4.7 Article

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

Related references

Note: Only part of the references are listed.
Review Computer Science, Information Systems

Machine learning predictive models for acute pancreatitis: A systematic review

You Zhou et al.

Summary: Machine learning has shown great potential in assisting decision-making in the prediction tasks of acute pancreatitis. However, existing studies still have some deficiencies that need to be optimized and evaluated to develop high-quality machine learning models for clinical practice.

INTERNATIONAL JOURNAL OF MEDICAL INFORMATICS (2022)

Article Gastroenterology & Hepatology

The Modified Pancreatitis Activity Scoring System Shows Distinct Trajectories in Acute Pancreatitis: An International Study

Pedram Paragomi et al.

Summary: This study aims to evaluate the performance of the Pancreatitis Activity Scoring System (PASS) in a global patient cohort and investigate the predictive accuracy and distinct trajectories of a modified PASS. The results suggest that the modified PASS performs well in predicting disease severity and exhibits distinct trajectories between severity subgroups.

CLINICAL GASTROENTEROLOGY AND HEPATOLOGY (2022)

Article Oncology

Development and validation of a novel model incorporating MRI-based radiomics signature with clinical biomarkers for distinguishing pancreatic carcinoma from mass-forming chronic pancreatitis

Jingjing Liu et al.

Summary: A mixed model combining MRI-based radiomics signature with clinical biomarkers was developed and preliminarily validated to distinguish pancreatic carcinoma (PC) from mass-forming chronic pancreatitis (MFCP), which is of great importance for treatment strategy formulation and selection of nonsurgical procedures.

TRANSLATIONAL ONCOLOGY (2022)

Article Gastroenterology & Hepatology

Management of Severe Acute Pancreatitis: An Update

Nina Gliem et al.

Summary: Severe acute pancreatitis is a serious gastrointestinal disease with high morbidity and mortality. Successful clinical management requires close interdisciplinary cooperation and coordination. Early targeted fluid therapy, thoracic epidural analgesia, and early enteral feeding are important for improving outcomes in severe AP patients. Persistent organ failure is a strong predictor of poor prognosis, and infected walled-off necrosis should be primarily treated by minimally invasive endoscopic step-up approaches.

DIGESTION (2021)

Article Urology & Nephrology

A practical guide to multiple imputation of missing data in nephrology

Katrina Blazek et al.

Summary: Health data often have missing values, and utilizing multiple imputation techniques can help reduce bias and maintain sample size. Correct specification of the imputation model is crucial for the validity of analyses. Considerations such as missing mechanism, imputation method, and result reporting are important when conducting research with multiply imputed data.

KIDNEY INTERNATIONAL (2021)

Article Biochemistry & Molecular Biology

The association of parameters of body composition and laboratory markers with the severity of hypertriglyceridemia-induced pancreatitis

Lifang Chen et al.

Summary: Low serum albumin and apolipoprotein A-I, high C-reactive protein and lipase levels at admission were associated with a more severe type of HTGP and longer hospital stay. Albumin and apolipoprotein A-I may serve as novel biomarkers for the severity of HTGP. However, none of the body composition parameters was associated with the severity of HTGP.

LIPIDS IN HEALTH AND DISEASE (2021)

Article Multidisciplinary Sciences

Artificial intelligence in sepsis early prediction and diagnosis using unstructured data in healthcare

Kim Huat Goh et al.

Summary: Sepsis is a major cause of death in hospitals, and early prediction and diagnosis are challenging. The study develops an artificial intelligence algorithm using both structured data and unstructured clinical notes, demonstrating high predictive accuracy 12 hours before the onset of sepsis.

NATURE COMMUNICATIONS (2021)

Article Health Care Sciences & Services

Establishing Machine Learning Models to Predict Curative Resection in Early Gastric Cancer with Undifferentiated Histology: Development and Usability Study

Chang Seok Bang et al.

Summary: This study established a machine learning model to accurately predict the possibility of curative resection in U-EGC before ESD by considering the morphological and ecological characteristics of the lesions. Among the 18 models, the extreme gradient boosting classifier showed the best performance with high accuracy in both internal and external validation. Lesion size was identified as the most important feature in explainable artificial intelligence analysis.

JOURNAL OF MEDICAL INTERNET RESEARCH (2021)

Article Biochemistry & Molecular Biology

Accuracy of conventional and novel scoring systems in predicting severity and outcomes of acute pancreatitis: a retrospective study

Qing Wu et al.

Summary: The study compared the effectiveness of novel and conventional scoring systems in predicting the severity and outcomes of acute pancreatitis. RS and GS predicted severity better, while PASS performed better in predicting mortality and organ failure. BISAP and CSSS performed equally well in severity and outcome predictions.

LIPIDS IN HEALTH AND DISEASE (2021)

Article Cell Biology

Prediction of Multiple Organ Failure Complicated by Moderately Severe or Severe Acute Pancreatitis Based on Machine Learning: A Multicenter Cohort Study

Fumin Xu et al.

Summary: The study successfully developed a predictive model of multiple organ failure complicating moderately severe or severe acute pancreatitis using machine learning. The adaptive boosting algorithm showed the best predictive performance among the six models tested.

MEDIATORS OF INFLAMMATION (2021)

Article Gastroenterology & Hepatology

Development and validation of a prediction model for deep vein thrombosis in older non-mild acute pancreatitis patients

Du-Jiang Yang et al.

Summary: A prediction nomogram model for DVT in elderly patients with moderate and severe acute pancreatitis was developed and validated, incorporating factors such as age, sex, surgery times, and blood markers. This model may assist doctors in making decisions regarding DVT prophylaxis based on individual patient risk factors.

WORLD JOURNAL OF GASTROINTESTINAL SURGERY (2021)

Article Oncology

Cardiac indicator CK-MB might be a predictive marker for severity and organ failure development of acute pancreatitis

Bing Zhao et al.

Summary: The prediction of severe acute pancreatitis is crucial for providing timely and targeted intensive care for acute pancreatitis. Cardiac function is involved in early stage SAP, and CK-MB may serve as an effective biomarker for predicting SAP occurrence and organ failure development upon admission.

ANNALS OF TRANSLATIONAL MEDICINE (2021)

Article Gastroenterology & Hepatology

Evaluation of the Prognostic Value of Red Cell Distribution Width to Total Serum Calcium Ratio in Patients with Acute Pancreatitis

Tian-Yong Han et al.

Summary: This retrospective study evaluated the prognostic value of RDW, TSC, and RDW/TSC in patients with AP, and found that RDW/TSC may be a new method to predict the prognosis of AP patients at an early stage. The study showed that RDW/TSC had better predictive value in predicting the need for ICU admission, surgery treatment, and hospital survival compared to TSC, suggesting that RDW/TSC could be a useful tool in identifying AP patients with poor prognosis.

GASTROENTEROLOGY RESEARCH AND PRACTICE (2021)

Article Medicine, General & Internal

Pleural effusion volume in patients with acute pancreatitis: a retrospective study from three acute pancreatitis centers

Gaowu Yan et al.

Summary: The volume of pleural effusion quantified on chest CT is closely related to the clinical outcomes and severity of acute pancreatitis in patients, serving as a reliable radiologic biomarker for predicting the severity and clinical outcomes of the disease.

ANNALS OF MEDICINE (2021)

Article Radiology, Nuclear Medicine & Medical Imaging

Chest computed tomography semi-quantitative pleural effusion and pulmonary consolidation are early predictors of acute pancreatitis severity

Rong Peng et al.

QUANTITATIVE IMAGING IN MEDICINE AND SURGERY (2020)

Article Gastroenterology & Hepatology

Triglyceride and glucose (TyG) index is an effective biomarker to identify severe acute pancreatitis

Jin Myung Park et al.

PANCREATOLOGY (2020)

Article Medicine, General & Internal

Deceased serum bilirubin and albumin levels in the assessment of severity and mortality in patients with acute pancreatitis

Xiao Xu et al.

INTERNATIONAL JOURNAL OF MEDICAL SCIENCES (2020)

Article Medicine, Research & Experimental

Development and validation of a risk prediction score for severe acute pancreatitis

Wandong Hong et al.

JOURNAL OF TRANSLATIONAL MEDICINE (2019)

Review Urology & Nephrology

Reporting and Interpreting Decision Curve Analysis: A Guide for Investigators

Ben Van Calster et al.

EUROPEAN UROLOGY (2018)

Article Gastroenterology & Hepatology

Serum Albumin Is Independently Associated with Persistent Organ Failure in Acute Pancreatitis

Wandong Hong et al.

CANADIAN JOURNAL OF GASTROENTEROLOGY AND HEPATOLOGY (2017)

Article Emergency Medicine

Serum calcium as an indicator of persistent organ failure in acute pancreatitis

Tao Peng et al.

AMERICAN JOURNAL OF EMERGENCY MEDICINE (2017)

Article Cardiac & Cardiovascular Systems

Machine Learning in Medicine

Rahul C. Deo

CIRCULATION (2015)

Article Biochemical Research Methods

An AUC-based permutation variable importance measure for random forests

Silke Janitza et al.

BMC BIOINFORMATICS (2013)

Article Gastroenterology & Hepatology

A Comparative Evaluation of Radiologic and Clinical Scoring Systems in the Early Prediction of Severity in Acute Pancreatitis

Thomas L. Bollen et al.

AMERICAN JOURNAL OF GASTROENTEROLOGY (2012)

Article Gastroenterology & Hepatology

D-Dimer in Acute Pancreatitis A New Approach for an Early Assessment of Organ Failure

Dejan Radenkovic et al.

PANCREAS (2009)