1
|
Sajdeya R, Narouze S. Harnessing artificial intelligence for predicting and managing postoperative pain: a narrative literature review. Curr Opin Anaesthesiol 2024:00001503-990000000-00209. [PMID: 39011674 DOI: 10.1097/aco.0000000000001408] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 07/17/2024]
Abstract
PURPOSE OF REVIEW This review examines recent research on artificial intelligence focusing on machine learning (ML) models for predicting postoperative pain outcomes. We also identify technical, ethical, and practical hurdles that demand continued investigation and research. RECENT FINDINGS Current ML models leverage diverse datasets, algorithmic techniques, and validation methods to identify predictive biomarkers, risk factors, and phenotypic signatures associated with increased acute and chronic postoperative pain and persistent opioid use. ML models demonstrate satisfactory performance to predict pain outcomes and their prognostic trajectories, identify modifiable risk factors and at-risk patients who benefit from targeted pain management strategies, and show promise in pain prevention applications. However, further evidence is needed to evaluate the reliability, generalizability, effectiveness, and safety of ML-driven approaches before their integration into perioperative pain management practices. SUMMARY Artificial intelligence (AI) has the potential to enhance perioperative pain management by providing more accurate predictive models and personalized interventions. By leveraging ML algorithms, clinicians can better identify at-risk patients and tailor treatment strategies accordingly. However, successful implementation needs to address challenges in data quality, algorithmic complexity, and ethical and practical considerations. Future research should focus on validating AI-driven interventions in clinical practice and fostering interdisciplinary collaboration to advance perioperative care.
Collapse
Affiliation(s)
- Ruba Sajdeya
- Department of Anesthesiology, Duke University School of Medicine, Durham, North Carolina
| | - Samer Narouze
- Division of Pain Medicine, University Hospitals Medical Center, Cleveland, Ohio, USA
| |
Collapse
|
2
|
El-Tallawy SN, Pergolizzi JV, Vasiliu-Feltes I, Ahmed RS, LeQuang JK, El-Tallawy HN, Varrassi G, Nagiub MS. Incorporation of "Artificial Intelligence" for Objective Pain Assessment: A Comprehensive Review. Pain Ther 2024; 13:293-317. [PMID: 38430433 PMCID: PMC11111436 DOI: 10.1007/s40122-024-00584-8] [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: 01/05/2024] [Accepted: 02/08/2024] [Indexed: 03/03/2024] Open
Abstract
Pain is a significant health issue, and pain assessment is essential for proper diagnosis, follow-up, and effective management of pain. The conventional methods of pain assessment often suffer from subjectivity and variability. The main issue is to understand better how people experience pain. In recent years, artificial intelligence (AI) has been playing a growing role in improving clinical diagnosis and decision-making. The application of AI offers promising opportunities to improve the accuracy and efficiency of pain assessment. This review article provides an overview of the current state of AI in pain assessment and explores its potential for improving accuracy, efficiency, and personalized care. By examining the existing literature, research gaps, and future directions, this article aims to guide further advancements in the field of pain management. An online database search was conducted via multiple websites to identify the relevant articles. The inclusion criteria were English articles published between January 2014 and January 2024). Articles that were available as full text clinical trials, observational studies, review articles, systemic reviews, and meta-analyses were included in this review. The exclusion criteria were articles that were not in the English language, not available as free full text, those involving pediatric patients, case reports, and editorials. A total of (47) articles were included in this review. In conclusion, the application of AI in pain management could present promising solutions for pain assessment. AI can potentially increase the accuracy, precision, and efficiency of objective pain assessment.
Collapse
Affiliation(s)
- Salah N El-Tallawy
- Anesthesia and Pain Department, College of Medicine, King Khalid University Hospital, King Saud University, Riyadh, Saudi Arabia.
- Anesthesia and Pain Department, Faculty of Medicine, Minia University & NCI, Cairo University, Giza, Egypt.
| | | | - Ingrid Vasiliu-Feltes
- Science, Entrepreneurship and Investments Institute, University of Miami, Miami, USA
| | - Rania S Ahmed
- College of Medicine, Alfaisal University, Riyadh, Saudi Arabia
| | | | | | | | | |
Collapse
|
3
|
Binson VA, Thomas S, Subramoniam M, Arun J, Naveen S, Madhu S. A Review of Machine Learning Algorithms for Biomedical Applications. Ann Biomed Eng 2024; 52:1159-1183. [PMID: 38383870 DOI: 10.1007/s10439-024-03459-3] [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: 12/30/2023] [Accepted: 01/24/2024] [Indexed: 02/23/2024]
Abstract
As the amount and complexity of biomedical data continue to increase, machine learning methods are becoming a popular tool in creating prediction models for the underlying biomedical processes. Although all machine learning methods aim to fit models to data, the methodologies used can vary greatly and may seem daunting at first. A comprehensive review of various machine learning algorithms per biomedical applications is presented. The key concepts of machine learning are supervised and unsupervised learning, feature selection, and evaluation metrics. Technical insights on the major machine learning methods such as decision trees, random forests, support vector machines, and k-nearest neighbors are analyzed. Next, the dimensionality reduction methods like principal component analysis and t-distributed stochastic neighbor embedding methods, and their applications in biomedical data analysis were reviewed. Moreover, in biomedical applications predominantly feedforward neural networks, convolutional neural networks, and recurrent neural networks are utilized. In addition, the identification of emerging directions in machine learning methodology will serve as a useful reference for individuals involved in biomedical research, clinical practice, and related professions who are interested in understanding and applying machine learning algorithms in their research or practice.
Collapse
Affiliation(s)
- V A Binson
- Department of Electronics Engineering, Saintgits College of Engineering, Kottayam, India
| | - Sania Thomas
- Department of Computer Science and Engineering, Saintgits College of Engineering, Kottayam, India
| | - M Subramoniam
- Department of Electronics Engineering, Sathyabama Institute of Science and Technology, Chennai, Tamil Nadu, India
| | - J Arun
- Centre for Waste Management-International Research Centre, Sathyabama Institute of Science and Technology, Chennai, 600119, India
| | - S Naveen
- Department of Automobile Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, Tamil Nadu, India
| | - S Madhu
- Department of Automobile Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Chennai, Tamil Nadu, India.
| |
Collapse
|
4
|
Tangaro S, Lopalco G, Sabella D, Venerito V, Novielli P, Romano D, Di Gilio A, Palmisani J, de Gennaro G, Filannino P, Latronico R, Bellotti R, De Angelis M, Iannone F. Unraveling the microbiome-metabolome nexus: a comprehensive study protocol for personalized management of Behçet's disease using explainable artificial intelligence. Front Microbiol 2024; 15:1341152. [PMID: 38410386 PMCID: PMC10895059 DOI: 10.3389/fmicb.2024.1341152] [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: 11/19/2023] [Accepted: 01/31/2024] [Indexed: 02/28/2024] Open
Abstract
The presented study protocol outlines a comprehensive investigation into the interplay among the human microbiota, volatilome, and disease biomarkers, with a specific focus on Behçet's disease (BD) using methods based on explainable artificial intelligence. The protocol is structured in three phases. During the initial three-month clinical study, participants will be divided into control and experimental groups. The experimental groups will receive a soluble fiber-based dietary supplement alongside standard therapy. Data collection will encompass oral and fecal microbiota, breath samples, clinical characteristics, laboratory parameters, and dietary habits. The subsequent biological data analysis will involve gas chromatography, mass spectrometry, and metagenetic analysis to examine the volatilome and microbiota composition of salivary and fecal samples. Additionally, chemical characterization of breath samples will be performed. The third phase introduces Explainable Artificial Intelligence (XAI) for the analysis of the collected data. This novel approach aims to evaluate eubiosis and dysbiosis conditions, identify markers associated with BD, dietary habits, and the supplement. Primary objectives include establishing correlations between microbiota, volatilome, phenotypic BD characteristics, and identifying patient groups with shared features. The study aims to identify taxonomic units and metabolic markers predicting clinical outcomes, assess the supplement's impact, and investigate the relationship between dietary habits and patient outcomes. This protocol contributes to understanding the microbiome's role in health and disease and pioneers an XAI-driven approach for personalized BD management. With 70 recruited BD patients, XAI algorithms will analyze multi-modal clinical data, potentially revolutionizing BD management and paving the way for improved patient outcomes.
Collapse
Affiliation(s)
- Sabina Tangaro
- Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo Moro, Bari, Italy
- Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy
| | - Giuseppe Lopalco
- Dipartimento di Medicina di Precisione e Rigenerativa e Area Jonica, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Daniele Sabella
- Dipartimento di Medicina di Precisione e Rigenerativa e Area Jonica, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Vincenzo Venerito
- Dipartimento di Medicina di Precisione e Rigenerativa e Area Jonica, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Pierfrancesco Novielli
- Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo Moro, Bari, Italy
- Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy
| | - Donato Romano
- Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo Moro, Bari, Italy
- Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy
| | - Alessia Di Gilio
- Dipartimento di Bioscienze, Biotecnologie e Ambiente, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Jolanda Palmisani
- Dipartimento di Bioscienze, Biotecnologie e Ambiente, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Gianluigi de Gennaro
- Dipartimento di Bioscienze, Biotecnologie e Ambiente, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Pasquale Filannino
- Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Rosanna Latronico
- Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Roberto Bellotti
- Istituto Nazionale di Fisica Nucleare, Sezione di Bari, Bari, Italy
- Dipartimento Interateneo di Fisica ‘M. Merlin’, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Maria De Angelis
- Dipartimento di Scienze del Suolo, della Pianta e degli Alimenti, Università degli Studi di Bari Aldo Moro, Bari, Italy
| | - Florenzo Iannone
- Dipartimento di Medicina di Precisione e Rigenerativa e Area Jonica, Università degli Studi di Bari Aldo Moro, Bari, Italy
| |
Collapse
|
5
|
Wang B, Asan O, Mansouri M. Perspectives of Patients With Chronic Diseases on Future Acceptance of AI-Based Home Care Systems: Cross-Sectional Web-Based Survey Study. JMIR Hum Factors 2023; 10:e49788. [PMID: 37930780 PMCID: PMC10660233 DOI: 10.2196/49788] [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: 06/08/2023] [Revised: 08/18/2023] [Accepted: 10/05/2023] [Indexed: 11/07/2023] Open
Abstract
BACKGROUND Artificial intelligence (AI)-based home care systems and devices are being gradually integrated into health care delivery to benefit patients with chronic diseases. However, existing research mainly focuses on the technical and clinical aspects of AI application, with an insufficient investigation of patients' motivation and intention to adopt such systems. OBJECTIVE This study aimed to examine the factors that affect the motivation of patients with chronic diseases to adopt AI-based home care systems and provide empirical evidence for the proposed research hypotheses. METHODS We conducted a cross-sectional web-based survey with 222 patients with chronic diseases based on a hypothetical scenario. RESULTS The results indicated that patients have an overall positive perception of AI-based home care systems. Their attitudes toward the technology, perceived usefulness, and comfortability were found to be significant factors encouraging adoption, with a clear understanding of accountability being a particularly influential factor in shaping patients' attitudes toward their motivation to use these systems. However, privacy concerns persist as an indirect factor, affecting the perceived usefulness and comfortability, hence influencing patients' attitudes. CONCLUSIONS This study is one of the first to examine the motivation of patients with chronic diseases to adopt AI-based home care systems, offering practical insights for policy makers, care or technology providers, and patients. This understanding can facilitate effective policy formulation, product design, and informed patient decision-making, potentially improving the overall health status of patients with chronic diseases.
Collapse
Affiliation(s)
- Bijun Wang
- Department of Business Analytics and Data Science, Florida Polytechnic University, Lakeland, FL, United States
| | - Onur Asan
- School of Systems and Enterprises, Stevens Institue of Technology, Hoboken, NJ, United States
| | - Mo Mansouri
- School of Systems and Enterprises, Stevens Institue of Technology, Hoboken, NJ, United States
| |
Collapse
|
6
|
Huang W, Suominen H, Liu T, Rice G, Salomon C, Barnard AS. Explainable discovery of disease biomarkers: The case of ovarian cancer to illustrate the best practice in machine learning and Shapley analysis. J Biomed Inform 2023; 141:104365. [PMID: 37062419 DOI: 10.1016/j.jbi.2023.104365] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/22/2022] [Revised: 03/24/2023] [Accepted: 04/10/2023] [Indexed: 04/18/2023]
Abstract
OBJECTIVE Ovarian cancer is a significant health issue with lasting impacts on the community. Despite recent advances in surgical, chemotherapeutic and radiotherapeutic interventions, they have had only marginal impacts due to an inability to identify biomarkers at an early stage. Biomarker discovery is challenging, yet essential for improving drug discovery and clinical care. Machine learning (ML) techniques are invaluable for recognising complex patterns in biomarkers compared to conventional methods, yet they can lack physical insights into diagnosis. eXplainable Artificial Intelligence (XAI) is capable of providing deeper insights into the decision-making of complex ML algorithms increasing their applicability. We aim to introduce best practice for combining ML and XAI techniques for biomarker validation tasks. METHODS We focused on classification tasks and a game theoretic approach based on Shapley values to build and evaluate models and visualise results. We described the workflow and apply the pipeline in a case study using the CDAS PLCO Ovarian Biomarkers dataset to demonstrate the potential for accuracy and utility. RESULTS The case study results demonstrate the efficacy of the ML pipeline, its consistency, and advantages compared to conventional statistical approaches. CONCLUSION The resulting guidelines provide a general framework for practical application of XAI in medical research that can inform clinicians and validate and explain cancer biomarkers.
Collapse
Affiliation(s)
- Weitong Huang
- School of Computing, Australian National University, Acton, ACT 2601, Australia.
| | - Hanna Suominen
- School of Computing, Australian National University, Acton, ACT 2601, Australia; Department of Computing, University of Turku, Turku, Finland
| | - Tommy Liu
- School of Computing, Australian National University, Acton, ACT 2601, Australia
| | - Gregory Rice
- Exosome Biology Laboratory, Centre for Clinical Diagnostics, University of Queensland Centre for Clinical Research, Royal Brisbane and Women's Hospital, Faculty of Medicine, The University of Queensland, Brisbane, Australia; Inoviq Limited, Notting Hill, Australia
| | - Carlos Salomon
- Exosome Biology Laboratory, Centre for Clinical Diagnostics, University of Queensland Centre for Clinical Research, Royal Brisbane and Women's Hospital, Faculty of Medicine, The University of Queensland, Brisbane, Australia; Translational Extracellular Vesicles in Obstetrics and Gynae-Oncology Group, Centre for Clinical Diagnostics, University of Queensland Centre for Clinical Research, Royal Brisbane and Women's Hospital, Faculty of Medicine, The University of Queensland, Brisbane, Australia
| | - Amanda S Barnard
- School of Computing, Australian National University, Acton, ACT 2601, Australia
| |
Collapse
|
7
|
Cenci A, Ilskov SJ, Andersen NS, Chiarandini M. The participatory value-sensitive design (VSD) of a mHealth app targeting citizens with dementia in a Danish municipality. AI AND ETHICS 2023:1-27. [PMID: 37360145 PMCID: PMC10099010 DOI: 10.1007/s43681-023-00274-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/17/2022] [Accepted: 03/02/2023] [Indexed: 06/28/2023]
Abstract
The Sammen Om Demens (together for dementia), a citizen science project developing and implementing an AI-based smartphone app targeting citizens with dementia, is presented as an illustrative case of ethical, applied AI entailing interdisciplinary collaborations and inclusive and participative scientific practices engaging citizens, end users, and potential recipients of technological-digital innovation. Accordingly, the participatory Value-Sensitive Design of the smartphone app (a tracking device) is explored and explained across all of its phases (conceptual, empirical, and technical). Namely, from value construction and value elicitation to the delivery, after various iterations engaging both expert and non-expert stakeholders, of an embodied prototype built on and tailored to their values. The emphasis is on how moral dilemmas and value conflicts, often resulting from diverse people's needs or vested interests, have been resolved in practice to deliver a unique digital artifact with moral imagination that fulfills vital ethical-social desiderata without undermining technical efficiency. The result is an AI-based tool for the management and care of dementia that can be considered more ethical and democratic, since it meaningfully reflects diverse citizens' values and expectations on the app. In the conclusion, we suggest that the co-design methodology outlined in this study is suitable to generate more explainable and trustworthy AI, and also, it helps to advance towards technical-digital innovation holding a human face.
Collapse
Affiliation(s)
- Alessandra Cenci
- Department of Philosophy, Institute for the Study and Culture (IKV), University of Southern Denmark, Odense, Denmark
| | - Susanne Jakobsen Ilskov
- Department of Philosophy, Institute for the Study and Culture (IKV), University of Southern Denmark, Odense, Denmark
| | - Nicklas Sindlev Andersen
- Department of Mathematics and Data Science (IMADA), University of Southern Denmark, Odense, Denmark
| | - Marco Chiarandini
- Department of Mathematics and Data Science (IMADA), University of Southern Denmark, Odense, Denmark
| |
Collapse
|
8
|
Ramgopal S, Sanchez-Pinto LN, Horvat CM, Carroll MS, Luo Y, Florin TA. Artificial intelligence-based clinical decision support in pediatrics. Pediatr Res 2023; 93:334-341. [PMID: 35906317 PMCID: PMC9668209 DOI: 10.1038/s41390-022-02226-1] [Citation(s) in RCA: 20] [Impact Index Per Article: 20.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 03/21/2022] [Revised: 06/29/2022] [Accepted: 07/18/2022] [Indexed: 11/24/2022]
Abstract
Machine learning models may be integrated into clinical decision support (CDS) systems to identify children at risk of specific diagnoses or clinical deterioration to provide evidence-based recommendations. This use of artificial intelligence models in clinical decision support (AI-CDS) may have several advantages over traditional "rule-based" CDS models in pediatric care through increased model accuracy, with fewer false alerts and missed patients. AI-CDS tools must be appropriately developed, provide insight into the rationale behind decisions, be seamlessly integrated into care pathways, be intuitive to use, answer clinically relevant questions, respect the content expertise of the healthcare provider, and be scientifically sound. While numerous machine learning models have been reported in pediatric care, their integration into AI-CDS remains incompletely realized to date. Important challenges in the application of AI models in pediatric care include the relatively lower rates of clinically significant outcomes compared to adults, and the lack of sufficiently large datasets available necessary for the development of machine learning models. In this review article, we summarize key concepts related to AI-CDS, its current application to pediatric care, and its potential benefits and risks. IMPACT: The performance of clinical decision support may be enhanced by the utilization of machine learning-based algorithms to improve the predictive performance of underlying models. Artificial intelligence-based clinical decision support (AI-CDS) uses models that are experientially improved through training and are particularly well suited toward high-dimensional data. The application of AI-CDS toward pediatric care remains limited currently but represents an important area of future research.
Collapse
Affiliation(s)
- Sriram Ramgopal
- Division of Emergency Medicine, Ann & Robert H. Lurie Children's Hospital of Chicago, Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, IL, USA.
| | - L. Nelson Sanchez-Pinto
- grid.16753.360000 0001 2299 3507Division of Critical Care Medicine, Ann & Robert H. Lurie Children’s Hospital of Chicago, Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, IL USA ,grid.16753.360000 0001 2299 3507Department of Preventive Medicine (Health and Biomedical Informatics), Feinberg School of Medicine, Northwestern University, Chicago, IL USA
| | - Christopher M. Horvat
- grid.21925.3d0000 0004 1936 9000Department of Critical Care Medicine, UPMC Children’s Hospital of Pittsburgh, University of Pittsburgh School of Medicine, Pittsburgh, PA USA
| | - Michael S. Carroll
- grid.16753.360000 0001 2299 3507Data Analytics and Reporting, Ann & Robert H. Lurie Children’s Hospital of Chicago, Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, IL USA
| | - Yuan Luo
- grid.16753.360000 0001 2299 3507Department of Preventive Medicine (Health and Biomedical Informatics), Feinberg School of Medicine, Northwestern University, Chicago, IL USA
| | - Todd A. Florin
- grid.16753.360000 0001 2299 3507Division of Emergency Medicine, Ann & Robert H. Lurie Children’s Hospital of Chicago, Department of Pediatrics, Northwestern University Feinberg School of Medicine, Chicago, IL USA
| |
Collapse
|
9
|
The Usefulness of Gradient-Weighted CAM in Assisting Medical Diagnoses. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12157748] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/07/2023]
Abstract
In modern medicine, medical imaging technologies such as computed tomography (CT), X-ray, ultrasound, magnetic resonance imaging (MRI), nuclear medicine, etc., have been proven to provide useful diagnostic information by displaying areas of a lesion or tumor not visible to the human eye, and may also help provide additional recessive information by using modern data analysis methods. These methods, including Artificial Intelligence (AI) technologies, are based on deep learning architectures, and have shown remarkable results in recent studies. However, the lack of explanatory ability of connection-based, instead of algorithm-based, deep learning technologies is one of the main reasons for the delay in the acceptance of these technologies in the mainstream medical field. One of the recent methods that may offer the explanatory ability for the CNN classes of deep learning neural networks is the gradient-weighted class activation mapping (Grad-CAM) method, which produces heat-maps that may offer explanations of the classification results. There are already many studies in the literature that compare the objective metrics of Grad-CAM-generated heat-maps against other methods. However, the subjective evaluation of AI-based classification/prediction results using medical images by qualified personnel could potentially contribute more to the acceptance of AI than objective metrics. The purpose of this paper is to investigate whether and how the Grad-CAM heat-maps can help physicians and radiologists in making diagnoses by presenting the results from AI-based classifications as well as their associated Grad-CAM-generated heat-maps to a qualified radiologist. The results of this study show that the radiologist considers Grad-CAM-generated heat-maps to be generally helpful toward diagnosis.
Collapse
|
10
|
Brakefield WS, Ammar N, Shaban-Nejad A. An Urban Population Health Observatory for Disease Causal Pathway Analysis and Decision Support: Underlying Explainable Artificial Intelligence Model. JMIR Form Res 2022; 6:e36055. [PMID: 35857363 PMCID: PMC9350817 DOI: 10.2196/36055] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/29/2021] [Revised: 05/03/2022] [Accepted: 06/07/2022] [Indexed: 01/16/2023] Open
Abstract
Background Many researchers have aimed to develop chronic health surveillance systems to assist in public health decision-making. Several digital health solutions created lack the ability to explain their decisions and actions to human users. Objective This study sought to (1) expand our existing Urban Population Health Observatory (UPHO) system by incorporating a semantics layer; (2) cohesively employ machine learning and semantic/logical inference to provide measurable evidence and detect pathways leading to undesirable health outcomes; (3) provide clinical use case scenarios and design case studies to identify socioenvironmental determinants of health associated with the prevalence of obesity, and (4) design a dashboard that demonstrates the use of UPHO in the context of obesity surveillance using the provided scenarios. Methods The system design includes a knowledge graph generation component that provides contextual knowledge from relevant domains of interest. This system leverages semantics using concepts, properties, and axioms from existing ontologies. In addition, we used the publicly available US Centers for Disease Control and Prevention 500 Cities data set to perform multivariate analysis. A cohesive approach that employs machine learning and semantic/logical inference reveals pathways leading to diseases. Results In this study, we present 2 clinical case scenarios and a proof-of-concept prototype design of a dashboard that provides warnings, recommendations, and explanations and demonstrates the use of UPHO in the context of obesity surveillance, treatment, and prevention. While exploring the case scenarios using a support vector regression machine learning model, we found that poverty, lack of physical activity, education, and unemployment were the most important predictive variables that contribute to obesity in Memphis, TN. Conclusions The application of UPHO could help reduce health disparities and improve urban population health. The expanded UPHO feature incorporates an additional level of interpretable knowledge to enhance physicians, researchers, and health officials' informed decision-making at both patient and community levels. International Registered Report Identifier (IRRID) RR2-10.2196/28269
Collapse
Affiliation(s)
- Whitney S Brakefield
- Center for Biomedical Informatics, Department of Pediatrics, College of Medicine, University of Tennessee Health Science Center, Memphis, TN, United States.,Bredesen Center for Data Science, University of Tennessee, Knoxville, TN, United States
| | - Nariman Ammar
- Center for Biomedical Informatics, Department of Pediatrics, College of Medicine, University of Tennessee Health Science Center, Memphis, TN, United States.,Ochsner Xavier Institute for Health Equity and Research, Ochsner Clinic Foundation, New Orleans, LA, United States
| | - Arash Shaban-Nejad
- Center for Biomedical Informatics, Department of Pediatrics, College of Medicine, University of Tennessee Health Science Center, Memphis, TN, United States
| |
Collapse
|
11
|
Meyer J, Khademi A, Têtu B, Han W, Nippak P, Remisch D. Impact of artificial intelligence on pathologists' decisions: an experiment. J Am Med Inform Assoc 2022; 29:1688-1695. [PMID: 35751441 DOI: 10.1093/jamia/ocac103] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2022] [Revised: 05/30/2022] [Accepted: 06/09/2022] [Indexed: 02/06/2023] Open
Abstract
OBJECTIVE The accuracy of artificial intelligence (AI) in medicine and in pathology in particular has made major progress but little is known on how much these algorithms will influence pathologists' decisions in practice. The objective of this paper is to determine the reliance of pathologists on AI and to investigate whether providing information on AI impacts this reliance. MATERIALS AND METHODS The experiment using an online survey design. Under 3 conditions, 116 pathologists and pathology students were tasked with assessing the Gleason grade for a series of 12 prostate biopsies: (1) without AI recommendations, (2) with AI recommendations, and (3) with AI recommendations accompanied by information about the algorithm itself, specifically algorithm accuracy rate and algorithm decision-making process. RESULTS Participant responses were significantly more accurate with the AI decision aids than without (92% vs 87%, odds ratio 13.30, P < .01). Unexpectedly, the provision of information on the algorithm made no significant difference compared to AI without information. The reliance on AI correlated with general beliefs on AI's usefulness but not with particular assessments of the AI tool offered. Decisions were made faster when AI was provided. DISCUSSION These results suggest that pathologists are willing to rely on AI regardless of accuracy or explanations. Generalization beyond the specific tasks and explanations provided will require further studies. CONCLUSION This study suggests that the factors that influence the reliance on AI differ in practice from beliefs expressed by clinicians in surveys. Implementation of AI in prospective settings should take individual behaviors into account.
Collapse
Affiliation(s)
- Julien Meyer
- School of Health Services Management, Ted Rogers School of Management, Toronto, Ontario, Canada
| | - April Khademi
- Department of Electrical, Computer, and Biomedical Engineering, Ryerson University, Toronto, Ontario, Canada
| | - Bernard Têtu
- Départment de biologie médicale, Université Laval, Québec City, Quebec, Canada
| | - Wencui Han
- Department of Business administration, Gies College of Business, University of Illinois at Urbana-Champaign, Champaign, Illinois, USA
| | - Pria Nippak
- School of Health Services Management, Ted Rogers School of Management, Toronto, Ontario, Canada
| | - David Remisch
- School of Health Services Management, Ted Rogers School of Management, Toronto, Ontario, Canada
| |
Collapse
|