differences between the artificial neural networks and logistic regression models in predictive performance. Bedside Index of Severity in Acute Pancreatitis score, procalcitonin, prothrombin time, and serum calcium were the most important predictive variables in the artificial neural networks model. The discrimination abilities of logistic regression and artificial neural networks models in predicting SAP-related ARDS were similar. It is advisable to choose the model according to the specific research purpose.

Use of machine learning to predict bladder cancer survival outcomes: a systematic literature review

INTRODUCTION

The objective of this systematic review is to summarize the use of machine learning (ML) in predicting overall survival (OS) in patients with bladder cancer.

METHODS

Search terms for bladder cancer, ML algorithms, and mortality were used to identify studies in PubMed and Web of Science as of February 2022. Notable inclusion/exclusion criteria contained the inclusion of studies that utilized patient-level datasets and exclusion of primary gene expression-related dataset studies. Study quality and bias were assessed using the International Journal of Medical Informatics (IJMEDI) checklist.

RESULTS

Of the 14 included studies, the most common algorithms were artificial neural networks (n = 8) and logistic regression (n = 4). Nine articles described missing data handling, with five articles removing patients with missing data entirely. With respect to feature selection, the most common sociodemographic variables were age (n = 9), gender (n = 9), and smoking status (n = 3), with clinical variables most commonly including tumor stage (n = 8), grade (n = 7), and lymph node involvement (n = 6). Most studies (n = 10) were of medium IJMEDI quality, with common areas of improvement being the descriptions of data preparation and deployment.

CONCLUSIONS

ML holds promise for optimizing bladder cancer care through accurate OS predictions, but challenges related to data processing, feature selection, and data source quality must be resolved to develop robust models. While this review is limited by its inability to compare models across studies, this systematic review will inform decision-making by various stakeholders to improve understanding of ML-based OS prediction in bladder cancer and foster interpretability of future models.

Machine learning in pancreas surgery, what is new? literature review

Background

Machine learning (ML) is an inquiry domain that aims to establish methodologies that leverage information to enhance performance of various applications. In the healthcare domain, the ML concept has gained prominence over the years. As a result, the adoption of ML algorithms has become expansive. The aim of this scoping review is to evaluate the application of ML in pancreatic surgery.

Methods

We integrated the preferred reporting items for systematic reviews and meta-analyses for scoping reviews. Articles that contained relevant data specializing in ML in pancreas surgery were included.

Results

A search of the following four databases PubMed, Cochrane, EMBASE, and IEEE and files adopted from Google and Google Scholar was 21. The main features of included studies revolved around the year of publication, the country, and the type of article. Additionally, all the included articles were published within January 2019 to May 2022.

Conclusion

The integration of ML in pancreas surgery has gained much attention in previous years. The outcomes derived from this study indicate an extensive literature gap on the topic despite efforts by various researchers. Hence, future studies exploring how pancreas surgeons can apply different learning algorithms to perform essential practices may ultimately improve patient outcomes.

Detecting acute respiratory diseases in the pediatric population using cough sound features and machine learning: A systematic review

BACKGROUND

Acute respiratory diseases are a leading cause of morbidity and mortality in children. Cough is a common symptom of acute respiratory diseases and the sound of cough can be indicative of the respiratory disease. However, cough sound assessment in routine clinical practice is limited to human perception and the skills of the clinician. Objective cough sound evaluation has the potential to aid clinicians in acute respiratory disease diagnosis. In this systematic review, we assess and summarize the predictive ability of machine learning algorithms in analyzing cough sounds of acute respiratory diseases in the pediatric population.

METHOD

Our systematic search of the Scopus, Medline, and Embase databases on 25 January 2023 identified six articles meeting the inclusion criteria. Quality assessment of the included studies was performed using the checklist for the assessment of medical artificial intelligence.

RESULTS

Our analysis shows variability in the input to the machine learning algorithms, such as the use of various cough sound features and combining cough sound features with clinical features. The use of the machine learning algorithms also varies from conventional algorithms, such as logistic regression and support vector machine, to deep learning techniques, such as convolutional neural networks. The classification accuracy for the detection of bronchiolitis, croup, pertussis, and pneumonia across five articles is in the range of 82-96%. However, a significant drop is observed in the detection accuracy for bronchiolitis and pneumonia in the remaining article.

CONCLUSION

The number of articles is limited but, in general, the predictive ability of cough sound classification algorithms in childhood acute respiratory diseases shows promise.

Robust Acute Pancreatitis Identification and Diagnosis: RAPIDx

The occurrence of acute pancreatitis (AP) is increasing significantly worldwide. However, current diagnostic methods of AP do not provide a clear clinical stratification of severity, and the prediction of complications in AP is still limited. Here, we present a robust AP identification and diagnosis (RAPIDx) method by the proteomic fingerprinting of intact nanoscale extracellular vesicles (EVs) from clinical samples. By tracking analysis of circulating biological nanoparticles released by cells (i.e., EVs) via bottom-up proteomics, we obtain close phenotype connections between EVs, cell types, and multiple tissues based on their specific proteomes and identify the serum amyloid A (SAA) proteins on EVs as potential biomarkers that are differentially expressed from AP patients significantly. We accomplish the quantitative analysis of EVs fingerprints using MALDI-TOF MS and find the SAA proteins (SAA1-1, desR-SAA1-2, SAA2, SAA1-2) with areas under the curve (AUCs) from 0.92 to 0.97, which allows us to detect AP within 30 min. We further realize that SAA1-1 and SAA2, combined with two protein peaks (5290.19, 14032.33 m/z), can achieve an AUC of 0.83 for classifying the severity of AP. The RAPIDx platform will facilitate timely diagnosis and treatment of AP before severity development and persistent organ failure and promote precision diagnostics and the early diagnosis of pancreatic cancer.

Artificial intelligence-based snakebite identification using snake images, snakebite wound images, and other modalities of information: A systematic review

BACKGROUND AND OBJECTIVE

Artificial intelligence (AI) is widely applied in medical decision support systems. AI also plays an essential role in snakebite identification (SI). To date, no review has been conducted on AI-based SI. This work aims to identify, compare, and summarize the state-of-the-art AI methods in SI. Another objective is to analyze these methods and propose solutions for future directions.

METHODS

Searches were performed in PubMed, Web of Science, Engineering Village, and IEEE Xplore to identify the SI studies. The datasets, preprocessing, feature extraction, and classification algorithms of these studies were systematically reviewed. Then, their merits and defects were also analyzed and compared. Next, the quality of these studies was assessed by using the ChAIMAI checklist. Finally, solutions were proposed based on the limitations of current studies.

RESULTS

Twenty-six articles were included in the review. Traditional machine learning (ML) and deep learning (DL) algorithms were applied for the classification of snake images (Acc = 72 %∼98 %), wound images (Acc = 80 %∼100 %), and other modalities of information (Acc = 71.67 %∼97.6 %). According to the research quality assessment, one of the studies was considered to be of high quality. Most studies were flawed in data preparation, data understanding, validation, and deployment dimensions. In addition, we propose an active perception-based system framework for collecting images and bite forces and constructing a multi-modal dataset named "Digital Snake" to address the lack of high-quality datasets for DL algorithms to improve recognition accuracy and robustness. A Snakebite Identification, Treatment, and Management Assistive Platform architecture is also proposed as a decision support system for patients and doctors.

CONCLUSIONS

AI-based methods can quickly and accurately decide the snake species and classify venomous and non-venomous snakes. Current studies still have limitations in SI. Future studies based on AI methods should focus on constructing high-quality datasets and decision support systems for snakebite treatment.

Anxiety, depression, and coping styles among patients with chronic pancreatitis in East China

BACKGROUND

Anxiety and depression are common psychological comorbidities in patients with chronic pancreatitis (CP). There is still a lack of epidemiological studies on anxiety and depression in Chinese CP patients. This study aimed to identify the incidence and related factor of anxiety and depression among East Chinese CP patients and explore the relationship between anxiety, depression, and coping styles.

METHODS

This prospective observational study was conducted from June 1, 2019 to March 31, 2021 in Shanghai, China. Patient diagnosed with CP were interviewed using the sociodemographic and clinical characteristics questionnaire, Self-rating Anxiety Scale (SAS), Self-rating Depression Scale (SDS), and Coping Style Questionnaire (CSQ). Multivariate logistic regression analysis was conducted to identify the related factors of anxiety and depression. Correlation test was preformed to analyze the correlation between anxiety, depression, and coping styles.

RESULTS

The incidence of anxiety and depression in East Chinese CP patients was 22.64% and 38.61%, respectively. Patients' previous health status, level of disease coping, frequency of abdominal pain episodes, and pain severity were significantly associated with anxiety and depression. Mature coping styles (Problem solving, Seeking for help) had a positive impact on anxiety and depression, while immature coping styles (Self-blame, Fantasy, Repression, Rationalization) had negative effects on anxiety and depression.

CONCLUSION

Anxiety and depression were common in patients with CP in China. The factors identified in this study may provide references for the management of anxiety and depression in CP patients.

Deep learning for pancreatic diseases based on endoscopic ultrasound: A systematic review

BACKGROUND AND AIMS

Endoscopic ultrasonography (EUS) is one of the main examinations in pancreatic diseases. A series of the studies reported the application of deep learning (DL)-assisted EUS in the diagnosis of pancreatic diseases. This systematic review is to evaluate the role of DL algorithms in assisting EUS diagnosis of pancreatic diseases.

METHODS

Literature search were conducted in PubMed and Semantic Scholar databases. Studies that developed DL models for pancreatic diseases based on EUS were eligible for inclusion. This review was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines and quality assessment of the included studies was performed according to the IJMEDI checklist.

RESULTS

A total of 23 studies were enrolled into this systematic review, which could be categorized into three groups according to computer vision tasks: classification, detection and segmentation. Seventeen studies focused on the classification task, among which five studies developed simple neural network (NN) models while twelve studies constructed convolutional NN (CNN) models. Three studies were concerned the detection task and five studies were the segmentation task, all based on CNN architectures. All models presented in the studies performed well based on EUS images, videos or voice. According to the IJMEDI checklist, six studies were recognized as high-grade quality, with scores beyond 35 points.

CONCLUSIONS

DL algorithms show great potential in EUS images/videos/voice for pancreatic diseases. However, there is room for improvement such as sample sizes, multi-center cooperation, data preprocessing, model interpretability, and code sharing.

Development and evaluation of machine learning models and nomogram for the prediction of severe acute pancreatitis

BACKGROUND AND AIM

Severe acute pancreatitis (SAP) in patients progresses rapidly and can cause multiple organ failures associated with high mortality. We aimed to train a machine learning (ML) model and establish a nomogram that could identify SAP, early in the course of acute pancreatitis (AP).

METHODS

In this retrospective study, 631 patients with AP were enrolled in the training cohort. For predicting SAP early, five supervised ML models were employed, such as random forest (RF), K-nearest neighbors (KNN), and naive Bayes (NB), which were evaluated by accuracy (ACC) and the areas under the receiver operating characteristic curve (AUC). The nomogram was established, and the predictive ability was assessed by the calibration curve and AUC. They were externally validated by an independent cohort of 109 patients with AP.

RESULTS

In the training cohort, the AUC of RF, KNN, and NB models were 0.969, 0.954, and 0.951, respectively, while the AUC of the Bedside Index for Severity in Acute Pancreatitis (BISAP), Ranson and Glasgow scores were only 0.796, 0.847, and 0.837, respectively. In the validation cohort, the RF model also showed the highest AUC, which was 0.961. The AUC for the nomogram was 0.888 and 0.955 in the training and validation cohort, respectively.

CONCLUSIONS

Our findings suggested that the RF model exhibited the best predictive performance, and the nomogram provided a visual scoring model for clinical practice. Our models may serve as practical tools for facilitating personalized treatment options and improving clinical outcomes through pre-treatment stratification of patients with AP.

Early prediction of the severe course, survival, and ICU requirements in acute pancreatitis by artificial intelligence

OBJECTIVE

To evaluate the success of artificial intelligence for early prediction of severe course, survival, and intensive care unit(ICU) requirement in patients with acute pancreatitis(AP).

METHODS

Retrospectively, 1334 patients were included the study. Severity is determined according to the Revised Atlanta Classification(RAC). The success of machine learning(ML) method was evaluated by 13 simple demographic, clinical, etiologic, and laboratory features obtained on ER admission. Additionally, it was evaluated whether Balthazar-computerized tomography severity index(CTSI) at 48-h contributed to success. The dataset was split into two parts, 90% for ML(of which 70% for learning and 30% for testing) and 10% for validation and 5-fold stratified sampling has been utilized. Variable Importance was used in the selection of features during training phase of machine. The Gradient Boost Algorithm trained the machine by KNIME analytics platform. SMOTE has been applied to increase the minority classes for training. The combined effects of the measured features were examined by multivariate logistic regression analysis and reciever operating curve curves of the prediction and confidence of the target variables were obtained.

RESULTS

Accuracy values for the early estimation of Atlanta severity score, ICU requirement, and survival were found as 88.20%, 98.25%, and 92.77% respectively. When Balthazar-CTSI score is used, results were found as 91.02%, 92.25%, and 98% respectively.

CONCLUSIONS

The ML method we used successfully predicted the severe course, ICU requirement and survival, with promising accuracy values of over 88%. If 48-h Balthazar-CTSI is included in the calculation, the severity score and survival rates increase even more.

Prediction of acute pancreatitis complications using routine blood parameters during early admission

BACKGROUND

There have been many reports on biomarkers for predicting the severity of acute pancreatitis (AP), but few studies on biomarkers for predicting complications; some simple and inexpensive indicators, in particular, are worth exploring.

METHODS

We retrospectively collected clinical data of 809 AP patients, including medical history and results of routine blood tests, and grouped them according to the occurrence of complications. Differences in clinical characteristics between groups with and without complications were compared using t-test or χ² test. Receiver operating curve (ROC) and area under the curve were calculated to evaluate the ability of predicting the occurrence of complications for the routine blood parameters with statistical differences. Then, through univariate and multivariate analyses, independent risk factors closely associated with complications were identified. Finally, we built a three-parameter prediction system and evaluated its ability to predict AP complications.

RESULTS

Compared with the group without complications, the patients in the complication group had higher white blood cells, neutrophils, C-reactive protein, and erythrocyte sedimentation rate (ESR), and lower red blood cells and hemoglobin (Hb) (all p < .05), and most of them had severe pancreatitis. In addition, pseudocysts were more common in patients with alcoholic etiology, recurrence, low BMI, and high platelet (PLT) and plateletocrit. Acute respiratory failure was more common in patients with first onset and high mean PLT volume (MPV). Sepsis was more common in patients with lipogenic etiology, high MPV, and low lymphocytes. Infectious pancreatic necrosis was more common in patients with alcoholic etiology. Acute renal failure was more common in patients with monocytes and high MPV and low PLT. Multivariate analysis showed that PLT and ESR were risk factors for pseudocyst development. The ROC showed that the combination of Hb, PLT and ESR had a significantly higher predictive ability for pseudocyst than the single parameter.

CONCLUSION

Routine blood parameters can be used to predict the complications of AP. A predictive model combining ESR, PLT, and Hb may be an effective tool for identifying pseudocysts in AP patients.

Improving mortality prediction in Acute Pancreatitis by machine learning and data augmentation

Acute Pancreatitis (AP) is the inflammation of the pancreas that can be fatal or lead to further complications based on the severity of the attack. Early detection of AP disease can help save lives by providing utmost care, rigorous treatment, and better resources. In this era of data and technology, instead of relying on manual scoring systems, scientists are employing advanced machine learning and data mining models for the early detection of patients with high chances of mortality. The current work on AP mortality prediction is negligible, and the few studies that exist have many shortcomings and are impractical for clinical deployment. In this research work, we tried to overcome the existing issues. One main issue is the lack of high-quality public datasets for AP, which are crucial for effectively training ML models. The available datasets are small in size, have many missing values, and suffer from high class imbalance. We augmented three public datasets, MIMIC-III, MIMIC-IV, and eICU, to obtain a larger dataset, and experiments proved that augmented data trained classifiers better than original small datasets. Moreover, we employed emerging advanced techniques to handle underlying issues in data. The results showed that iterative imputer is best for filling missing values in AP data. It beats not only the basic techniques but also the Knn-based imputation. Class imbalance is first addressed using data downsampling; apparently, it gave decent results on small test sets. However, we conducted numerous experiments on large test sets to prove that downsampling in the case of AP produced misleading and poor results. Next, we applied various techniques to upsample data in two different class splits, a 50 to 50 and a 70 to 30 majority-minority class split. Four different tabular generative adversarial networks, CTGAN, TGAN, CopulaGAN, and CTAB, and a variational autoencoder, TVAE, were deployed for synthetic data generation. SMOTE was also utilized for data upsampling. The computational results showed that the Random Forest (RF) classifier outperformed all other classifiers on a 50 to 50 class split data generated by CTGAN, with 0.702 Fβ and 0.833 recall. Results produced by RF on the TVAE dataset were also comparable, with 0.698 Fβ. In the case of SMOTE-based upsampling, DNN performed best with a 0.671 Fβ score.

Acute Pancreatitis: Diagnosis and Treatment

Acute pancreatitis is a common indication for hospital admission, increasing in incidence, including in children, pregnancy and the elderly. Moderately severe acute pancreatitis with fluid and/or necrotic collections causes substantial morbidity, and severe disease with persistent organ failure causes significant mortality. The diagnosis requires two of upper abdominal pain, amylase/lipase ≥ 3 ×upper limit of normal, and/or cross-sectional imaging findings. Gallstones and ethanol predominate while hypertriglyceridaemia and drugs are notable among many causes. Serum triglycerides, full blood count, renal and liver function tests, glucose, calcium, transabdominal ultrasound, and chest imaging are indicated, with abdominal cross-sectional imaging if there is diagnostic uncertainty. Subsequent imaging is undertaken to detect complications, for example, if C-reactive protein exceeds 150 mg/L, or rarer aetiologies. Pancreatic intracellular calcium overload, mitochondrial impairment, and inflammatory responses are critical in pathogenesis, targeted in current treatment trials, which are crucially important as there is no internationally licenced drug to treat acute pancreatitis and prevent complications. Initial priorities are intravenous fluid resuscitation, analgesia, and enteral nutrition, and when necessary, critical care and organ support, parenteral nutrition, antibiotics, pancreatic exocrine and endocrine replacement therapy; all may have adverse effects. Patients with local complications should be referred to specialist tertiary centres to guide further management, which may include drainage and/or necrosectomy. The impact of acute pancreatitis can be devastating, so prevention or reduction of the risk of recurrence and progression to chronic pancreatitis with an increased risk of pancreas cancer requires proactive management that should be long term for some patients.

Automated Machine Learning for the Early Prediction of the Severity of Acute Pancreatitis in Hospitals

Background

Machine learning (ML) algorithms are widely applied in building models of medicine due to their powerful studying and generalizing ability. This study aims to explore different ML models for early identification of severe acute pancreatitis (SAP) among patients hospitalized for acute pancreatitis.

Methods

This retrospective study enrolled patients with acute pancreatitis (AP) from multiple centers. Data from the First Affiliated Hospital and Changshu No. 1 Hospital of Soochow University were adopted for training and internal validation, and data from the Second Affiliated Hospital of Soochow University were adopted for external validation from January 2017 to December 2021. The diagnosis of AP and SAP was based on the 2012 revised Atlanta classification of acute pancreatitis. Models were built using traditional logistic regression (LR) and automated machine learning (AutoML) analysis with five types of algorithms. The performance of models was evaluated by the receiver operating characteristic (ROC) curve, the calibration curve, and the decision curve analysis (DCA) based on LR and feature importance, SHapley Additive exPlanation (SHAP) Plot, and Local Interpretable Model Agnostic Explanation (LIME) based on AutoML.

Results

A total of 1,012 patients were included in this study to develop the AutoML models in the training/validation dataset. An independent dataset of 212 patients was used to test the models. The model developed by the gradient boost machine (GBM) outperformed other models with an area under the ROC curve (AUC) of 0.937 in the validation set and an AUC of 0.945 in the test set. Furthermore, the GBM model achieved the highest sensitivity value of 0.583 among these AutoML models. The model developed by eXtreme Gradient Boosting (XGBoost) achieved the highest specificity value of 0.980 and the highest accuracy of 0.958 in the test set.

Conclusions

The AutoML model based on the GBM algorithm for early prediction of SAP showed evident clinical practicability.

Prevalence and Outcomes of Pancreatic Enzymes Elevation in Patients With COVID-19: A Meta-Analysis and Systematic Review

Background

Although coronavirus disease 2019 (COVID-19) is considered to be a disease that mainly involves the respiratory system, an increasing number of studies have reported that COVID-19 patients had pancreatic enzymes (PE) elevation and even pancreatic injury. The study aims to determine the prevalence of PE elevation, and the relationship between elevated PE and prognosis in COVID-19 patients.

Methods

A comprehensive literature search was conducted according to the PRISMA guideline in PubMed, Embase, Scopus, Web of Science, and Google Scholar for studies reporting PE elevation in patients with COVID-19 from 1st January 2020 to 24th November 2021.

Results

A total of 13 studies (24,353 participants) were included in our review. The pooled prevalence of PE elevation in COVID-19 patients was 24% (18%-31%), the pooled odds ratio (OR) of mortality was 2.5 (1.7-3.6), the pooled OR of ICU admission was 4.4 (2.8-6.8), and the pooled OR of kidney injury, respiratory failure and liver injury were 3.5 (1.6-7.4), 2.0 (0.5-8.7), and 2.3 (1.4-3.9) respectively. In addition, the subgroup analysis revealed that although PE elevated to > 3 × upper normal limit (ULN) was significantly related to the mortality (OR = 4.4, 2.1-9.4), it seemed that mild elevation of PE to 1-3 ULN also had a considerable risk of mortality (OR = 2.3, 1.5-3.5).

Conclusions

PE elevation was a common phenomenon in patients with COVID-19, and was associated with poor clinical outcomes. However, due to the limited numbers of included studies, the result of our study still needed to be validated.

Systematic Review Registration

https://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=295630, identifier: CRD42021295630.

Ideal scoring system for acute pancreatitis: Quest for the Holy Grail

Clinical scoring systems are required to predict complications, severity, need for intensive care unit admission, and mortality in patients with acute pancreatitis. Over the years, many scores have been developed, tested, and compared for their efficacy and accuracy. An ideal score should be rapid, reliable, and validated in different patient populations and geographical areas and should not lose relevance over time. A combination of scores or serial monitoring of a single score may increase their efficacy.

Usefulness of Random Forest Algorithm in Predicting Severe Acute Pancreatitis

BACKGROUND AND AIMS

This study aimed to develop an interpretable random forest model for predicting severe acute pancreatitis (SAP).

METHODS

Clinical and laboratory data of 648 patients with acute pancreatitis were retrospectively reviewed and randomly assigned to the training set and test set in a 3:1 ratio. Univariate analysis was used to select candidate predictors for the SAP. Random forest (RF) and logistic regression (LR) models were developed on the training sample. The prediction models were then applied to the test sample. The performance of the risk models was measured by calculating the area under the receiver operating characteristic (ROC) curves (AUC) and area under precision recall curve. We provide visualized interpretation by using local interpretable model-agnostic explanations (LIME).

RESULTS

The LR model was developed to predict SAP as the following function: -1.10-0.13×albumin (g/L) + 0.016 × serum creatinine (μmol/L) + 0.14 × glucose (mmol/L) + 1.63 × pleural effusion (0/1)(No/Yes). The coefficients of this formula were utilized to build a nomogram. The RF model consists of 16 variables identified by univariate analysis. It was developed and validated by a tenfold cross-validation on the training sample. Variables importance analysis suggested that blood urea nitrogen, serum creatinine, albumin, high-density lipoprotein cholesterol, low-density lipoprotein cholesterol, calcium, and glucose were the most important seven predictors of SAP. The AUCs of RF model in tenfold cross-validation of the training set and the test set was 0.89 and 0.96, respectively. Both the area under precision recall curve and the diagnostic accuracy of the RF model were higher than that of both the LR model and the BISAP score. LIME plots were used to explain individualized prediction of the RF model.

CONCLUSIONS

An interpretable RF model exhibited the highest discriminatory performance in predicting SAP. Interpretation with LIME plots could be useful for individualized prediction in a clinical setting. A nomogram consisting of albumin, serum creatinine, glucose, and pleural effusion was useful for prediction of SAP.