1
|
Kyrimi E, Stoner RS, Perkins ZB, Pisirir E, Wohlgemut JM, Marsh W, Tai NRM. Updating and recalibrating causal probabilistic models on a new target population. J Biomed Inform 2024; 149:104572. [PMID: 38081566 DOI: 10.1016/j.jbi.2023.104572] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2023] [Revised: 10/13/2023] [Accepted: 12/08/2023] [Indexed: 12/17/2023]
Abstract
OBJECTIVE Very often the performance of a Bayesian Network (BN) is affected when applied to a new target population. This is mainly because of differences in population characteristics. External validation of the model performance on different populations is a standard approach to test model's generalisability. However, a good predictive performance is not enough to show that the model represents the unique population characteristics and can be adopted in the new environment. METHODS In this paper, we present a methodology for updating and recalibrating developed BN models - both their structure and parameters - to better account for the characteristics of the target population. Attention has been given on incorporating expert knowledge and recalibrating latent variables, which are usually omitted from data-driven models. RESULTS The method is successfully applied to a clinical case study about the prediction of trauma-induced coagulopathy, where a BN has already been developed for civilian trauma patients and now it is recalibrated on combat casualties. CONCLUSION The methodology proposed in this study is important for developing credible models that can demonstrate a good predictive performance when applied to a target population. Another advantage of the proposed methodology is that it is not limited to data-driven techniques and shows how expert knowledge can also be used when updating and recalibrating the model.
Collapse
Affiliation(s)
- Evangelia Kyrimi
- Department of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom. https://twitter.com/@LinaKyrimi
| | - Rebecca S Stoner
- Centre for Trauma Sciences, Blizard Institute, Queen Mary University of London, London, United Kingdom; Royal London Hospital, Barts Health NHS Trust, London, United Kingdom
| | - Zane B Perkins
- Centre for Trauma Sciences, Blizard Institute, Queen Mary University of London, London, United Kingdom; Royal London Hospital, Barts Health NHS Trust, London, United Kingdom
| | - Erhan Pisirir
- Department of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom
| | - Jared M Wohlgemut
- Centre for Trauma Sciences, Blizard Institute, Queen Mary University of London, London, United Kingdom; Royal London Hospital, Barts Health NHS Trust, London, United Kingdom
| | - William Marsh
- Department of Electronic Engineering and Computer Science, Queen Mary University of London, United Kingdom
| | - Nigel R M Tai
- Centre for Trauma Sciences, Blizard Institute, Queen Mary University of London, London, United Kingdom; Royal London Hospital, Barts Health NHS Trust, London, United Kingdom; Royal Centre for Defence Medicine, Birmingham, United Kingdom
| |
Collapse
|
2
|
Juhan N, Zubairi YZ, Mahmood Zuhdi AS, Mohd Khalid Z. Predictors on outcomes of cardiovascular disease of male patients in Malaysia using Bayesian network analysis. BMJ Open 2023; 13:e066748. [PMID: 37923353 PMCID: PMC10626862 DOI: 10.1136/bmjopen-2022-066748] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/19/2022] [Accepted: 08/30/2023] [Indexed: 11/07/2023] Open
Abstract
OBJECTIVES Despite extensive advances in medical and surgical treatment, cardiovascular disease (CVD) remains the leading cause of mortality worldwide. Identifying the significant predictors will help clinicians with the prognosis of the disease and patient management. This study aims to identify and interpret the dependence structure between the predictors and health outcomes of ST-elevation myocardial infarction (STEMI) male patients in Malaysian setting. DESIGN Retrospective study. SETTING Malaysian National Cardiovascular Disease Database-Acute Coronary Syndrome (NCVD-ACS) registry years 2006-2013, which consists of 18 hospitals across the country. PARTICIPANTS 7180 male patients diagnosed with STEMI from the NCVD-ACS registry. PRIMARY AND SECONDARY OUTCOME MEASURES A graphical model based on the Bayesian network (BN) approach has been considered. A bootstrap resampling approach was integrated into the structural learning algorithm to estimate probabilistic relations between the studied features that have the strongest influence and support. RESULTS The relationships between 16 features in the domain of CVD were visualised. From the bootstrap resampling approach, out of 250, only 25 arcs are significant (strength value ≥0.85 and the direction value ≥0.50). Age group, Killip class and renal disease were classified as the key predictors in the BN model for male patients as they were the most influential variables directly connected to the outcome, which is the patient status. Widespread probabilistic associations between the key predictors and the remaining variables were observed in the network structure. High likelihood values are observed for patient status variable stated alive (93.8%), Killip class I on presentation (66.8%), patient younger than 65 (81.1%), smoker patient (77.2%) and ethnic Malay (59.2%). The BN model has been shown to have good predictive performance. CONCLUSIONS The data visualisation analysis can be a powerful tool to understand the relationships between the CVD prognostic variables and can be useful to clinicians.
Collapse
Affiliation(s)
- Nurliyana Juhan
- Preparatory Centre for Science and Technology, Universiti Malaysia Sabah, Kota Kinabalu, Malaysia
| | - Yong Zulina Zubairi
- Institute for Advanced Studies, University of Malaya, Kuala Lumpur, Malaysia
| | | | - Zarina Mohd Khalid
- Department of Mathematical Sciences, Universiti Teknologi Malaysia, Skudai, Malaysia
| |
Collapse
|
3
|
Shinada K, Matsuoka A, Koami H, Sakamoto Y. Bayesian network predicted variables for good neurological outcomes in patients with out-of-hospital cardiac arrest. PLoS One 2023; 18:e0291258. [PMID: 37768915 PMCID: PMC10538776 DOI: 10.1371/journal.pone.0291258] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/06/2023] [Accepted: 08/24/2023] [Indexed: 09/30/2023] Open
Abstract
Out-of-hospital cardiac arrest (OHCA) is linked to a poor prognosis and remains a public health concern. Several studies have predicted good neurological outcomes of OHCA. In this study, we used the Bayesian network to identify variables closely associated with good neurological survival outcomes in patients with OHCA. This was a retrospective observational study using the Japan Association for Acute Medicine OHCA registry. Fifteen explanatory variables were used, and the outcome was one-month survival with Glasgow-Pittsburgh cerebral performance category (CPC) 1-2. The 2014-2018 dataset was used as training data. The variables selected were identified and a sensitivity analysis was performed. The 2019 dataset was used for the validation analysis. Four variables were identified, including the motor response component of the Glasgow Coma Scale (GCS M), initial rhythm, age, and absence of epinephrine. Estimated probabilities were increased in the following order: GCS M score: 2-6; epinephrine: non-administered; initial rhythm: spontaneous rhythm and shockable; and age: <58 and 59-70 years. The validation showed a sensitivity of 75.4% and a specificity of 95.4%. We identified GCS M score of 2-6, initial rhythm (spontaneous rhythm and shockable), younger age, and absence of epinephrine as variables associated with one-month survival with CPC 1-2. These variables may help clinicians in the decision-making process while treating patients with OHCA.
Collapse
Affiliation(s)
- Kota Shinada
- Department of Emergency and Critical Care Medicine, Faculty of Medicine, Saga University, Saga City, Saga Prefecture, Japan
| | - Ayaka Matsuoka
- Department of Emergency and Critical Care Medicine, Faculty of Medicine, Saga University, Saga City, Saga Prefecture, Japan
| | - Hiroyuki Koami
- Department of Emergency and Critical Care Medicine, Faculty of Medicine, Saga University, Saga City, Saga Prefecture, Japan
| | - Yuichiro Sakamoto
- Department of Emergency and Critical Care Medicine, Faculty of Medicine, Saga University, Saga City, Saga Prefecture, Japan
| |
Collapse
|
4
|
Vink M, Sjerps M. A collection of idioms for modeling activity level evaluations in forensic science. Forensic Sci Int Synerg 2023; 6:100331. [PMID: 37332325 PMCID: PMC10276233 DOI: 10.1016/j.fsisyn.2023.100331] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/07/2023] [Revised: 05/01/2023] [Accepted: 05/02/2023] [Indexed: 06/20/2023]
Abstract
This paper presents a collection of idioms that is useful for modeling activity level evaluations in forensic science using Bayesian networks. The idioms are categorized into five groups: cause-consequence idioms, narrative idioms, synthesis idioms, hypothesis-conditioning idioms, and evidence-conditioning idioms. Each category represents a specific modeling objective. Furthermore, we support the use of an idiom-based approach and emphasize the relevance of our collection by combining several of the presented idioms to create a more comprehensive template model. This model can be used in cases involving transfer evidence and disputes over the actor and/or activity. Additionally, we cite literature that employs idioms in template models or case-specific models, providing the reader with examples of their use in forensic casework.
Collapse
Affiliation(s)
- M. Vink
- University of Amsterdam, KdVI, PO Box 94248, 1090 GE, Amsterdam, Netherlands
- Netherlands Forensic Institute, Laan van Ypenburg 6, 2497GB, The Hague, Netherlands
| | - M.J. Sjerps
- University of Amsterdam, KdVI, PO Box 94248, 1090 GE, Amsterdam, Netherlands
- Netherlands Forensic Institute, Laan van Ypenburg 6, 2497GB, The Hague, Netherlands
| |
Collapse
|
6
|
Ramsay JA, Mascaro S, Campbell AJ, Foley DA, Mace AO, Ingram P, Borland ML, Blyth CC, Larkins NG, Robertson T, Williams PCM, Snelling TL, Wu Y. Urinary tract infections in children: building a causal model-based decision support tool for diagnosis with domain knowledge and prospective data. BMC Med Res Methodol 2022; 22:218. [PMID: 35941543 PMCID: PMC9358867 DOI: 10.1186/s12874-022-01695-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/19/2022] [Accepted: 07/21/2022] [Indexed: 11/10/2022] Open
Abstract
BACKGROUND Diagnosing urinary tract infections (UTIs) in children in the emergency department (ED) is challenging due to the variable clinical presentations and difficulties in obtaining a urine sample free from contamination. Clinicians need to weigh a range of observations to make timely diagnostic and management decisions, a difficult task to achieve without support due to the complex interactions among relevant factors. Directed acyclic graphs (DAG) and causal Bayesian networks (BN) offer a way to explicitly outline the underlying disease, contamination and diagnostic processes, and to further make quantitative inference on the event of interest thus serving as a tool for decision support. METHODS We prospectively collected data on children present to ED with suspected UTIs. Through knowledge elicitation workshops and one-on-one meetings, a DAG was co-developed with clinical domain experts (the Expert DAG) to describe the causal relationships among variables relevant to paediatric UTIs. The Expert DAG was combined with prospective data and further domain knowledge to inform the development of an application-oriented BN (the Applied BN), designed to support the diagnosis of UTI. We assessed the performance of the Applied BN using quantitative and qualitative methods. RESULTS We summarised patient background, clinical and laboratory characteristics of 431 episodes of suspected UTIs enrolled from May 2019 to November 2020. The Expert DAG was presented with a narrative description, elucidating how infection, specimen contamination and management pathways causally interact to form the complex picture of paediatric UTIs. Parameterised using prospective data and expert-elicited parameters, the Applied BN achieved an excellent and stable performance in predicting Escherichia coli culture results, with a mean area under the receiver operating characteristic curve of 0.86 and a mean log loss of 0.48 based on 10-fold cross-validation. The BN predictions were reviewed via a validation workshop, and we illustrate how they can be presented for decision support using three hypothetical clinical scenarios. CONCLUSION Causal BNs created from both expert knowledge and data can integrate case-specific information to provide individual decision support during the diagnosis of paediatric UTIs in ED. The model aids the interpretation of culture results and the diagnosis of UTIs, promising the prospect of improved patient care and judicious use of antibiotics.
Collapse
Affiliation(s)
- Jessica A Ramsay
- Wesfarmers Centre of Vaccines and Infectious Diseases, Telethon Kids Institute, University of Western Australia, Nedlands, WA, 6009, Australia
| | - Steven Mascaro
- Bayesian Intelligence Pty Ltd, Upwey, VIC, 3158, Australia.,Faculty of Information Technology, Monash University, Clayton, VIC, 3168, Australia
| | - Anita J Campbell
- Wesfarmers Centre of Vaccines and Infectious Diseases, Telethon Kids Institute, University of Western Australia, Nedlands, WA, 6009, Australia.,Department of Infectious Diseases, Perth Children's Hospital, Nedlands, WA, 6009, Australia
| | - David A Foley
- Department of Microbiology, PathWest Laboratory Medicine, Nedlands, WA, 6009, Australia
| | - Ariel O Mace
- Wesfarmers Centre of Vaccines and Infectious Diseases, Telethon Kids Institute, University of Western Australia, Nedlands, WA, 6009, Australia.,Department of General Paediatrics, Perth Children's Hospital, Nedlands, WA, 6009, Australia
| | - Paul Ingram
- Department of Microbiology, PathWest Laboratory Medicine, Nedlands, WA, 6009, Australia.,School of Pathology and Laboratory Medicine, University of Western Australia, Nedlands, WA, 6009, Australia
| | - Meredith L Borland
- Emergency Department, Perth Children's Hospital, Nedlands, WA, 6009, Australia.,Divisions of Emergency Medicine and Paediatrics, School of Medicine, University of Western Australia, Nedlands, WA, 6009, Australia
| | - Christopher C Blyth
- Wesfarmers Centre of Vaccines and Infectious Diseases, Telethon Kids Institute, University of Western Australia, Nedlands, WA, 6009, Australia.,Department of Infectious Diseases, Perth Children's Hospital, Nedlands, WA, 6009, Australia.,Department of Microbiology, PathWest Laboratory Medicine, Nedlands, WA, 6009, Australia.,Faculty of Health and Medical Sciences, University of Western Australia, Crawley, Australia
| | - Nicholas G Larkins
- Department of Nephrology, Perth Children's Hospital, Nedlands, WA, 6009, Australia
| | - Tim Robertson
- Child and Adolescent Health Service, Perth Children's Hospital, Nedlands, WA, 6009, Australia
| | - Phoebe C M Williams
- Sydney School of Public Health, Faculty of Medicine and Health, University of Sydney, 2006, Camperdown, NSW , Australia.,Sydney Children's Hospital Network, Randwick, NSW, 2031, Australia.,School of Women's and Children's Health, The University of New South Wales, Sydney, NSW, 2052, Australia
| | - Thomas L Snelling
- Wesfarmers Centre of Vaccines and Infectious Diseases, Telethon Kids Institute, University of Western Australia, Nedlands, WA, 6009, Australia.,Sydney School of Public Health, Faculty of Medicine and Health, University of Sydney, 2006, Camperdown, NSW , Australia.,Sydney Children's Hospital Network, Randwick, NSW, 2031, Australia.,School of Public Health, Curtin University, Bentley, WA, 6102, Australia.,Menzies School of Health Research, Charles Darwin University, Darwin, NT, 0815, Australia
| | - Yue Wu
- Wesfarmers Centre of Vaccines and Infectious Diseases, Telethon Kids Institute, University of Western Australia, Nedlands, WA, 6009, Australia. .,Sydney School of Public Health, Faculty of Medicine and Health, University of Sydney, 2006, Camperdown, NSW , Australia.
| |
Collapse
|
7
|
Ciunkiewicz P, Roumeliotis M, Stenhouse K, McGeachy P, Quirk S, Grendarova P, Yanushkevich S. Assessment of Tissue Toxicity Risk in Breast Radiotherapy using Bayesian Networks. Med Phys 2022; 49:3585-3596. [PMID: 35442533 DOI: 10.1002/mp.15651] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2021] [Revised: 02/19/2022] [Accepted: 03/23/2022] [Indexed: 11/07/2022] Open
Abstract
PURPOSE The purpose of this analysis is to predict worsening post-treatment normal tissue toxicity in patients undergoing accelerated partial breast irradiation (APBI) therapy and to quantitatively identify which diagnostic, anatomical, and dosimetric features are contributing to these outcomes. METHODS A retrospective study of APBI treatments was performed using 32 features pertaining to various stages of the patient's treatment journey. These features were used to inform and construct a Bayesian network (BN) based on both statistical analysis of feature distributions and relative clinical importance. The target feature for prediction was defined as a measurable worsening of telangiectasia, subcutaneous tissue induration, or fibrosis when compared against the observed baseline. Parameter learning for the network was performed using data from the 299 patients included in the ACCEL trial and predictive performance was measured. Feature importance for the BN was quantified using a novel information-theoretic approach. RESULTS Cross validated performance of the BN for predicting toxicity was consistently higher when compared against conventional machine learning (ML) techniques. The measured BN receiver operating characteristic area under the curve was 0.960±0.013 against the best ML result of 0.942±0.021 using 5-fold cross validation with separate test data across 100 trials. The volume of the clinical target volume, gross target volume, and baseline toxicity measurements were found to have the highest feature importance and mutual dependence with normal tissue toxicity in the network, representing the strongest contribution to patient outcomes. CONCLUSIONS The BN outperformed conventional ML techniques in predicting tissue toxicity outcomes and provided deeper insight into which features are contributing to these outcomes. This article is protected by copyright. All rights reserved.
Collapse
Affiliation(s)
- Philip Ciunkiewicz
- University of Calgary, Biomedical Engineering, 2500 University Dr. NW, Calgary, AB, T2N1N4, Canada
| | | | | | | | - Sarah Quirk
- Tom Baker Cancer Centre, Calgary, AB, Canada
| | - Petra Grendarova
- University of Calgary, Alberta Health Services, Calgary, AB, Canada
| | - Svetlana Yanushkevich
- University of Calgary, Biomedical Engineering, 2500 University Dr. NW, Calgary, AB, T2N1N4, Canada
| |
Collapse
|
8
|
Hill A, Joyner CH, Keith-Jopp C, Yet B, Tuncer Sakar C, Marsh W, Morrissey D. A Bayesian Network Decision Support Tool for Low Back Pain Using a RAND Appropriateness Procedure: Proposal and Internal Pilot Study. JMIR Res Protoc 2021; 10:e21804. [PMID: 33448937 PMCID: PMC7846442 DOI: 10.2196/21804] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/07/2020] [Revised: 09/01/2020] [Accepted: 11/10/2020] [Indexed: 11/13/2022] Open
Abstract
BACKGROUND Low back pain (LBP) is an increasingly burdensome condition for patients and health professionals alike, with consistent demonstration of increasing persistent pain and disability. Previous decision support tools for LBP management have focused on a subset of factors owing to time constraints and ease of use for the clinician. With the explosion of interest in machine learning tools and the commitment from Western governments to introduce this technology, there are opportunities to develop intelligent decision support tools. We will do this for LBP using a Bayesian network, which will entail constructing a clinical reasoning model elicited from experts. OBJECTIVE This paper proposes a method for conducting a modified RAND appropriateness procedure to elicit the knowledge required to construct a Bayesian network from a group of domain experts in LBP, and reports the lessons learned from the internal pilot of the procedure. METHODS We propose to recruit expert clinicians with a special interest in LBP from across a range of medical specialties, such as orthopedics, rheumatology, and sports medicine. The procedure will consist of four stages. Stage 1 is an online elicitation of variables to be considered by the model, followed by a face-to-face workshop. Stage 2 is an online elicitation of the structure of the model, followed by a face-to-face workshop. Stage 3 consists of an online phase to elicit probabilities to populate the Bayesian network. Stage 4 is a rudimentary validation of the Bayesian network. RESULTS Ethical approval has been obtained from the Research Ethics Committee at Queen Mary University of London. An internal pilot of the procedure has been run with clinical colleagues from the research team. This showed that an alternating process of three remote activities and two in-person meetings was required to complete the elicitation without overburdening participants. Lessons learned have included the need for a bespoke online elicitation tool to run between face-to-face meetings and for careful operational definition of descriptive terms, even if widely clinically used. Further, tools are required to remotely deliver training about self-identification of various forms of cognitive bias and explain the underlying principles of a Bayesian network. The use of the internal pilot was recognized as being a methodological necessity. CONCLUSIONS We have proposed a method to construct Bayesian networks that are representative of expert clinical reasoning for a musculoskeletal condition in this case. We have tested the method with an internal pilot to refine the process prior to deployment, which indicates the process can be successful. The internal pilot has also revealed the software support requirements for the elicitation process to model clinical reasoning for a range of conditions. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID) DERR1-10.2196/21804.
Collapse
Affiliation(s)
- Adele Hill
- Sport and Exercise Medicine, Queen Mary University of London, London, United Kingdom
| | - Christopher H Joyner
- Electronics, Engineering and Computer Science, Queen Mary University of London, London, United Kingdom
| | - Chloe Keith-Jopp
- Sport and Exercise Medicine, Queen Mary University of London, London, United Kingdom.,Barts Health NHS Trust, London, United Kingdom
| | - Barbaros Yet
- Graduate School of Informatics, Middle East Technical University, Ankara, Turkey
| | - Ceren Tuncer Sakar
- Department of Industrial Engineering, Hacettepe University, Ankara, Turkey
| | - William Marsh
- Electronics, Engineering and Computer Science, Queen Mary University of London, London, United Kingdom
| | - Dylan Morrissey
- Sport and Exercise Medicine, Queen Mary University of London, London, United Kingdom.,Barts Health NHS Trust, London, United Kingdom
| |
Collapse
|