1
|
Hurvitz N, Ilan Y. The Constrained-Disorder Principle Assists in Overcoming Significant Challenges in Digital Health: Moving from "Nice to Have" to Mandatory Systems. Clin Pract 2023; 13:994-1014. [PMID: 37623270 PMCID: PMC10453547 DOI: 10.3390/clinpract13040089] [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: 07/19/2023] [Revised: 08/16/2023] [Accepted: 08/18/2023] [Indexed: 08/26/2023] Open
Abstract
The success of artificial intelligence depends on whether it can penetrate the boundaries of evidence-based medicine, the lack of policies, and the resistance of medical professionals to its use. The failure of digital health to meet expectations requires rethinking some of the challenges faced. We discuss some of the most significant challenges faced by patients, physicians, payers, pharmaceutical companies, and health systems in the digital world. The goal of healthcare systems is to improve outcomes. Assisting in diagnosing, collecting data, and simplifying processes is a "nice to have" tool, but it is not essential. Many of these systems have yet to be shown to improve outcomes. Current outcome-based expectations and economic constraints make "nice to have," "assists," and "ease processes" insufficient. Complex biological systems are defined by their inherent disorder, bounded by dynamic boundaries, as described by the constrained disorder principle (CDP). It provides a platform for correcting systems' malfunctions by regulating their degree of variability. A CDP-based second-generation artificial intelligence system provides solutions to some challenges digital health faces. Therapeutic interventions are held to improve outcomes with these systems. In addition to improving clinically meaningful endpoints, CDP-based second-generation algorithms ensure patient and physician engagement and reduce the health system's costs.
Collapse
Affiliation(s)
| | - Yaron Ilan
- Hadassah Medical Center, Department of Medicine, Faculty of Medicine, Hebrew University, POB 1200, Jerusalem IL91120, Israel;
| |
Collapse
|
2
|
Arumugam S, Ma J, Macar U, Han G, McAulay K, Ingram D, Ying A, Chellani HH, Chern T, Reilly K, Colburn DAM, Stanciu R, Duffy C, Williams A, Grys T, Chang SF, Sia SK. Rapidly adaptable automated interpretation of point-of-care COVID-19 diagnostics. COMMUNICATIONS MEDICINE 2023; 3:91. [PMID: 37353603 DOI: 10.1038/s43856-023-00312-x] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/24/2022] [Accepted: 06/01/2023] [Indexed: 06/25/2023] Open
Abstract
BACKGROUND Point-of-care diagnostic devices, such as lateral-flow assays, are becoming widely used by the public. However, efforts to ensure correct assay operation and result interpretation rely on hardware that cannot be easily scaled or image processing approaches requiring large training datasets, necessitating large numbers of tests and expert labeling with validated specimens for every new test kit format. METHODS We developed a software architecture called AutoAdapt POC that integrates automated membrane extraction, self-supervised learning, and few-shot learning to automate the interpretation of POC diagnostic tests using smartphone cameras in a scalable manner. A base model pre-trained on a single LFA kit is adapted to five different COVID-19 tests (three antigen, two antibody) using just 20 labeled images. RESULTS Here we show AutoAdapt POC to yield 99% to 100% accuracy over 726 tests (350 positive, 376 negative). In a COVID-19 drive-through study with 74 untrained users self-testing, 98% found image collection easy, and the rapidly adapted models achieved classification accuracies of 100% on both COVID-19 antigen and antibody test kits. Compared with traditional visual interpretation on 105 test kit results, the algorithm correctly identified 100% of images; without a false negative as interpreted by experts. Finally, compared to a traditional convolutional neural network trained on an HIV test kit, the algorithm showed high accuracy while requiring only 1/50th of the training images. CONCLUSIONS The study demonstrates how rapid domain adaptation in machine learning can provide quality assurance, linkage to care, and public health tracking for untrained users across diverse POC diagnostic tests.
Collapse
Affiliation(s)
- Siddarth Arumugam
- Department of Biomedical Engineering, Columbia University, New York, NY, 10027, USA
| | - Jiawei Ma
- Department of Computer Science, Columbia University, New York, NY, 10027, USA
| | - Uzay Macar
- Department of Computer Science, Columbia University, New York, NY, 10027, USA
| | - Guangxing Han
- Department of Electrical Engineering, Columbia University, New York, NY, 10027, USA
| | - Kathrine McAulay
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Phoenix, AZ, 85054, USA
| | | | - Alex Ying
- Department of Biomedical Engineering, Columbia University, New York, NY, 10027, USA
| | | | - Terry Chern
- Department of Biomedical Engineering, Columbia University, New York, NY, 10027, USA
| | - Kenta Reilly
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Phoenix, AZ, 85054, USA
| | - David A M Colburn
- Department of Biomedical Engineering, Columbia University, New York, NY, 10027, USA
| | - Robert Stanciu
- Department of Biomedical Engineering, Columbia University, New York, NY, 10027, USA
| | - Craig Duffy
- Safe Health Systems, Inc., Los Angeles, CA, 90036, USA
| | | | - Thomas Grys
- Department of Laboratory Medicine and Pathology, Mayo Clinic, Phoenix, AZ, 85054, USA
| | - Shih-Fu Chang
- Department of Computer Science, Columbia University, New York, NY, 10027, USA.
- Department of Electrical Engineering, Columbia University, New York, NY, 10027, USA.
| | - Samuel K Sia
- Department of Biomedical Engineering, Columbia University, New York, NY, 10027, USA.
| |
Collapse
|
3
|
Yang L, Wu J, Mo X, Chen Y, Huang S, Zhou L, Dai J, Xie L, Chen S, Shang H, Rao B, Weng B, Abulimiti A, Wu S, Xie X. Changes in Mobile Health Apps Usage Before and After the COVID-19 Outbreak in China: Semilongitudinal Survey. JMIR Public Health Surveill 2023; 9:e40552. [PMID: 36634256 PMCID: PMC9996426 DOI: 10.2196/40552] [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: 06/27/2022] [Revised: 10/26/2022] [Accepted: 01/12/2023] [Indexed: 01/14/2023] Open
Abstract
BACKGROUND Mobile health (mHealth) apps are rapidly emerging technologies in China due to strictly controlled medical needs during the COVID-19 pandemic while continuing essential services for chronic diseases. However, there have been no large-scale, systematic efforts to evaluate relevant apps. OBJECTIVE We aim to provide a landscape of mHealth apps in China by describing and comparing digital health concerns before and after the COVID-19 outbreak, including mHealth app data flow and user experience, and analyze the impact of COVID-19 on mHealth apps. METHODS We conducted a semilongitudinal survey of 1593 mHealth apps to study the app data flow and clarify usage changes and influencing factors. We selected mHealth apps in app markets, web pages from the Baidu search engine, the 2018 top 100 hospitals with internet hospitals, and online shopping sites with apps that connect to smart devices. For user experience, we recruited residents from a community in southeastern China from October 2019 to November 2019 (before the outbreak) and from June 2020 to August 2020 (after the outbreak) comparing the attention of the population to apps. We also examined associations between app characteristics, functions, and outcomes at specific quantiles of distribution in download changes using quantile regression models. RESULTS Rehabilitation medical support was the top-ranked functionality, with a median 1.44 million downloads per app prepandemic and a median 2.74 million downloads per app postpandemic. Among the top 10 functions postpandemic, 4 were related to maternal and child health: pregnancy preparation (ranked second; fold change 4.13), women's health (ranked fifth; fold change 5.16), pregnancy (ranked sixth; fold change 5.78), and parenting (ranked tenth; fold change 4.03). Quantile regression models showed that rehabilitation (P75, P90), pregnancy preparation (P90), bodybuilding (P50, P90), and vaccination (P75) were positively associated with an increase in downloads after the outbreak. In the user experience survey, the attention given to health information (prepandemic: 249/375, 66.4%; postpandemic: 146/178, 82.0%; P=.006) steadily increased after the outbreak. CONCLUSIONS mHealth apps are an effective health care approach gaining in popularity among the Chinese population following the COVID-19 outbreak. This research provides direction for subsequent mHealth app development and promotion in the postepidemic era, supporting medical model reformation in China as a reference, which may provide new avenues for designing and evaluating indirect public health interventions such as health education and health promotion.
Collapse
Affiliation(s)
- Le Yang
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Jiadong Wu
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Xiaoxiao Mo
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Yaqin Chen
- School of Nursing, Fujian Medical University, Fuzhou, China
| | - Shanshan Huang
- School of Nursing, Fujian Medical University, Fuzhou, China
| | - Linlin Zhou
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Jiaqi Dai
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Linna Xie
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Siyu Chen
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Hao Shang
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Beibei Rao
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Bingtao Weng
- School of Public Health, Fujian Medical University, Fuzhou, China
| | | | - Siying Wu
- School of Public Health, Fujian Medical University, Fuzhou, China
| | - Xiaoxu Xie
- School of Public Health, Fujian Medical University, Fuzhou, China
| |
Collapse
|
4
|
McLean E, Cornwell MA, Bender HA, Sacks-Zimmerman A, Mandelbaum S, Koay JM, Raja N, Kohn A, Meli G, Spat-Lemus J. Innovations in Neuropsychology: Future Applications in Neurosurgical Patient Care. World Neurosurg 2023; 170:286-295. [PMID: 36782427 DOI: 10.1016/j.wneu.2022.09.103] [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: 09/21/2022] [Accepted: 09/22/2022] [Indexed: 02/11/2023]
Abstract
Over the last century, collaboration between clinical neuropsychologists and neurosurgeons has advanced the state of the science in both disciplines. These advances have provided the field of neuropsychology with many opportunities for innovation in the care of patients prior to, during, and following neurosurgical intervention. Beyond giving a general overview of how present-day advances in technology are being applied in the practice of neuropsychology within a neurological surgery department, this article outlines new developments that are currently unfolding. Improvements in remote platform, computer interface, "real-time" analytics, mobile devices, and immersive virtual reality have the capacity to increase the customization, precision, and accessibility of neuropsychological services. In doing so, such innovations have the potential to improve outcomes and ameliorate health care disparities.
Collapse
Affiliation(s)
- Erin McLean
- Department of Psychology, Hofstra University, Hempstead, New York, USA; Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA
| | - Melinda A Cornwell
- Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA
| | - H Allison Bender
- Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA.
| | | | - Sarah Mandelbaum
- Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA; Department of Clinical Psychology with Health Emphasis, Ferkauf Graduate School of Psychology, Yeshiva University, Bronx, New York, USA
| | - Jun Min Koay
- Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA; Department of Psychiatry and Psychology, Mayo Clinic, Jacksonville, Florida, USA
| | - Noreen Raja
- Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA; Graduate School of Applied and Professional Psychology, Rutgers University, Piscataway, New Jersey, USA
| | - Aviva Kohn
- Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA; Department of Clinical Psychology with Health Emphasis, Ferkauf Graduate School of Psychology, Yeshiva University, Bronx, New York, USA
| | - Gabrielle Meli
- Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA; Department of Human Ecology, Cornell University, Ithaca, New York, USA
| | - Jessica Spat-Lemus
- Department of Neurological Surgery, Weill Cornell Medicine, New York, New York, USA
| |
Collapse
|
5
|
Falling down the digital divide: A cautionary tale. Parkinsonism Relat Disord 2021; 93:33-34. [PMID: 34781236 PMCID: PMC8563503 DOI: 10.1016/j.parkreldis.2021.10.032] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 09/01/2021] [Revised: 10/20/2021] [Accepted: 10/31/2021] [Indexed: 11/21/2022]
Abstract
The disruptions of the coronavirus pandemic have enabled new opportunities for telehealth expansion within movement disorders. However, inadequate internet infrastructure has, unfortunately, led to fragmented implementation and may worsen disparities in some areas. In this Correspondence, we report on geographic and racial/ethnic disparities in access to our center's comprehensive care clinic for people with Parkinson's disease. While both in-person and virtual versions of the clinic enjoyed high patient satisfaction, we discovered that participation by Black/African-American individuals was cut in half when we shifted to a virtual delivery format in April 2020. We outline potential barriers in access using a socio-ecological model.
Collapse
|
6
|
Marwaha JS, Kvedar JC. Cultural adaptation: a framework for addressing an often-overlooked dimension of digital health accessibility. NPJ Digit Med 2021; 4:143. [PMID: 34599270 PMCID: PMC8486834 DOI: 10.1038/s41746-021-00516-2] [Citation(s) in RCA: 9] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2021] [Accepted: 09/13/2021] [Indexed: 12/13/2022] Open
Abstract
Relatively little is known about how to make digital health tools accessible to different populations from a cultural standpoint. Alignment with cultural values and communication styles may affect these tools’ ability to diagnose and treat various conditions. In this Editorial, we highlight the findings of recent work to make digital tools for mental health more culturally accessible, and propose ways to advance this area of study.
Collapse
Affiliation(s)
- Jayson S Marwaha
- Beth Israel Deaconess Medical Center, Boston, MA, USA. .,Harvard Medical School, Boston, MA, USA.
| | - Joseph C Kvedar
- Harvard Medical School, Boston, MA, USA.,Mass General Brigham, Boston, MA, USA
| |
Collapse
|