1
|
Labrom FR, Izatt MT, Askin GN, Labrom RD, Claus AP, Little JP. Quantifying Typical Progression of Adolescent Idiopathic Scoliosis: Longitudinal Three-Dimensional MRI Measures of Disk and Vertebral Deformities. Spine (Phila Pa 1976) 2023; 48:1642-1651. [PMID: 37702242 DOI: 10.1097/brs.0000000000004829] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 06/23/2023] [Accepted: 09/06/2023] [Indexed: 09/14/2023]
Abstract
STUDY DESIGN A prospective cohort study. OBJECTIVE Detail typical three-dimensional segmental deformities and their rates of change that occur within developing adolescent idiopathic scoliosis (AIS) spines over multiple timepoints. SUMMARY OF BACKGROUND DATA AIS is a potentially progressive deforming condition that occurs in three dimensions of the scoliotic spine during periods of growth. However, there remains a gap for multiple timepoint segmental deformity analysis in AIS cohorts during development. MATERIALS AND METHODS Thirty-six female patients with Lenke 1 AIS curves underwent two to six sequential magnetic resonance images. Scans were reformatted to produce images in orthogonal dimensions. Wedging angles and rotatory values were measured for segmental elements within the major curve. Two-tailed, paired t tests compared morphologic differences between sequential scans. Rates of change were calculated for variables given the actual time between successive scans. Pearson correlation coefficients were determined for multidimensional deformity measurements. RESULTS Vertebral bodies were typically coronally convexly wedged, locally lordotic, convexly axially rotated, and demonstrated evidence of local mechanical torsion. Between the first and final scans, apical measures of coronal wedging and axial rotation were all greater in both vertebral and intervertebral disk morphology than nonapical regions (all reaching differences where P <0.05). No measures of sagittal deformity demonstrated a statistically significant change between scans. Cross-planar correlations were predominantly apparent between coronal and axial planes, with sagittal plane parameters rarely correlating across dimensions. Rates of segmental deformity changes between earlier scans were characterized by coronal plane convex wedging and convexly directed axial rotation. The major locally lordotic deformity changes that did occur in the sagittal plane were static between scans. CONCLUSIONS This novel investigation documented a three-dimensional characterization of segmental elements of the growing AIS spine and reported these changes across multiple timepoints. Segmental elements are typically deformed from initial presentation, and subsequent changes occur in separate orthogonal planes at unique times.
Collapse
Affiliation(s)
- Fraser R Labrom
- Biomechanics & Spine Research Group, Centre for Children's Health Research, Queensland University of Technology, Brisbane, Australia
- Queensland Children's Hospital and Mater Health Services, Brisbane, Australia
| | - Maree T Izatt
- Biomechanics & Spine Research Group, Centre for Children's Health Research, Queensland University of Technology, Brisbane, Australia
- Queensland Children's Hospital and Mater Health Services, Brisbane, Australia
| | - Geoffrey N Askin
- Biomechanics & Spine Research Group, Centre for Children's Health Research, Queensland University of Technology, Brisbane, Australia
- Queensland Children's Hospital and Mater Health Services, Brisbane, Australia
| | - Robert D Labrom
- Biomechanics & Spine Research Group, Centre for Children's Health Research, Queensland University of Technology, Brisbane, Australia
- Queensland Children's Hospital and Mater Health Services, Brisbane, Australia
| | - Andrew P Claus
- Tess Cramond Pain and Research Centre, Royal Brisbane and Women's Hospital, Brisbane, Queensland, Australia
- University of Queensland, School of Health & Rehabilitation Sciences, St Lucia, Queensland, Australia
| | - J Paige Little
- Biomechanics & Spine Research Group, Centre for Children's Health Research, Queensland University of Technology, Brisbane, Australia
| |
Collapse
|
2
|
Das S, Zomorrodi R, Mirjalili M, Kirkovski M, Blumberger DM, Rajji TK, Desarkar P. Machine learning approaches for electroencephalography and magnetoencephalography analyses in autism spectrum disorder: A systematic review. Prog Neuropsychopharmacol Biol Psychiatry 2023; 123:110705. [PMID: 36574922 DOI: 10.1016/j.pnpbp.2022.110705] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/29/2022] [Revised: 12/04/2022] [Accepted: 12/21/2022] [Indexed: 12/26/2022]
Abstract
There are growing application of machine learning models to study the intricacies of non-linear and non-stationary characteristics of electroencephalography (EEG) and magnetoencephalography (MEG) data in neurobiologically complex and heterogeneous conditions such as autism spectrum disorder (ASD). Such tools have potential diagnostic applications, and given the highly heterogeneous presentation of ASD, might prove fruitful in early detection and therefore could facilitate very early intervention. We conducted a systematic review (PROSPERO ID#CRD42021257438) by searching PubMed, EMBASE, and PsychINFO for machine learning approaches for EEG and MEG analyses in ASD. Thirty-nine studies were identified, of which the majority (18) used support vector machines for classification; other successful methods included deep learning. Thirty-seven studies were found to employ EEG and two were found to employ MEG. This systematic review indicate that machine learning methods can be used to classify ASD, predict ASD diagnosis in high-risk infants as early as 3 months of age, predict ASD symptom severity, and classify states of cognition in ASD with high accuracy. Replication studies testing validity, reproducibility and generalizability in tandem with randomized controlled trials in ASD populations will likely benefit the field.
Collapse
Affiliation(s)
- Sushmit Das
- Centre for Addiction and Mental Health, Toronto, Canada; Azrieli Adult Neurodevelopmental Centre, Centre for Addiction and Mental Health, Toronto, ON, Canada
| | - Reza Zomorrodi
- Centre for Addiction and Mental Health, Toronto, Canada; Temerty Centre for Therapeutic Brain Intervention, Centre for Addiction and Mental Health, Toronto, ON, Canada
| | - Mina Mirjalili
- Centre for Addiction and Mental Health, Toronto, Canada; Campbell Family Mental Health Research Institute, Centre for Addiction and Mental Health, Toronto, ON, Canada; Adult Neurodevelopmental and Geriatric Psychiatry Division, Centre for Addiction and Mental Health, Toronto, ON, Canada; Institute of Medical Science, University of Toronto, Toronto, ON, Canada; Vector Institute for Artificial Intelligence, Toronto, ON, Canada
| | - Melissa Kirkovski
- Cognitive Neuroscience Unit, School of Psychology, Deakin University, Geelong, Australia; Insitute for Health and Sport, Victoria University, Melbourne, Australia
| | - Daniel M Blumberger
- Centre for Addiction and Mental Health, Toronto, Canada; Department of Psychiatry, University of Toronto, Toronto, ON, Canada; Temerty Centre for Therapeutic Brain Intervention, Centre for Addiction and Mental Health, Toronto, ON, Canada
| | - Tarek K Rajji
- Centre for Addiction and Mental Health, Toronto, Canada; Department of Psychiatry, University of Toronto, Toronto, ON, Canada; Temerty Centre for Therapeutic Brain Intervention, Centre for Addiction and Mental Health, Toronto, ON, Canada
| | - Pushpal Desarkar
- Centre for Addiction and Mental Health, Toronto, Canada; Department of Psychiatry, University of Toronto, Toronto, ON, Canada; Azrieli Adult Neurodevelopmental Centre, Centre for Addiction and Mental Health, Toronto, ON, Canada; Temerty Centre for Therapeutic Brain Intervention, Centre for Addiction and Mental Health, Toronto, ON, Canada.
| |
Collapse
|
3
|
Coiera E, Liu S. Evidence synthesis, digital scribes, and translational challenges for artificial intelligence in healthcare. Cell Rep Med 2022; 3:100860. [PMID: 36513071 PMCID: PMC9798027 DOI: 10.1016/j.xcrm.2022.100860] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2022] [Revised: 10/15/2022] [Accepted: 11/18/2022] [Indexed: 12/14/2022]
Abstract
Healthcare has well-known challenges with safety, quality, and effectiveness, and many see artificial intelligence (AI) as essential to any solution. Emerging applications include the automated synthesis of best-practice research evidence including systematic reviews, which would ultimately see all clinical trial data published in a computational form for immediate synthesis. Digital scribes embed themselves in the process of care to detect, record, and summarize events and conversations for the electronic record. However, three persistent translational challenges must be addressed before AI is widely deployed. First, little effort is spent replicating AI trials, exposing patients to risks of methodological error and biases. Next, there is little reporting of patient harms from trials. Finally, AI built using machine learning may perform less effectively in different clinical settings.
Collapse
Affiliation(s)
- Enrico Coiera
- Centre for Health Informatics, Australian Institute of Health Innovation, Macquarie University, Level 6, 75 Talavera Road, North Ryde, Sydney, NSW 2109, Australia.
| | - Sidong Liu
- Centre for Health Informatics, Australian Institute of Health Innovation, Macquarie University, Level 6, 75 Talavera Road, North Ryde, Sydney, NSW 2109, Australia
| |
Collapse
|
4
|
Javaid A, Zghyer F, Kim C, Spaulding EM, Isakadze N, Ding J, Kargillis D, Gao Y, Rahman F, Brown DE, Saria S, Martin SS, Kramer CM, Blumenthal RS, Marvel FA. Medicine 2032: The future of cardiovascular disease prevention with machine learning and digital health technology. Am J Prev Cardiol 2022; 12:100379. [PMID: 36090536 PMCID: PMC9460561 DOI: 10.1016/j.ajpc.2022.100379] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/11/2022] [Revised: 08/21/2022] [Accepted: 08/28/2022] [Indexed: 11/30/2022] Open
Abstract
Machine learning (ML) refers to computational algorithms that iteratively improve their ability to recognize patterns in data. The digitization of our healthcare infrastructure is generating an abundance of data from electronic health records, imaging, wearables, and sensors that can be analyzed by ML algorithms to generate personalized risk assessments and promote guideline-directed medical management. ML's strength in generating insights from complex medical data to guide clinical decisions must be balanced with the potential to adversely affect patient privacy, safety, health equity, and clinical interpretability. This review provides a primer on key advances in ML for cardiovascular disease prevention and how they may impact clinical practice.
Collapse
|
5
|
Salwei ME, Carayon P. A Sociotechnical Systems Framework for the Application of Artificial Intelligence in Health Care Delivery. JOURNAL OF COGNITIVE ENGINEERING AND DECISION MAKING 2022; 16:194-206. [PMID: 36704421 PMCID: PMC9873227 DOI: 10.1177/15553434221097357] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/14/2023]
Abstract
In the coming years, artificial intelligence (AI) will pervade almost every aspect of the health care delivery system. AI has the potential to improve patient safety (e.g. diagnostic accuracy) as well as reduce the burden on clinicians (e.g. documentation-related workload); however, these benefits are yet to be realized. AI is only one element of a larger sociotechnical system that needs to be considered for effective AI application. In this paper, we describe the current challenges of integrating AI into clinical care and propose a sociotechnical systems (STS) approach for AI design and implementation. We demonstrate the importance of an STS approach through a case study on the design and implementation of a clinical decision support (CDS). In order for AI to reach its potential, the entire work system as well as clinical workflow must be systematically considered throughout the design of AI technology.
Collapse
Affiliation(s)
- Megan E. Salwei
- Center for Research and Innovation in Systems Safety, Department of Anesthesiology, Vanderbilt University Medical Center, Nashville, TN
- Department of Biomedical Informatics, Vanderbilt University Medical Center, Nashville, TN
| | - Pascale Carayon
- Department of Industrial and Systems Engineering, University of Wisconsin-Madison, Madison, WI
- Wisconsin Institute for Healthcare Systems Engineering, University of Wisconsin-Madison, Madison, WI
| |
Collapse
|
6
|
Zhao X, Gu B, Li Q, Li J, Zeng W, Li Y, Guan Y, Huang M, Lei L, Zhong G. Machine learning approach identified clusters for patients with low cardiac output syndrome and outcomes after cardiac surgery. Front Cardiovasc Med 2022; 9:962992. [PMID: 36061544 PMCID: PMC9434347 DOI: 10.3389/fcvm.2022.962992] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/07/2022] [Accepted: 07/25/2022] [Indexed: 11/18/2022] Open
Abstract
Background Low cardiac output syndrome (LCOS) is the most serious physiological abnormality with high mortality for patients after cardiac surgery. This study aimed to explore the multidimensional data of clinical features and outcomes to provide individualized care for patients with LCOS. Methods The electronic medical information of the intensive care units (ICUs) was extracted from a tertiary hospital in South China. We included patients who were diagnosed with LCOS in the ICU database. We used the consensus clustering approach based on patient characteristics, laboratory data, and vital signs to identify LCOS subgroups. The consensus clustering method involves subsampling from a set of items, such as microarrays, and determines to cluster of specified cluster counts (k). The primary clinical outcome was in-hospital mortality and was compared between the clusters. Results A total of 1,205 patients were included and divided into three clusters. Cluster 1 (n = 443) was defined as the low-risk group [in-hospital mortality =10.1%, odds ratio (OR) = 1]. Cluster 2 (n = 396) was defined as the medium-risk group [in-hospital mortality =25.0%, OR = 2.96 (95% CI = 1.97–4.46)]. Cluster 3 (n = 366) was defined as the high-risk group [in-hospital mortality =39.2%, OR = 5.75 (95% CI = 3.9–8.5)]. Conclusion Patients with LCOS after cardiac surgery could be divided into three clusters and had different outcomes.
Collapse
Affiliation(s)
- Xu Zhao
- Department of Pharmaceutical Sciences, Institute of Clinical Pharmacology, Sun Yat-sen University, Guangzhou, China
| | - Bowen Gu
- Laboratory of South China Structural Heart Disease, Department of Intensive Care Unit of Cardiovascular Suregery, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangzhou, China
| | - Qiuying Li
- Laboratory of South China Structural Heart Disease, Department of Intensive Care Unit of Cardiovascular Suregery, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangzhou, China
| | - Jiaxin Li
- Laboratory of South China Structural Heart Disease, Department of Intensive Care Unit of Cardiovascular Suregery, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangzhou, China
| | - Weiwei Zeng
- Department of Pharmacy, The Second People's Hospital of Longgang District, Shenzhen, China
| | - Yagang Li
- Department of Pharmaceutical Sciences, Institute of Clinical Pharmacology, Sun Yat-sen University, Guangzhou, China
| | - Yanping Guan
- Department of Pharmaceutical Sciences, Institute of Clinical Pharmacology, Sun Yat-sen University, Guangzhou, China
| | - Min Huang
- Department of Pharmaceutical Sciences, Institute of Clinical Pharmacology, Sun Yat-sen University, Guangzhou, China
| | - Liming Lei
- Laboratory of South China Structural Heart Disease, Department of Intensive Care Unit of Cardiovascular Suregery, Guangdong Cardiovascular Institute, Guangdong Provincial People's Hospital, Guangzhou, China
- *Correspondence: Liming Lei
| | - Guoping Zhong
- Department of Pharmaceutical Sciences, Institute of Clinical Pharmacology, Sun Yat-sen University, Guangzhou, China
- Guoping Zhong
| |
Collapse
|
7
|
Deep Learning Approaches for the Segmentation of Glomeruli in Kidney Histopathological Images. MATHEMATICS 2022. [DOI: 10.3390/math10111934] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/01/2023]
Abstract
Deep learning is widely applied in bioinformatics and biomedical imaging, due to its ability to perform various clinical tasks automatically and accurately. In particular, the application of deep learning techniques for the automatic identification of glomeruli in histopathological kidney images can play a fundamental role, offering a valid decision support system tool for the automatic evaluation of the Karpinski metric. This will help clinicians in detecting the presence of sclerotic glomeruli in order to decide whether the kidney is transplantable or not. In this work, we implemented a deep learning framework to identify and segment sclerotic and non-sclerotic glomeruli from scanned Whole Slide Images (WSIs) of human kidney biopsies. The experiments were conducted on a new dataset collected by both the Siena and Trieste hospitals. The images were segmented using the DeepLab V2 model, with a pre-trained ResNet101 encoder, applied to 512 × 512 patches extracted from the original WSIs. The results obtained are promising and show a good performance in the segmentation task and a good generalization capacity, despite the different coloring and typology of the histopathological images. Moreover, we present a novel use of the CD10 staining procedure, which gives promising results when applied to the segmentation of sclerotic glomeruli in kidney tissues.
Collapse
|
8
|
Huang G, Mao J. Identification of a 12-Gene Signature and Hub Genes Involved in Kidney Wilms Tumor via Integrated Bioinformatics Analysis. Front Oncol 2022; 12:877796. [PMID: 35480093 PMCID: PMC9038080 DOI: 10.3389/fonc.2022.877796] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/17/2022] [Accepted: 03/07/2022] [Indexed: 01/23/2023] Open
Abstract
Wilms tumor (WT), also known as nephroblastoma, is a rare primary malignancy in all kinds of tumor. With the development of second-generation sequencing, the discovery of new tumor markers and potential therapeutic targets has become easier. This study aimed to explore new WT prognostic biomarkers. In this study, WT-miRNA datasets GSE57370 and GSE73209 were selected for expression profiling to identify differentially expressed genes. The key gene miRNA, namely hsa-miR-30c-5p, was identified by overlapping, and the target gene of candidate hsa-miR-30c-5p was predicted using an online database. Furthermore, 384 genes were obtained by intersecting them with differentially expressed genes in the TARGET-WT database, and the genes were analyzed for pathway and functional enrichment. Kaplan–Meier survival analysis of the 384 genes yielded a total of 25 key genes associated with WT prognosis. Subsequently, a prediction model with 12 gene signatures (BCL6, CCNA1, CTHRC1, DGKD, EPB41L4B, ERRFI1, LRRC40, NCEH1, NEBL, PDSS1, ROR1, and RTKN2) was developed. The model had good predictive power for the WT prognosis at 1, 3, and 5 years (AUC: 0.684, 0.762, and 0.774). Finally, ERRFI1 (hazard ratios [HR] = 1.858, 95% confidence intervals [CI]: 1.298–2.660) and ROR1 (HR = 0.780, 95% CI: 0.609–0.998) were obtained as independent predictors of prognosis in WT patients by single, multifactorial Cox analysis.
Collapse
|
9
|
Looi JCL, Bonner D, Maguire P. Maslow's hammer: considering the perils of solutionism in mental healthcare and psychiatric practice. Australas Psychiatry 2021; 29:687-689. [PMID: 34014790 DOI: 10.1177/10398562211005438] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/17/2022]
Abstract
OBJECTIVE To discuss narrow pragmatism, manifest as digital and technical solutionism, in mental healthcare and psychiatric practice. Pragmatism is a view of the field of psychiatry as an instrument or tool for the purpose of providing psychiatric care for people with a mental illness. Solutionism, as proposed by Morozov, can be considered a special case of pragmatism that valorises an approach to solving real-world problems based on computation, algorithms and digital technology,1 which we extend to discuss other technical solutions such as medication, non-invasive brain stimulation and psychotherapy. CONCLUSIONS Digital or technical solutionism may unnecessarily constrain approaches to mental healthcare and psychiatric practice. Psychiatrists can consider, and should advocate for, appropriate adaptation of technology and technical solutions toward collaborative and effective mental healthcare.
Collapse
Affiliation(s)
- Jeffrey C L Looi
- Academic Unit of Psychiatry and Addiction Medicine, the Australian National University Medical School, Canberra Hospital, ACT, Australia
| | - Daniel Bonner
- Academic Unit of Psychiatry and Addiction Medicine, the Australian National University Medical School, Canberra Hospital, ACT, Australia
| | - Paul Maguire
- Academic Unit of Psychiatry and Addiction Medicine, the Australian National University Medical School, Canberra Hospital, ACT, Australia
| |
Collapse
|
10
|
Javaid A, Shahab O, Adorno W, Fernandes P, May E, Syed S. Machine Learning Predictive Outcomes Modeling in Inflammatory Bowel Diseases. Inflamm Bowel Dis 2021; 28:819-829. [PMID: 34417815 PMCID: PMC9165557 DOI: 10.1093/ibd/izab187] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 02/19/2021] [Indexed: 12/14/2022]
Abstract
There is a rising interest in use of big data approaches to personalize treatment of inflammatory bowel diseases (IBDs) and to predict and prevent outcomes such as disease flares and therapeutic nonresponse. Machine learning (ML) provides an avenue to identify and quantify features across vast quantities of data to produce novel insights in disease management. In this review, we cover current approaches in ML-driven predictive outcomes modeling for IBD and relate how advances in other fields of medicine may be applied to improve future IBD predictive models. Numerous studies have incorporated clinical, laboratory, or omics data to predict significant outcomes in IBD, including hospitalizations, outpatient corticosteroid use, biologic response, and refractory disease after colectomy, among others, with considerable health care dollars saved as a result. Encouraging results in other fields of medicine support efforts to use ML image analysis-including analysis of histopathology, endoscopy, and radiology-to further advance outcome predictions in IBD. Though obstacles to clinical implementation include technical barriers, bias within data sets, and incongruence between limited data sets preventing model validation in larger cohorts, ML-predictive analytics have the potential to transform the clinical management of IBD. Future directions include the development of models that synthesize all aforementioned approaches to produce more robust predictive metrics.
Collapse
Affiliation(s)
- Aamir Javaid
- Division of Pediatric Gastroenterology and Hepatology, Department of Pediatrics, University of Virginia, Charlottesville, VA, USA
| | - Omer Shahab
- Division of Gastroenterology and Hepatology, Department of Medicine, Virginia Commonwealth University, Richmond, VA, USA
| | - William Adorno
- School of Data Science, University of Virginia, Charlottesville, VA, USA
| | - Philip Fernandes
- Division of Pediatric Gastroenterology and Hepatology, Department of Pediatrics, University of Virginia, Charlottesville, VA, USA
| | - Eve May
- Division of Gastroenterology and Hepatology, Department of Pediatrics, Children’s National Hospital, Washington, DC, USA
| | - Sana Syed
- Division of Pediatric Gastroenterology and Hepatology, Department of Pediatrics, University of Virginia, Charlottesville, VA, USA,School of Data Science, University of Virginia, Charlottesville, VA, USA,Address Correspondence to: Sana Syed, MD, MSCR, MSDS, Division of Pediatric Gastroenterology and Hepatology, Department of Pediatrics, University of Virginia, 409 Lane Rd, Room 2035B, Charlottesville, VA, 22908, USA ()
| |
Collapse
|
11
|
Scott IA, Abdel-Hafez A, Barras M, Canaris S. What is needed to mainstream artificial intelligence in health care? AUST HEALTH REV 2021; 45:591-596. [PMID: 34162464 DOI: 10.1071/ah21034] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/02/2021] [Accepted: 04/27/2021] [Indexed: 11/23/2022]
Abstract
Artificial intelligence (AI) has become a mainstream technology in many industries, but not yet in health care. Although basic research and commercial investment are burgeoning across various clinical disciplines, AI remains relatively non-existent in most healthcare organisations. This is despite hundreds of AI applications having passed proof-of-concept phase, and scores receiving regulatory approval overseas. AI has considerable potential to optimise multiple care processes, maximise workforce capacity, reduce waste and costs, and improve patient outcomes. The current obstacles to wider AI adoption in health care and the pre-requisites for its successful development, evaluation and implementation need to be defined.
Collapse
Affiliation(s)
- Ian A Scott
- Princess Alexandra Hospital, Ipswich Road, Brisbane, Qld, Australia
| | - Ahmad Abdel-Hafez
- Division of Clinical Informatics, Metro South Hospital and Health Service, 199 Ipswich Road, Brisbane, Qld, Australia
| | - Michael Barras
- Princess Alexandra Hospital, Ipswich Road, Brisbane, Qld, Australia
| | - Stephen Canaris
- Division of Clinical Informatics, Metro South Hospital and Health Service, 199 Ipswich Road, Brisbane, Qld, Australia
| |
Collapse
|
12
|
Chang KP, Lin SH, Chu YW. Artificial intelligence in gastrointestinal radiology: A review with special focus on recent development of magnetic resonance and computed tomography. Artif Intell Gastroenterol 2021; 2:27-41. [DOI: 10.35712/aig.v2.i2.27] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 01/27/2021] [Revised: 03/21/2021] [Accepted: 04/20/2021] [Indexed: 02/06/2023] Open
Abstract
Artificial intelligence (AI), particularly the deep learning technology, have been proven influential to radiology in the recent decade. Its ability in image classification, segmentation, detection and reconstruction tasks have substantially assisted diagnostic radiology, and has even been viewed as having the potential to perform better than radiologists in some tasks. Gastrointestinal radiology, an important subspecialty dealing with complex anatomy and various modalities including endoscopy, have especially attracted the attention of AI researchers and engineers worldwide. Consequently, recently many tools have been developed for lesion detection and image construction in gastrointestinal radiology, particularly in the fields for which public databases are available, such as diagnostic abdominal magnetic resonance imaging (MRI) and computed tomography (CT). This review will provide a framework for understanding recent advancements of AI in gastrointestinal radiology, with a special focus on hepatic and pancreatobiliary diagnostic radiology with MRI and CT. For fields where AI is less developed, this review will also explain the difficulty in AI model training and possible strategies to overcome the technical issues. The authors’ insights of possible future development will be addressed in the last section.
Collapse
Affiliation(s)
- Kai-Po Chang
- PhD Program in Medical Biotechnology, National Chung Hsing University, Taichung 40227, Taiwan
- Department of Pathology, China Medical University Hospital, Taichung 40447, Taiwan
| | - Shih-Huan Lin
- PhD Program in Medical Biotechnology, National Chung Hsing University, Taichung 40227, Taiwan
| | - Yen-Wei Chu
- PhD Program in Medical Biotechnology, National Chung Hsing University, Taichung 40227, Taiwan
- Institute of Genomics and Bioinformatics, National Chung Hsing University, Taichung 40227, Taiwan
- Institute of Molecular Biology, National Chung Hsing University, Taichung 40227, Taiwan
- Agricultural Biotechnology Center, National Chung Hsing University, Taichung 40227, Taiwan
- Biotechnology Center, National Chung Hsing University, Taichung 40227, Taiwan
- PhD Program in Translational Medicine, National Chung Hsing University, Taichung 40227, Taiwan
- Rong Hsing Research Center for Translational Medicine, Taichung 40227, Taiwan
| |
Collapse
|
13
|
Goyal S. An Overview of Current Trends, Techniques, Prospects, and Pitfalls of Artificial Intelligence in Breast Imaging. REPORTS IN MEDICAL IMAGING 2021. [DOI: 10.2147/rmi.s295205] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
|
14
|
Falconer N, Spinewine A, Doogue MP, Barras M. Identifying medication harm in hospitalised patients: a bimodal, targeted approach. Ther Adv Drug Saf 2020; 11:2042098620975516. [PMID: 33294155 PMCID: PMC7705802 DOI: 10.1177/2042098620975516] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/26/2022] Open
Affiliation(s)
- Nazanin Falconer
- Department of Pharmacy, Ground floor,
Princess Alexandra Hospital, Woolloongabba, QLD. Centre for
Health Services Research, Faculty of Medicine and School of
Pharmacy, The University of Queensland, Brisbane, QLD, 4102,
Australia
| | - Anne Spinewine
- Université catholique de Louvain,
Louvain Drug Research Institute, Brussels, Belgium
- Pharmacy Department, Université
catholique de Louvain, CHU UCL Namur, Yvoir, Belgium
| | - Matthew P. Doogue
- Department of Medicine, University of
Otago, Christchurch, New Zealand
- Department of Clinical Pharmacology,
Canterbury District Health Board, Christchurch, New
Zealand
| | - Michael Barras
- School of Pharmacy, The University of
Queensland, Brisbane, QLD, Australia
- Department of Pharmacy, Princess
Alexandra Hospital, Woollongabba, Brisbane, QLD, Australia
| |
Collapse
|
15
|
Kantidakis G, Putter H, Lancia C, Boer JD, Braat AE, Fiocco M. Survival prediction models since liver transplantation - comparisons between Cox models and machine learning techniques. BMC Med Res Methodol 2020; 20:277. [PMID: 33198650 PMCID: PMC7667810 DOI: 10.1186/s12874-020-01153-1] [Citation(s) in RCA: 20] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/11/2020] [Accepted: 10/26/2020] [Indexed: 01/29/2023] Open
Abstract
BACKGROUND Predicting survival of recipients after liver transplantation is regarded as one of the most important challenges in contemporary medicine. Hence, improving on current prediction models is of great interest.Nowadays, there is a strong discussion in the medical field about machine learning (ML) and whether it has greater potential than traditional regression models when dealing with complex data. Criticism to ML is related to unsuitable performance measures and lack of interpretability which is important for clinicians. METHODS In this paper, ML techniques such as random forests and neural networks are applied to large data of 62294 patients from the United States with 97 predictors selected on clinical/statistical grounds, over more than 600, to predict survival from transplantation. Of particular interest is also the identification of potential risk factors. A comparison is performed between 3 different Cox models (with all variables, backward selection and LASSO) and 3 machine learning techniques: a random survival forest and 2 partial logistic artificial neural networks (PLANNs). For PLANNs, novel extensions to their original specification are tested. Emphasis is given on the advantages and pitfalls of each method and on the interpretability of the ML techniques. RESULTS Well-established predictive measures are employed from the survival field (C-index, Brier score and Integrated Brier Score) and the strongest prognostic factors are identified for each model. Clinical endpoint is overall graft-survival defined as the time between transplantation and the date of graft-failure or death. The random survival forest shows slightly better predictive performance than Cox models based on the C-index. Neural networks show better performance than both Cox models and random survival forest based on the Integrated Brier Score at 10 years. CONCLUSION In this work, it is shown that machine learning techniques can be a useful tool for both prediction and interpretation in the survival context. From the ML techniques examined here, PLANN with 1 hidden layer predicts survival probabilities the most accurately, being as calibrated as the Cox model with all variables. TRIAL REGISTRATION Retrospective data were provided by the Scientific Registry of Transplant Recipients under Data Use Agreement number 9477 for analysis of risk factors after liver transplantation.
Collapse
Affiliation(s)
- Georgios Kantidakis
- Mathematical Institute (MI) Leiden University, Niels Bohrweg 1, Leiden, 2333 CA, the Netherlands. .,Department of Biomedical Data Sciences, Section Medical Statistics, Leiden University Medical Center (LUMC), Albinusdreef 2, Leiden, 2333 ZA, The Netherlands. .,Department of Statistics, European Organisation for Research and Treatment of Cancer (EORTC) Headquarters, Ave E. Mounier 83/11, Brussels, 1200, Belgium.
| | - Hein Putter
- Department of Biomedical Data Sciences, Section Medical Statistics, Leiden University Medical Center (LUMC), Albinusdreef 2, Leiden, 2333 ZA, The Netherlands
| | - Carlo Lancia
- Mathematical Institute (MI) Leiden University, Niels Bohrweg 1, Leiden, 2333 CA, the Netherlands
| | - Jacob de Boer
- Department of Surgery, Leiden University Medical Center (LUMC), Albinusdreef 2, Leiden, 2333 ZA, the Netherlands
| | - Andries E Braat
- Department of Surgery, Leiden University Medical Center (LUMC), Albinusdreef 2, Leiden, 2333 ZA, the Netherlands
| | - Marta Fiocco
- Mathematical Institute (MI) Leiden University, Niels Bohrweg 1, Leiden, 2333 CA, the Netherlands.,Department of Biomedical Data Sciences, Section Medical Statistics, Leiden University Medical Center (LUMC), Albinusdreef 2, Leiden, 2333 ZA, The Netherlands.,Trial and Data Center, Princess Máxima Center for pediatric oncology (PMC), Heidelberglaan 25, Utrecht, 3584 CS, the Netherlands
| |
Collapse
|
16
|
Affiliation(s)
- Ian A Scott
- Princess Alexandra Hospital, Brisbane, QLD.,University of Queensland, Brisbane, QLD
| | - Enrico W Coiera
- Centre for Health Informatics, Macquarie University, Sydney, NSW
| |
Collapse
|
17
|
Sung JJ, Stewart CL, Freedman B. Artificial intelligence in health care: preparing for the fifth Industrial Revolution. Med J Aust 2020; 213:253-255.e1. [PMID: 32892395 DOI: 10.5694/mja2.50755] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/16/2022]
Affiliation(s)
| | | | - Ben Freedman
- Heart Research Institute, University of Sydney, Sydney, NSW
| |
Collapse
|
18
|
Abstract
Purpose of Review Artificial intelligence (AI) offers huge potential in infection prevention and control (IPC). We explore its potential IPC benefits in epidemiology, laboratory infection diagnosis, and hand hygiene. Recent Findings AI has the potential to detect transmission events during outbreaks or predict high-risk patients, enabling development of tailored IPC interventions. AI offers opportunities to enhance diagnostics with objective pattern recognition, standardize the diagnosis of infections with IPC implications, and facilitate the dissemination of IPC expertise. AI hand hygiene applications can deliver behavior change, though it requires further evaluation in different clinical settings. However, staff can become dependent on automatic reminders, and performance returns to baseline if feedback is removed. Summary Advantages for IPC include speed, consistency, and capability of handling infinitely large datasets. However, many challenges remain; improving the availability of high-quality representative datasets and consideration of biases within preexisting databases are important challenges for future developments. AI in itself will not improve IPC; this requires culture and behavior change. Most studies to date assess performance retrospectively so there is a need for prospective evaluation in the real-life, often chaotic, clinical setting. Close collaboration with IPC experts to interpret outputs and ensure clinical relevance is essential.
Collapse
|