1
|
Kamis A, Gadia N, Luo Z, Ng SX, Thumbar M. Obtaining the Most Accurate, Explainable Model for Predicting Chronic Obstructive Pulmonary Disease: Triangulation of Multiple Linear Regression and Machine Learning Methods. JMIR AI 2024; 3:e58455. [PMID: 39207843 PMCID: PMC11393512 DOI: 10.2196/58455] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/15/2024] [Revised: 07/09/2024] [Accepted: 07/10/2024] [Indexed: 09/04/2024]
Abstract
BACKGROUND Lung disease is a severe problem in the United States. Despite the decreasing rates of cigarette smoking, chronic obstructive pulmonary disease (COPD) continues to be a health burden in the United States. In this paper, we focus on COPD in the United States from 2016 to 2019. OBJECTIVE We gathered a diverse set of non-personally identifiable information from public data sources to better understand and predict COPD rates at the core-based statistical area (CBSA) level in the United States. Our objective was to compare linear models with machine learning models to obtain the most accurate and interpretable model of COPD. METHODS We integrated non-personally identifiable information from multiple Centers for Disease Control and Prevention sources and used them to analyze COPD with different types of methods. We included cigarette smoking, a well-known contributing factor, and race/ethnicity because health disparities among different races and ethnicities in the United States are also well known. The models also included the air quality index, education, employment, and economic variables. We fitted models with both multiple linear regression and machine learning methods. RESULTS The most accurate multiple linear regression model has variance explained of 81.1%, mean absolute error of 0.591, and symmetric mean absolute percentage error of 9.666. The most accurate machine learning model has variance explained of 85.7%, mean absolute error of 0.456, and symmetric mean absolute percentage error of 6.956. Overall, cigarette smoking and household income are the strongest predictor variables. Moderately strong predictors include education level and unemployment level, as well as American Indian or Alaska Native, Black, and Hispanic population percentages, all measured at the CBSA level. CONCLUSIONS This research highlights the importance of using diverse data sources as well as multiple methods to understand and predict COPD. The most accurate model was a gradient boosted tree, which captured nonlinearities in a model whose accuracy is superior to the best multiple linear regression. Our interpretable models suggest ways that individual predictor variables can be used in tailored interventions aimed at decreasing COPD rates in specific demographic and ethnographic communities. Gaps in understanding the health impacts of poor air quality, particularly in relation to climate change, suggest a need for further research to design interventions and improve public health.
Collapse
Affiliation(s)
- Arnold Kamis
- Brandeis International Business School, Brandeis University, Waltham, MA, United States
| | - Nidhi Gadia
- Brandeis International Business School, Brandeis University, Waltham, MA, United States
| | - Zilin Luo
- Brandeis International Business School, Brandeis University, Waltham, MA, United States
| | - Shu Xin Ng
- Brandeis International Business School, Brandeis University, Waltham, MA, United States
| | - Mansi Thumbar
- Brandeis International Business School, Brandeis University, Waltham, MA, United States
| |
Collapse
|
2
|
de Gonzalo-Calvo D, Karaduzovic-Hadziabdic K, Dalgaard LT, Dieterich C, Perez-Pons M, Hatzigeorgiou A, Devaux Y, Kararigas G. Machine learning for catalysing the integration of noncoding RNA in research and clinical practice. EBioMedicine 2024; 106:105247. [PMID: 39029428 PMCID: PMC11314885 DOI: 10.1016/j.ebiom.2024.105247] [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: 03/08/2024] [Revised: 06/17/2024] [Accepted: 07/02/2024] [Indexed: 07/21/2024] Open
Abstract
The human transcriptome predominantly consists of noncoding RNAs (ncRNAs), transcripts that do not encode proteins. The noncoding transcriptome governs a multitude of pathophysiological processes, offering a rich source of next-generation biomarkers. Toward achieving a holistic view of disease, the integration of these transcripts with clinical records and additional data from omic technologies ("multiomic" strategies) has motivated the adoption of artificial intelligence (AI) approaches. Given their intricate biological complexity, machine learning (ML) techniques are becoming a key component of ncRNA-based research. This article presents an overview of the potential and challenges associated with employing AI/ML-driven approaches to identify clinically relevant ncRNA biomarkers and to decipher ncRNA-associated pathogenetic mechanisms. Methodological and conceptual constraints are discussed, along with an exploration of ethical considerations inherent to AI applications for healthcare and research. The ultimate goal is to provide a comprehensive examination of the multifaceted landscape of this innovative field and its clinical implications.
Collapse
Affiliation(s)
- David de Gonzalo-Calvo
- Translational Research in Respiratory Medicine, University Hospital Arnau de Vilanova and Santa Maria, IRBLleida, Lleida, Spain; CIBER of Respiratory Diseases (CIBERES), Institute of Health Carlos III, Madrid, Spain.
| | | | | | - Christoph Dieterich
- Klaus Tschira Institute for Integrative Computational Cardiology and Department of Internal Medicine III, University Hospital Heidelberg, Germany; German Center for Cardiovascular Research (DZHK) - Partner Site Heidelberg/Mannheim, Germany
| | - Manel Perez-Pons
- Translational Research in Respiratory Medicine, University Hospital Arnau de Vilanova and Santa Maria, IRBLleida, Lleida, Spain; CIBER of Respiratory Diseases (CIBERES), Institute of Health Carlos III, Madrid, Spain
| | - Artemis Hatzigeorgiou
- DIANA-Lab, Department of Computer Science and Biomedical Informatics, University of Thessaly, Lamia, Greece; Hellenic Pasteur Institute, Athens, Greece
| | - Yvan Devaux
- Cardiovascular Research Unit, Department of Precision Health, Luxembourg Institute of Health, Strassen, Luxembourg
| | - Georgios Kararigas
- Department of Physiology, Faculty of Medicine, University of Iceland, Reykjavik, Iceland.
| |
Collapse
|
3
|
Bürger VK, Amann J, Bui CKT, Fehr J, Madai VI. The unmet promise of trustworthy AI in healthcare: why we fail at clinical translation. Front Digit Health 2024; 6:1279629. [PMID: 38698888 PMCID: PMC11063331 DOI: 10.3389/fdgth.2024.1279629] [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: 08/18/2023] [Accepted: 04/02/2024] [Indexed: 05/05/2024] Open
Abstract
Artificial intelligence (AI) has the potential to revolutionize healthcare, for example via decision support systems, computer vision approaches, or AI-based prevention tools. Initial results from AI applications in healthcare show promise but are rarely translated into clinical practice successfully and ethically. This occurs despite an abundance of "Trustworthy AI" guidelines. How can we explain the translational gaps of AI in healthcare? This paper offers a fresh perspective on this problem, showing that failing translation of healthcare AI markedly arises from a lack of an operational definition of "trust" and "trustworthiness". This leads to (a) unintentional misuse concerning what trust (worthiness) is and (b) the risk of intentional abuse by industry stakeholders engaging in ethics washing. By pointing out these issues, we aim to highlight the obstacles that hinder translation of Trustworthy medical AI to practice and prevent it from fulfilling its unmet promises.
Collapse
Affiliation(s)
- Valerie K. Bürger
- QUEST Center for Responsible Research, Berlin Institute of Health (BIH), Charité—Universitätsmedizin Berlin, Berlin, Germany
| | - Julia Amann
- Strategy and Innovation, Careum Foundation, Zurich, Switzerland
| | - Cathrine K. T. Bui
- QUEST Center for Responsible Research, Berlin Institute of Health (BIH), Charité—Universitätsmedizin Berlin, Berlin, Germany
| | - Jana Fehr
- QUEST Center for Responsible Research, Berlin Institute of Health (BIH), Charité—Universitätsmedizin Berlin, Berlin, Germany
- Digital Health & Machine Learning, Hasso Plattner Institute for Digital Engineering, Digital Engineering Faculty, University of Potsdam, Potsdam, Germany
| | - Vince I. Madai
- QUEST Center for Responsible Research, Berlin Institute of Health (BIH), Charité—Universitätsmedizin Berlin, Berlin, Germany
- Faculty of Computing, Engineering, and the Built Environment, School of Computing and Digital Technology, Birmingham City University, Birmingham, United Kingdom
| |
Collapse
|
4
|
Okada Y, Ning Y, Ong MEH. Explainable artificial intelligence in emergency medicine: an overview. Clin Exp Emerg Med 2023; 10:354-362. [PMID: 38012816 PMCID: PMC10790070 DOI: 10.15441/ceem.23.145] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/09/2023] [Revised: 11/06/2023] [Accepted: 11/16/2023] [Indexed: 11/29/2023] Open
Abstract
Artificial intelligence (AI) and machine learning (ML) have potential to revolutionize emergency medical care by enhancing triage systems, improving diagnostic accuracy, refining prognostication, and optimizing various aspects of clinical care. However, as clinicians often lack AI expertise, they might perceive AI as a "black box," leading to trust issues. To address this, "explainable AI," which teaches AI functionalities to end-users, is important. This review presents the definitions, importance, and role of explainable AI, as well as potential challenges in emergency medicine. First, we introduce the terms explainability, interpretability, and transparency of AI models. These terms sound similar but have different roles in discussion of AI. Second, we indicate that explainable AI is required in clinical settings for reasons of justification, control, improvement, and discovery and provide examples. Third, we describe three major categories of explainability: pre-modeling explainability, interpretable models, and post-modeling explainability and present examples (especially for post-modeling explainability), such as visualization, simplification, text justification, and feature relevance. Last, we show the challenges of implementing AI and ML models in clinical settings and highlight the importance of collaboration between clinicians, developers, and researchers. This paper summarizes the concept of "explainable AI" for emergency medicine clinicians. This review may help clinicians understand explainable AI in emergency contexts.
Collapse
Affiliation(s)
- Yohei Okada
- Health Services and Systems Research, Duke-NUS Medical School, Singapore
- Preventive Services, Graduate School of Medicine, Kyoto University, Kyoto, Japan
| | - Yilin Ning
- Centre for Quantitative Medicine, Duke-NUS Medical School, Singapore
| | - Marcus Eng Hock Ong
- Health Services and Systems Research, Duke-NUS Medical School, Singapore
- Department of Emergency Medicine, Singapore General Hospital, Singapore
| |
Collapse
|
5
|
McFadden BR, Reynolds M, Inglis TJJ. Developing machine learning systems worthy of trust for infection science: a requirement for future implementation into clinical practice. Front Digit Health 2023; 5:1260602. [PMID: 37829595 PMCID: PMC10565494 DOI: 10.3389/fdgth.2023.1260602] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2023] [Accepted: 09/15/2023] [Indexed: 10/14/2023] Open
Abstract
Infection science is a discipline of healthcare which includes clinical microbiology, public health microbiology, mechanisms of microbial disease, and antimicrobial countermeasures. The importance of infection science has become more apparent in recent years during the SARS-CoV-2 (COVID-19) pandemic and subsequent highlighting of critical operational domains within infection science including the hospital, clinical laboratory, and public health environments to prevent, manage, and treat infectious diseases. However, as the global community transitions beyond the pandemic, the importance of infection science remains, with emerging infectious diseases, bloodstream infections, sepsis, and antimicrobial resistance becoming increasingly significant contributions to the burden of global disease. Machine learning (ML) is frequently applied in healthcare and medical domains, with growing interest in the application of ML techniques to problems in infection science. This has the potential to address several key aspects including improving patient outcomes, optimising workflows in the clinical laboratory, and supporting the management of public health. However, despite promising results, the implementation of ML into clinical practice and workflows is limited. Enabling the migration of ML models from the research to real world environment requires the development of trustworthy ML systems that support the requirements of users, stakeholders, and regulatory agencies. This paper will provide readers with a brief introduction to infection science, outline the principles of trustworthy ML systems, provide examples of the application of these principles in infection science, and propose future directions for moving towards the development of trustworthy ML systems in infection science.
Collapse
Affiliation(s)
- Benjamin R. McFadden
- School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia
| | - Mark Reynolds
- School of Physics, Mathematics and Computing, University of Western Australia, Perth, WA, Australia
| | - Timothy J. J. Inglis
- Western Australian Country Health Service, Perth, WA, Australia
- School of Medicine, University of Western Australia, Perth, WA, Australia
- Department of Microbiology, Pathwest Laboratory Medicine, Perth, WA, Australia
| |
Collapse
|
6
|
Hille EM, Hummel P, Braun M. Meaningful Human Control over AI for Health? A Review. JOURNAL OF MEDICAL ETHICS 2023:jme-2023-109095. [PMID: 37730418 DOI: 10.1136/jme-2023-109095] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 03/15/2023] [Accepted: 08/27/2023] [Indexed: 09/22/2023]
Abstract
Artificial intelligence is currently changing many areas of society. Especially in health, where critical decisions are made, questions of control must be renegotiated: who is in control when an automated system makes clinically relevant decisions? Increasingly, the concept of meaningful human control (MHC) is being invoked for this purpose. However, it is unclear exactly how this concept is to be understood in health. Through a systematic review, we present the current state of the concept of MHC in health. The results show that there is not yet a robust MHC concept for health. We propose a broader understanding of MHC along three strands of action: enabling, exercising and evaluating control. Taking into account these strands of action and the established rules and processes in the different health sectors, the MHC concept needs to be further developed to avoid falling into two gaps, which we have described as theoretical and labelling gaps.
Collapse
Affiliation(s)
- Eva Maria Hille
- Chair of Social Ethics & Ethics of Technology, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| | - Patrik Hummel
- Department of Industrial Engineering and Innovation Sciences, Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Matthias Braun
- Chair of Social Ethics & Ethics of Technology, Rheinische Friedrich-Wilhelms-Universität Bonn, Bonn, Germany
| |
Collapse
|
7
|
Lenatti M, Paglialonga A, Orani V, Ferretti M, Mongelli M. Characterization of Synthetic Health Data Using Rule-Based Artificial Intelligence Models. IEEE J Biomed Health Inform 2023; 27:3760-3769. [PMID: 37018683 DOI: 10.1109/jbhi.2023.3236722] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/15/2023]
Abstract
The aim of this study is to apply and characterize eXplainable AI (XAI) to assess the quality of synthetic health data generated using a data augmentation algorithm. In this exploratory study, several synthetic datasets are generated using various configurations of a conditional Generative Adversarial Network (GAN) from a set of 156 observations related to adult hearing screening. A rule-based native XAI algorithm, the Logic Learning Machine, is used in combination with conventional utility metrics. The classification performance in different conditions is assessed: models trained and tested on synthetic data, models trained on synthetic data and tested on real data, and models trained on real data and tested on synthetic data. The rules extracted from real and synthetic data are then compared using a rule similarity metric. The results indicate that XAI may be used to assess the quality of synthetic data by (i) the analysis of classification performance and (ii) the analysis of the rules extracted on real and synthetic data (number, covering, structure, cut-off values, and similarity). These results suggest that XAI can be used in an original way to assess synthetic health data and extract knowledge about the mechanisms underlying the generated data.
Collapse
|
8
|
Zicari RV. Assessing Trustworthy AI in Times of COVID-19: Deep Learning for Predicting a Multiregional Score Conveying the Degree of Lung Compromise in COVID-19 Patients. IEEE TRANSACTIONS ON TECHNOLOGY AND SOCIETY 2022; 3:272-289. [PMID: 36573115 PMCID: PMC9762021 DOI: 10.1109/tts.2022.3195114] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/08/2021] [Revised: 07/13/2022] [Accepted: 07/18/2022] [Indexed: 12/30/2022]
Abstract
This article's main contributions are twofold: 1) to demonstrate how to apply the general European Union's High-Level Expert Group's (EU HLEG) guidelines for trustworthy AI in practice for the domain of healthcare and 2) to investigate the research question of what does "trustworthy AI" mean at the time of the COVID-19 pandemic. To this end, we present the results of a post-hoc self-assessment to evaluate the trustworthiness of an AI system for predicting a multiregional score conveying the degree of lung compromise in COVID-19 patients, developed and verified by an interdisciplinary team with members from academia, public hospitals, and industry in time of pandemic. The AI system aims to help radiologists to estimate and communicate the severity of damage in a patient's lung from Chest X-rays. It has been experimentally deployed in the radiology department of the ASST Spedali Civili clinic in Brescia, Italy, since December 2020 during pandemic time. The methodology we have applied for our post-hoc assessment, called Z-Inspection®, uses sociotechnical scenarios to identify ethical, technical, and domain-specific issues in the use of the AI system in the context of the pandemic.
Collapse
Affiliation(s)
- Roberto V. Zicari
- Department of Business Management and Analytics, Arcada University of Applied Sciences, Helsinki, Finland
| |
Collapse
|
9
|
Artificial intelligence and Multidisciplinary Team Meetings; A communication challenge for radiologists' sense of agency and position as spider in a web? Eur J Radiol 2022; 155:110231. [DOI: 10.1016/j.ejrad.2022.110231] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/29/2021] [Revised: 02/24/2022] [Accepted: 03/01/2022] [Indexed: 11/19/2022]
|
10
|
To explain or not to explain?-Artificial intelligence explainability in clinical decision support systems. PLOS DIGITAL HEALTH 2022; 1:e0000016. [PMID: 36812545 PMCID: PMC9931364 DOI: 10.1371/journal.pdig.0000016] [Citation(s) in RCA: 33] [Impact Index Per Article: 16.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Accepted: 01/03/2022] [Indexed: 12/15/2022]
Abstract
Explainability for artificial intelligence (AI) in medicine is a hotly debated topic. Our paper presents a review of the key arguments in favor and against explainability for AI-powered Clinical Decision Support System (CDSS) applied to a concrete use case, namely an AI-powered CDSS currently used in the emergency call setting to identify patients with life-threatening cardiac arrest. More specifically, we performed a normative analysis using socio-technical scenarios to provide a nuanced account of the role of explainability for CDSSs for the concrete use case, allowing for abstractions to a more general level. Our analysis focused on three layers: technical considerations, human factors, and the designated system role in decision-making. Our findings suggest that whether explainability can provide added value to CDSS depends on several key questions: technical feasibility, the level of validation in case of explainable algorithms, the characteristics of the context in which the system is implemented, the designated role in the decision-making process, and the key user group(s). Thus, each CDSS will require an individualized assessment of explainability needs and we provide an example of how such an assessment could look like in practice.
Collapse
|
11
|
Brusseau J. From the ground truth up: doing AI ethics from practice to principles. AI & SOCIETY 2022. [DOI: 10.1007/s00146-021-01336-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/19/2022]
|