Machine learning predictive models for acute pancreatitis: A systematic review

Zhou, Yuhua; Ge, Yutong; Shi, Xiaolei; Wu, Keyan; Chen, Weiwei; Ding, Yanbing; Xiao, Weiming; Wang, Dan; Lu, Guotao; Hu, Liang‐Hao

doi:10.1016/j.ijmedinf.2021.104641

Cited by 40 publications

(22 citation statements)

References 58 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Delayed prognostication, although not optimal, remains helpful because this may be when patients reach specialist service provision in some geographical areas [16]. Machine-learning approaches have been applied to increase the accuracy of prediction [107], although extensive evaluation of these and other approaches, for example omics technologies, is required [108,109]. The simpler the method, the more applicable it becomes; point-of-care technology is required for omics applications [110,111].…”

Section: Predicted Severitymentioning

confidence: 99%

Acute Pancreatitis: Diagnosis and Treatment

Szatmary

Grammatikopoulos

Cai

et al. 2022

Drugs

205

View full text Add to dashboard Cite

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 crosssectional 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.

show abstract

Section: Predicted Severitymentioning

confidence: 99%

Acute Pancreatitis: Diagnosis and Treatment

Szatmary

Grammatikopoulos

Cai

et al. 2022

Drugs

205

View full text Add to dashboard Cite

show abstract

“…Among the included multi-center studies, one was a database study ( 25 ), one study was based on two tertiary hospitals and four community hospitals ( 16 ), and two studies was based on several major tertiary medical systems ( 14 , 29 ). Since the time of data recorded and the methods of measurement and testing in public databases were difficult to ensure consistency ( 50 ), and the conditions of patients in community hospitals were different from those in tertiary medical institutions, we believed that the existing multi-center studies may underestimate the real risk of mortality in COVID-19 patients with elevated PE. Therefore, we hoped that prospective studies based on several tertiary medical institutions can be carried out to explore the real risk of hospital mortality related to PE elevation in COVID-19 patients.…”

Section: Discussionmentioning

confidence: 99%

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

Zhou

Yang

et al. 2022

Front. Public Health

Self Cite

View full text Add to dashboard Cite

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.MethodsA 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.ResultsA 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).ConclusionsPE 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 Registrationhttps://www.crd.york.ac.uk/PROSPERO/display_record.php?RecordID=295630, identifier: CRD42021295630.

show abstract

“…Machine learning has been extensively used for the prediction of severity or complication of AP (Zhou et al, 2022). Thapa et al has reported that an XGBoost model could predict which patients would require treatment for SAP (Thapa et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Usefulness of Random Forest Algorithm in Predicting Severe Acute Pancreatitis

Hong

Zhou

et al. 2022

Front. Cell. Infect. Microbiol.

View full text Add to dashboard Cite

Background and AimsThis study aimed to develop an interpretable random forest model for predicting severe acute pancreatitis (SAP).MethodsClinical 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).ResultsThe 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.ConclusionsAn 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.

show abstract

Machine learning predictive models for acute pancreatitis: A systematic review

Cited by 40 publications

References 58 publications

Acute Pancreatitis: Diagnosis and Treatment

Acute Pancreatitis: Diagnosis and Treatment

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

Usefulness of Random Forest Algorithm in Predicting Severe Acute Pancreatitis

Contact Info

Product

Resources

About