TY - JOUR
T1 - A multi-stage machine learning model for diagnosis of esophageal manometry
AU - Kou, Wenjun
AU - Carlson, Dustin A.
AU - Baumann, Alexandra J.
AU - Donnan, Erica N.
AU - Schauer, Jacob M.
AU - Etemadi, Mozziyar
AU - Pandolfino, John E.
N1 - Funding Information:
This work was supported by P01 DK117824 (JEP) from the Public Health service. In addition, this work was made possible by a grant from the Northwestern Digestive Health Foundation and gifts from Joe and Nives Rizza and The Todd and Renee Schilling Charitable Fund.
Publisher Copyright:
© 2021 Elsevier B.V.
PY - 2022/2
Y1 - 2022/2
N2 - High-resolution manometry (HRM) is the primary procedure used to diagnose esophageal motility disorders. Its manual interpretation and classification, including evaluation of swallow-level outcomes and then derivation of a study-level diagnosis based on Chicago Classification (CC), may be limited by inter-rater variability and inaccuracy of an individual interpreter. We hypothesized that an automatic diagnosis platform using machine learning and artificial intelligence approaches could be developed to accurately identify esophageal motility diagnoses. Further, a multi-stage modeling framework, akin to the step-wise approach of the CC, was utilized to leverage advantages of a combination of machine learning approaches including deep-learning models and feature-based models. Models were trained and tested using a dataset comprised of 1741 patients' HRM studies with CC diagnoses assigned by expert physician raters. In the swallow-level stage, three models based on convolutional neural networks (CNNs) were developed to predict swallow type and swallow pressurization (test accuracies of 0.88 and 0.93, respectively), and integrated relaxation pressure (IRP)(regression model with test error of 4.49 mmHg). At the study-level stage, model selection from families of the expert-knowledge-based rule models, xgboost models and artificial neural network(ANN) models were conducted. A simple model-agnostic strategy of model balancing motivated by Bayesian principles was utilized, which gave rise to model averaging weighted by precision scores. The averaged (blended) models and individual models were compared and evaluated, of which the best performance on test dataset is 0.81 in top-1 prediction, 0.92 in top-2 predictions. This is the first artificial-intelligence style model to automatically predict esophageal motility (CC) diagnoses from HRM studies using raw multi-swallow data and it achieved high accuracy. Thus, this proposed modeling framework could be broadly applied to assist with HRM interpretation in a clinical setting.
AB - High-resolution manometry (HRM) is the primary procedure used to diagnose esophageal motility disorders. Its manual interpretation and classification, including evaluation of swallow-level outcomes and then derivation of a study-level diagnosis based on Chicago Classification (CC), may be limited by inter-rater variability and inaccuracy of an individual interpreter. We hypothesized that an automatic diagnosis platform using machine learning and artificial intelligence approaches could be developed to accurately identify esophageal motility diagnoses. Further, a multi-stage modeling framework, akin to the step-wise approach of the CC, was utilized to leverage advantages of a combination of machine learning approaches including deep-learning models and feature-based models. Models were trained and tested using a dataset comprised of 1741 patients' HRM studies with CC diagnoses assigned by expert physician raters. In the swallow-level stage, three models based on convolutional neural networks (CNNs) were developed to predict swallow type and swallow pressurization (test accuracies of 0.88 and 0.93, respectively), and integrated relaxation pressure (IRP)(regression model with test error of 4.49 mmHg). At the study-level stage, model selection from families of the expert-knowledge-based rule models, xgboost models and artificial neural network(ANN) models were conducted. A simple model-agnostic strategy of model balancing motivated by Bayesian principles was utilized, which gave rise to model averaging weighted by precision scores. The averaged (blended) models and individual models were compared and evaluated, of which the best performance on test dataset is 0.81 in top-1 prediction, 0.92 in top-2 predictions. This is the first artificial-intelligence style model to automatically predict esophageal motility (CC) diagnoses from HRM studies using raw multi-swallow data and it achieved high accuracy. Thus, this proposed modeling framework could be broadly applied to assist with HRM interpretation in a clinical setting.
KW - Artificial intelligence
KW - High-resolution manometry
KW - Model averaging
UR - http://www.scopus.com/inward/record.url?scp=85122185782&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85122185782&partnerID=8YFLogxK
U2 - 10.1016/j.artmed.2021.102233
DO - 10.1016/j.artmed.2021.102233
M3 - Article
C2 - 35115131
AN - SCOPUS:85122185782
SN - 0933-3657
VL - 124
JO - Artificial Intelligence in Medicine
JF - Artificial Intelligence in Medicine
M1 - 102233
ER -