Machine Learning Can Improve Prediction of Severity in Acute Pancreatitis Using Admission Values of APACHE II Score and C-Reactive Protein

doi:10.1159/000090032

Pancreatology

Volume 6, Issues 1–2, April 2006, Pages 123-131

https://doi.org/10.1159/000090032 Get rights and content

Abstract

Background: Acute pancreatitis (AP) has a variable course. Accurate early prediction of severity is essential to direct clinical care. Current assessment tools are inaccurate, and unable to adapt to new parameters. None of the current systems uses C-reactive protein (CRP). Modern machine-learning tools can address these issues. Methods: 370 patients admitted with AP in a 5-year period were retrospectively assessed; after exclusions, 265 patients were studied. First recorded values for physical examination and blood tests, aetiology, severity and complications were recorded. A kernel logistic regression model was used to remove redundant features, and identify the relationships between relevant features and outcome. Bootstrapping was used to make the best use of data and obtain confidence estimates on the parameters of the model.Results: A model containing 8 variables (age, CRP, respiratory rate, pO₂ on air, arterial pH, serum creatinine, white cell count and GCS) predicted a severe attack with an area under the receiver-operating characteristic curve (AUC) of 0.82 (SD 0.01). The optimum cut-off value for predicting severity gave sensitivity and specificity of 0.87 and 0.71 respectively. The predictions were significantly better (p = 0.0036) than admission APACHE II scores in the same patients (AUC 0.74) and better than historical admission APACHE II data (AUC 0.68-0.75).Conclusions: This system for the first time combines admission values of selected components of APACHE II and CRP for prediction of severe AP. The score is simple to use, and is more accurate than admission APACHE II alone. It is adaptable and would allow incorporation of new predictive factors.

References (58)

ML Steer
Early events in acute pancreatitis
Baillieres Best Pract Res Clin Gastroenterol
(1999)
J Norman
The role of cytokines in the patho-genesis of acute pancreatitis
Am J Surg
(1998)
AP Corfield et al.
Prediction of severity in acute pancreatitis: prospective comparison of three prognostic indices
Lancet
(1985)
M Larvin et al.
APACHE-II score for assessment and monitoring of acute pancreatitis
Lancet
(1989)
F Imbert-Bismut et al.
Biochemical markers of liver fibrosis in patients with hepatitis C virus infection: A prospective study
Lancet
(2001)
RK Orr
Use of an artificial neural network to quantitate risk of malignancy for abnormal mammograms
Surgery
(2001)
T Blum et al.
Fatal outcome in acute pancreatitis: its occurrence and early prediction
Pancreatology
(2001)
CD Johnson et al.
Combination of APACHE II score and an obesity score (APACHE O) for the prediction of severe acute pancreatitis
Pancreatology
(2004)
CC Chen et al.
Proinflammatory cytokines in early assessment of the prognosis of acute pancreatitis
Am J Gastro-enterol
(1999)
MT Keogan et al.
Outcome analysis of patients with acute pancreatitis by using an artificial neural network
Acad Radiol
(2002)

EJ Balthazar

CT diagnosis and staging of acute pancreatitis

Radiol Clin N Am

(1989)

J Wyatt

Nervous about artificial neural networks?

Lancet

(1995)

United Kingdom guidelines for the management of acute pancreatitis

British Society of Gastroenterology

Gut

(1998)

R Gupta et al.

Early ERCP is an essential part of the management of all cases of acute pancreatitis

Ann R Coll Surg Engl

(1999)

CD Johnson

Antibiotic prophylaxis in severe acute pancreatitis

Br J Surg

(1996)

M Ratschko et al.

The role of antibiotic prophylaxis in the treatment of acute pancreatitis

Gastroenterol Clin North Am

(1999)

GH Sakorafas et al.

Etiology and pathogenesis of acute pancreatitis: current concepts

J Clin Gastroenterol

(2000)

M Bhatia et al.

Role of substance P and the neurokinin 1 receptor in acute pancreatitis and pancreatitis-associated lung injury

Proc Natl Acad Sci USA

(1998)

MJ Mc Mahon et al.

A comparative study of methods for the prediction of severity of attacks of acute pancreatitis

Br J Surg

(1980)

C Wilson et al.

Prediction of outcome in acute pancreatitis: a comparative study of APACHE II, clinical assessment and multiple factor scoring systems

Br J Surg

(1990)

JH Ranson et al.

Objective early identification of severe acute pancreatitis

Am J Gastroenterol

(1974)

CW Imrie et al.

A single-centre double-blind trial of Trasylol therapy in primary acute pancreatitis

Br J Surg

(1978)

SL Blamey et al.

Prognostic factors in acute pancreatitis

Gut

(1984)

CW Imrie

Ranson, Glasgow, APACHE II systems: is the score a bore?

C Dervenis et al.

Diagnosis, objective assessment of severity, and management of acute pancreatitis. Santorini consensus conference

Int J Pancreatol

(1999)

AA Sandberg et al.

Early prediction of severity in acute pancreatitis. Is this possible?

JOP

(2002)

M Larvin

V Gross et al.

Granulocyte elastase in assessment of severity of acute pancreatitis. Comparison with acute-phase proteins C-reactive protein, a₁-antitryp-sin, and protease inhibitor a₂-macroglobulin

Dig Dis Sci

(1990)

JE Dominguez-Munoz et al.

Hyperlipidemia in acute pancreatitis. Relationship with etiology, onset, and severity of the disease

Int J Pancreatol

(1991)

Cited by (69)

Early prediction of the severe course, survival, and ICU requirements in acute pancreatitis by artificial intelligence
2023, Pancreatology
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).
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.
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.
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.
Artificial intelligence in liver diseases: Improving diagnostics, prognostics and response prediction
2022, JHEP Reports
Clinical routine in hepatology involves the diagnosis and treatment of a wide spectrum of metabolic, infectious, autoimmune and neoplastic diseases. Clinicians integrate qualitative and quantitative information from multiple data sources to make a diagnosis, prognosticate the disease course, and recommend a treatment. In the last 5 years, advances in artificial intelligence (AI), particularly in deep learning, have made it possible to extract clinically relevant information from complex and diverse clinical datasets. In particular, histopathology and radiology image data contain diagnostic, prognostic and predictive information which AI can extract. Ultimately, such AI systems could be implemented in clinical routine as decision support tools. However, in the context of hepatology, this requires further large-scale clinical validation and regulatory approval. Herein, we summarise the state of the art in AI in hepatology with a particular focus on histopathology and radiology data. We present a roadmap for the further development of novel biomarkers in hepatology and outline critical obstacles which need to be overcome.
Machine learning predictive models for acute pancreatitis: A systematic review
2022, International Journal of Medical Informatics
Citation Excerpt :
Two studies [22,29] used LR models. Pearc et al. [29] used an LR model with a sensitivity of 0.87 and a specificity of 0.71, which was superior to the single APACHE Ⅱ score in predicting SAP. In the study by Sun et al. [22], the combined model of LR based on 11 markers and the Ranson score had a better performance, with an AUROC of 0.79.
Acute pancreatitis (AP) is a common clinical pancreatic disease. Patients with different severity levels have different clinical outcomes. With the advantages of algorithms, machine learning (ML) has gradually emerged in the field of disease prediction, assisting doctors in decision-making.
A systematic review was conducted using the PubMed, Web of Science, Scopus, and Embase databases, following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. Publication time was limited from inception to 29 May 2021. Studies that have used ML to establish predictive tools for AP were eligible for inclusion. Quality assessment of the included studies was conducted in accordance with the IJMEDI checklist.
In this systematic review, 24 of 2,913 articles, with a total of 8,327 patients and 47 models, were included. The studies could be divided into five categories: 10 studies (42%) reported severity prediction; 10 studies (42%), complication prediction; 3 studies (13%), mortality prediction; 2 studies (8%), recurrence prediction; and 2 studies (8%), surgery timing prediction. ML showed great accuracy in several prediction tasks. However, most of the included studies were retrospective in nature, conducted at a single centre, based on database data, and lacked external validation. According to the IJMEDI checklist and our scoring criteria, two studies were considered to be of high quality. Most studies had an obvious bias in the quality of data preparation, validation, and deployment dimensions.
In the prediction tasks for AP, ML has shown great potential in assisting decision-making. However, the existing studies still have some deficiencies in the process of model construction. Future studies need to optimize the deficiencies and further evaluate the comparability of the ML systems and model performance, so as to consequently develop high-quality ML-based models that can be used in clinical practice.
Early prediction of severe acute pancreatitis using machine learning
2022, Pancreatology
Citation Excerpt :
To this end, several studies have applied machine learning methods to SAP prediction. Pearce et al. developed a machine learning algorithm that utilized CRP measurements to predict SAP, and found that the model outperformed the APACHE II score [47]. Additional work by Qui et al. developed three machine learning algorithms to predict multiple organ failure in MSAP and SAP, finding that a neural network-based model outperformed logistic regression and support vector machine methods on this task [48].
Acute pancreatitis (AP) is one of the most common causes of gastrointestinal-related hospitalizations in the United States. Severe AP (SAP) is associated with a mortality rate of nearly 30% and is distinguished from milder forms of AP. Risk stratification to identify SAP cases needing inpatient treatment is an important aspect of AP diagnosis.
We developed machine learning algorithms to predict which patients presenting with AP would require treatment for SAP. Three models were developed using logistic regression, neural networks, and XGBoost. Models were assessed in terms of area under the receiver operating characteristic (AUROC) and compared to the Harmless Acute Pancreatitis Score (HAPS) and Bedside Index for Severity in Acute Pancreatitis (BISAP) scores for AP risk stratification.
61,894 patients were used to train and test the machine learning models. With an AUROC value of 0.921, the model developed using XGBoost outperformed the logistic regression and neural network-based models. The XGBoost model also achieved a higher AUROC than both HAPS and BISAP for identifying patients who would be diagnosed with SAP.
Machine learning may be able to improve the accuracy of AP risk stratification methods and allow for more timely treatment and initiation of interventions.
Evidence-Based Management of Gallstone Pancreatitis
2020, Advances in Surgery
Application of Artificial Intelligence to Gastroenterology and Hepatology
2020, Gastroenterology
Since 2010, substantial progress has been made in artificial intelligence (AI) and its application to medicine. AI is explored in gastroenterology for endoscopic analysis of lesions, in detection of cancer, and to facilitate the analysis of inflammatory lesions or gastrointestinal bleeding during wireless capsule endoscopy. AI is also tested to assess liver fibrosis and to differentiate patients with pancreatic cancer from those with pancreatitis. AI might also be used to establish prognoses of patients or predict their response to treatments, based on multiple factors. We review the ways in which AI may help physicians make a diagnosis or establish a prognosis and discuss its limitations, knowing that further randomized controlled studies will be required before the approval of AI techniques by the health authorities.

View all citing articles on Scopus

View full text

Machine Learning Can Improve Prediction of Severity in Acute Pancreatitis Using Admission Values of APACHE II Score and C-Reactive Protein

Abstract

Baillieres Best Pract Res Clin Gastroenterol

Am J Surg

Lancet

Lancet

Lancet

Surgery

Pancreatology

Pancreatology

Am J Gastro-enterol

Acad Radiol

Radiol Clin N Am

Lancet

British Society of Gastroenterology

Gut

Early ERCP is an essential part of the management of all cases of acute pancreatitis

Ann R Coll Surg Engl

Antibiotic prophylaxis in severe acute pancreatitis

Br J Surg

The role of antibiotic prophylaxis in the treatment of acute pancreatitis

Gastroenterol Clin North Am

Etiology and pathogenesis of acute pancreatitis: current concepts

J Clin Gastroenterol

Role of substance P and the neurokinin 1 receptor in acute pancreatitis and pancreatitis-associated lung injury

Proc Natl Acad Sci USA

A comparative study of methods for the prediction of severity of attacks of acute pancreatitis

Br J Surg

Prediction of outcome in acute pancreatitis: a comparative study of APACHE II, clinical assessment and multiple factor scoring systems

Br J Surg

Objective early identification of severe acute pancreatitis

Am J Gastroenterol

A single-centre double-blind trial of Trasylol therapy in primary acute pancreatitis

Br J Surg

Prognostic factors in acute pancreatitis

Gut

Ranson, Glasgow, APACHE II systems: is the score a bore?

Diagnosis, objective assessment of severity, and management of acute pancreatitis. Santorini consensus conference

Int J Pancreatol

Early prediction of severity in acute pancreatitis. Is this possible?

JOP

Granulocyte elastase in assessment of severity of acute pancreatitis. Comparison with acute-phase proteins C-reactive protein, a1-antitryp-sin, and protease inhibitor a2-macroglobulin

Dig Dis Sci

Hyperlipidemia in acute pancreatitis. Relationship with etiology, onset, and severity of the disease

Int J Pancreatol

Granulocyte elastase in assessment of severity of acute pancreatitis. Comparison with acute-phase proteins C-reactive protein, a₁-antitryp-sin, and protease inhibitor a₂-macroglobulin