1
|
Bays HE, Fitch A, Cuda S, Gonsahn-Bollie S, Rickey E, Hablutzel J, Coy R, Censani M. Artificial intelligence and obesity management: An Obesity Medicine Association (OMA) Clinical Practice Statement (CPS) 2023. OBESITY PILLARS (ONLINE) 2023; 6:100065. [PMID: 37990659 PMCID: PMC10662105 DOI: 10.1016/j.obpill.2023.100065] [Citation(s) in RCA: 9] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 04/18/2023] [Accepted: 04/18/2023] [Indexed: 11/23/2023]
Abstract
Background This Obesity Medicine Association (OMA) Clinical Practice Statement (CPS) provides clinicians an overview of Artificial Intelligence, focused on the management of patients with obesity. Methods The perspectives of the authors were augmented by scientific support from published citations and integrated with information derived from search engines (i.e., Chrome by Google, Inc) and chatbots (i.e., Chat Generative Pretrained Transformer or Chat GPT). Results Artificial Intelligence (AI) is the technologic acquisition of knowledge and skill by a nonhuman device, that after being initially programmed, has varying degrees of operations autonomous from direct human control, and that performs adaptive output tasks based upon data input learnings. AI has applications regarding medical research, medical practice, and applications relevant to the management of patients with obesity. Chatbots may be useful to obesity medicine clinicians as a source of clinical/scientific information, helpful in writings and publications, as well as beneficial in drafting office or institutional Policies and Procedures and Standard Operating Procedures. AI may facilitate interactive programming related to analyses of body composition imaging, behavior coaching, personal nutritional intervention & physical activity recommendations, predictive modeling to identify patients at risk for obesity-related complications, and aid clinicians in precision medicine. AI can enhance educational programming, such as personalized learning, virtual reality, and intelligent tutoring systems. AI may help augment in-person office operations and telemedicine (e.g., scheduling and remote monitoring of patients). Finally, AI may help identify patterns in datasets related to a medical practice or institution that may be used to assess population health and value-based care delivery (i.e., analytics related to electronic health records). Conclusions AI is contributing to both an evolution and revolution in medical care, including the management of patients with obesity. Challenges of Artificial Intelligence include ethical and legal concerns (e.g., privacy and security), accuracy and reliability, and the potential perpetuation of pervasive systemic biases.
Collapse
Affiliation(s)
- Harold Edward Bays
- Louisville Metabolic and Atherosclerosis Research Center, University of Louisville School of Medicine, 3288 Illinois Avenue, Louisville, KY, 40213, USA
| | | | - Suzanne Cuda
- Alamo City Healthy Kids and Families, 1919 Oakwell Farms Parkway Ste 145, San Antonio, TX, 78218, USA
| | - Sylvia Gonsahn-Bollie
- Embrace You Weight & Wellness, 8705 Colesville Rd Suite 103, Silver Spring, MD, 10, USA
| | - Elario Rickey
- Obesity Medicine Association, 7173 S. Havana St. #600-130, Centennial, CO, 80112, USA
| | - Joan Hablutzel
- Obesity Medicine Association, 7173 S. Havana St. #600-130, Centennial, CO, 80112, USA
| | - Rachel Coy
- Obesity Medicine Association, 7173 S. Havana St. #600-130, Centennial, CO, 80112, USA
| | - Marisa Censani
- Division of Pediatric Endocrinology, Department of Pediatrics, New York Presbyterian Hospital, Weill Cornell Medicine, 525 East 68th Street, Box 103, New York, NY, 10021, USA
| |
Collapse
|
2
|
Diaz C, Caillaud C, Yacef K. Mining Sensor Data to Assess Changes in Physical Activity Behaviors in Health Interventions: Systematic Review. JMIR Med Inform 2023; 11:e41153. [PMID: 36877559 PMCID: PMC10028506 DOI: 10.2196/41153] [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: 07/17/2022] [Revised: 11/25/2022] [Accepted: 11/27/2022] [Indexed: 03/07/2023] Open
Abstract
BACKGROUND Sensors are increasingly used in health interventions to unobtrusively and continuously capture participants' physical activity in free-living conditions. The rich granularity of sensor data offers great potential for analyzing patterns and changes in physical activity behaviors. The use of specialized machine learning and data mining techniques to detect, extract, and analyze these patterns has increased, helping to better understand how participants' physical activity evolves. OBJECTIVE The aim of this systematic review was to identify and present the various data mining techniques employed to analyze changes in physical activity behaviors from sensors-derived data in health education and health promotion intervention studies. We addressed two main research questions: (1) What are the current techniques used for mining physical activity sensor data to detect behavior changes in health education or health promotion contexts? (2) What are the challenges and opportunities in mining physical activity sensor data for detecting physical activity behavior changes? METHODS The systematic review was performed in May 2021 using the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines. We queried the Association for Computing Machinery (ACM), IEEE Xplore, ProQuest, Scopus, Web of Science, Education Resources Information Center (ERIC), and Springer literature databases for peer-reviewed references related to wearable machine learning to detect physical activity changes in health education. A total of 4388 references were initially retrieved from the databases. After removing duplicates and screening titles and abstracts, 285 references were subjected to full-text review, resulting in 19 articles included for analysis. RESULTS All studies used accelerometers, sometimes in combination with another sensor (37%). Data were collected over a period ranging from 4 days to 1 year (median 10 weeks) from a cohort size ranging between 10 and 11615 (median 74). Data preprocessing was mainly carried out using proprietary software, generally resulting in step counts and time spent in physical activity aggregated predominantly at the daily or minute level. The main features used as input for the data mining models were descriptive statistics of the preprocessed data. The most common data mining methods were classifiers, clusters, and decision-making algorithms, and these focused on personalization (58%) and analysis of physical activity behaviors (42%). CONCLUSIONS Mining sensor data offers great opportunities to analyze physical activity behavior changes, build models to better detect and interpret behavior changes, and allow for personalized feedback and support for participants, especially where larger sample sizes and longer recording times are available. Exploring different data aggregation levels can help detect subtle and sustained behavior changes. However, the literature suggests that there is still work remaining to improve the transparency, explicitness, and standardization of the data preprocessing and mining processes to establish best practices and make the detection methods easier to understand, scrutinize, and reproduce.
Collapse
Affiliation(s)
- Claudio Diaz
- School of Computer Science, The University of Sydney, Sydney, Australia
| | - Corinne Caillaud
- Charles Perkins Centre, School of Medical Sciences, The University of Sydney, Sydney, Australia
| | - Kalina Yacef
- School of Computer Science, The University of Sydney, Sydney, Australia
| |
Collapse
|
3
|
Kaywan P, Ahmed K, Ibaida A, Miao Y, Gu B. Early detection of depression using a conversational AI bot: A non-clinical trial. PLoS One 2023; 18:e0279743. [PMID: 36735701 PMCID: PMC9897524 DOI: 10.1371/journal.pone.0279743] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/10/2022] [Accepted: 11/24/2022] [Indexed: 02/04/2023] Open
Abstract
BACKGROUND Artificial intelligence (AI) has gained momentum in behavioural health interventions in recent years. However, a limited number of studies use or apply such methodologies in the early detection of depression. A large population needing psychological-intervention is left unidentified due to barriers such as cost, location, stigma and a global shortage of health workers. Therefore, it is essential to develop a mass screening integrative approach that can identify people with depression at its early stage to avoid a potential crisis. OBJECTIVES This study aims to understand the feasibility and efficacy of using AI-enabled chatbots in the early detection of depression. METHODS We use Dialogflow as a conversation interface to build a Depression Analysisn (DEPRA) chatbot. A structured and authoritative early detection depression interview guide, which contains 27 questions combining the structured interview guide for the Hamilton Depression Scale (SIGH-D) and the inventory of depressive symptomatology (IDS-C), underpins the design of the conversation flow. To attain better accuracy and a wide variety of responses, we train Dialogflow with the utterances collected from a focus group of 10 people. The occupation of the focus group members included academics and HDR candidates who are conscious, vigilant and have a clear understanding of the questions. In addition, DEPRA is integrated with a social media platform to provide practical access to all the participants. For the non-clinical trial, we recruited 50 participants aged between 18 and 80 from across Australia. To evaluate the practicability and performance of DEPRA, we also asked participants to submit a user satisfaction survey at the end of the conversation. RESULTS A sample of 50 participants, with an average age of 34.7 years, completed this non-clinical trial. More than half of the participants (54%) are male and the major ethnicities are Asian (63%), Middle Eastern (25%), and others 12%. The first group comprises professional academic staff and HDR candidates, the second and third groups comprise relatives, friends, and volunteers who were recruited via social media promotions. DEPRA uses two scientific scoring systems, QIDS-SR and IDS-SR to verify the results of early depression detection. As the results indicate, both scoring systems return a similar outcome with slight variations for different depression levels. According to IDS-SR, 30% of participants were healthy, 14% mild, 22% moderate, 14% severe, and 20% very severe. QIDS-SR suggests 32% were healthy, 18% mild, 10% moderate, 18% severe, and 22% very severe. Furthermore, the overall satisfaction rate of using DEPRA was 79% indicating that the participants had a high rate of user satisfaction and engagement. CONCLUSION DEPRA shows promises as a feasible option for developing a mass screening integrated approach for early detection of depression. Although the chatbot is not intended to replace the functionality of mental health professionals, it does show promise as a means of assisting with automation and concealed communication with verified scoring systems.
Collapse
Affiliation(s)
- Payam Kaywan
- Intelligent Technology Innovation Lab, Victoria University, Melbourne, Victoria, Australia
| | - Khandakar Ahmed
- Intelligent Technology Innovation Lab, Victoria University, Melbourne, Victoria, Australia
- * E-mail:
| | - Ayman Ibaida
- Intelligent Technology Innovation Lab, Victoria University, Melbourne, Victoria, Australia
| | - Yuan Miao
- Intelligent Technology Innovation Lab, Victoria University, Melbourne, Victoria, Australia
| | - Bruce Gu
- Intelligent Technology Innovation Lab, Victoria University, Melbourne, Victoria, Australia
| |
Collapse
|
4
|
Albers N, Neerincx MA, Brinkman WP. Addressing people's current and future states in a reinforcement learning algorithm for persuading to quit smoking and to be physically active. PLoS One 2022; 17:e0277295. [PMID: 36454782 PMCID: PMC9714722 DOI: 10.1371/journal.pone.0277295] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/31/2022] [Accepted: 10/25/2022] [Indexed: 12/02/2022] Open
Abstract
Behavior change applications often assign their users activities such as tracking the number of smoked cigarettes or planning a running route. To help a user complete these activities, an application can persuade them in many ways. For example, it may help the user create a plan or mention the experience of peers. Intuitively, the application should thereby pick the message that is most likely to be motivating. In the simplest case, this could be the message that has been most effective in the past. However, one could consider several other elements in an algorithm to choose a message. Possible elements include the user's current state (e.g., self-efficacy), the user's future state after reading a message, and the user's similarity to the users on which data has been gathered. To test the added value of subsequently incorporating these elements into an algorithm that selects persuasive messages, we conducted an experiment in which more than 500 people in four conditions interacted with a text-based virtual coach. The experiment consisted of five sessions, in each of which participants were suggested a preparatory activity for quitting smoking or increasing physical activity together with a persuasive message. Our findings suggest that adding more elements to the algorithm is effective, especially in later sessions and for people who thought the activities were useful. Moreover, while we found some support for transferring knowledge between the two activity types, there was rather low agreement between the optimal policies computed separately for the two activity types. This suggests limited policy generalizability between activities for quitting smoking and those for increasing physical activity. We see our results as supporting the idea of constructing more complex persuasion algorithms. Our dataset on 2,366 persuasive messages sent to 671 people is published together with this article for researchers to build on our algorithm.
Collapse
Affiliation(s)
- Nele Albers
- Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands
- * E-mail: E-mail:
| | - Mark A. Neerincx
- Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands
- Department of Perceptual and Cognitive Systems, Nederlandse Organisatie voor Toegepast Natuurwetenschappelijk Onderzoek (TNO), Soesterberg, The Netherlands
| | - Willem-Paul Brinkman
- Department of Intelligent Systems, Delft University of Technology, Delft, The Netherlands
| |
Collapse
|
5
|
Diaz C, Caillaud C, Yacef K. Unsupervised Early Detection of Physical Activity Behaviour Changes from Wearable Accelerometer Data. SENSORS (BASEL, SWITZERLAND) 2022; 22:s22218255. [PMID: 36365953 PMCID: PMC9658769 DOI: 10.3390/s22218255] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/20/2022] [Revised: 10/20/2022] [Accepted: 10/24/2022] [Indexed: 05/27/2023]
Abstract
Wearable accelerometers record physical activity with high resolution, potentially capturing the rich details of behaviour changes and habits. Detecting these changes as they emerge is valuable information for any strategy that promotes physical activity and teaches healthy behaviours or habits. Indeed, this offers the opportunity to provide timely feedback and to tailor programmes to each participant's needs, thus helping to promote the adherence to and the effectiveness of the intervention. This article presents and illustrates U-BEHAVED, an unsupervised algorithm that periodically scans step data streamed from activity trackers to detect physical activity behaviour changes to assess whether they may become habitual patterns. Using rolling time windows, current behaviours are compared with recent previous ones, identifying any significant change. If sustained over time, these new behaviours are classified as potentially new habits. We validated this detection algorithm using a physical activity tracker step dataset (N = 12,798) from 79 users. The algorithm detected 80% of behaviour changes of at least 400 steps within the same hour in users with low variability in physical activity, and of 1600 steps in those with high variability. Based on a threshold cadence of approximately 100 steps per minute for standard walking pace, this number of steps would suggest approximately 4 and 16 min of physical activity at moderate-to-vigorous intensity, respectively. The detection rate for new habits was 80% with a minimum threshold of 500 or 1600 steps within the same hour in users with low or high variability, respectively.
Collapse
Affiliation(s)
- Claudio Diaz
- School of Computer Science, The University of Sydney, Sydney, NSW 2006, Australia
| | - Corinne Caillaud
- Biomedical Informatics and Digital Health, School of Medical Sciences, Faculty of Medicine and Health, The University of Sydney, Sydney, NSW 2006, Australia
- Charles Perkins Centre, The University of Sydney, Sydney, NSW 2006, Australia
| | - Kalina Yacef
- School of Computer Science, The University of Sydney, Sydney, NSW 2006, Australia
| |
Collapse
|
6
|
Trella AL, Zhang KW, Nahum-Shani I, Shetty V, Doshi-Velez F, Murphy SA. Designing Reinforcement Learning Algorithms for Digital Interventions: Pre-Implementation Guidelines. ALGORITHMS 2022; 15:255. [PMID: 36713810 PMCID: PMC9881427 DOI: 10.3390/a15080255] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 02/02/2023]
Abstract
Online reinforcement learning (RL) algorithms are increasingly used to personalize digital interventions in the fields of mobile health and online education. Common challenges in designing and testing an RL algorithm in these settings include ensuring the RL algorithm can learn and run stably under real-time constraints, and accounting for the complexity of the environment, e.g., a lack of accurate mechanistic models for the user dynamics. To guide how one can tackle these challenges, we extend the PCS (predictability, computability, stability) framework, a data science framework that incorporates best practices from machine learning and statistics in supervised learning to the design of RL algorithms for the digital interventions setting. Furthermore, we provide guidelines on how to design simulation environments, a crucial tool for evaluating RL candidate algorithms using the PCS framework. We show how we used the PCS framework to design an RL algorithm for Oralytics, a mobile health study aiming to improve users' tooth-brushing behaviors through the personalized delivery of intervention messages. Oralytics will go into the field in late 2022.
Collapse
Affiliation(s)
- Anna L. Trella
- School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02420, USA
- Correspondence:
| | - Kelly W. Zhang
- School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02420, USA
| | - Inbal Nahum-Shani
- Institute for Social Research, University of Michigan, Ann Arbor, MI 48109, USA
| | - Vivek Shetty
- Schools of Dentistry & Engineering, University of California, Los Angeles, CA 90095, USA
| | - Finale Doshi-Velez
- School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02420, USA
| | - Susan A. Murphy
- School of Engineering and Applied Sciences, Harvard University, Cambridge, MA 02420, USA
| |
Collapse
|
7
|
Bertsimas D, Klasnja P, Murphy S, Na L. Data-driven Interpretable Policy Construction for Personalized Mobile Health. 2022 IEEE INTERNATIONAL CONFERENCE ON DIGITAL HEALTH (IEEE ICDH 2022) : PROCEEDINGS : HYBRID CONFERENCE, BARCELONA, SPAIN, 11-15 JULY 2022. INTERNATIONAL CONFERENCE ON DIGITAL HEALTH (2022 : BARCELONA, SPAIN; ONLINE) 2022; 2022:13-22. [PMID: 37965645 PMCID: PMC10645432 DOI: 10.1109/icdh55609.2022.00010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/16/2023]
Abstract
To promote healthy behaviors, many mobile health applications provide message-based interventions, such as tips, motivational messages, or suggestions for healthy activities. Ideally, the intervention policies should be carefully designed so that users obtain the benefits without being overwhelmed by overly frequent messages. As part of the HeartSteps physical-activity intervention, users receive messages intended to disrupt sedentary behavior. HeartSteps uses an algorithm to uniformly spread out the daily message budget over time, but does not attempt to maximize treatment effects. This limitation motivates constructing a policy to optimize the message delivery decisions for more effective treatments. Moreover, the learned policy needs to be interpretable to enable behavioral scientists to examine it and to inform future theorizing. We address this problem by learning an effective and interpretable policy that reduces sedentary behavior. We propose Optimal Policy Trees + (OPT+), an innovative batch off-policy learning method, that combines a personalized threshold learning and an extension of Optimal Policy Trees under a budget-constrained setting. We implement and test the method using data collected in HeartSteps V2/V3. Computational results demonstrate a significant reduction in sedentary behavior with a lower delivery budget. OPT+ produces a highly interpretable and stable output decision tree thus enabling theoretical insights to guide future research.
Collapse
Affiliation(s)
- Dimitris Bertsimas
- Sloan School of Management Massachusetts Institute of Technology Cambridge, USA
| | | | - Susan Murphy
- Department of Statistics Harvard University Cambridge, USA
| | - Liangyuan Na
- Operations Research Center Massachusetts Institute of Technology Cambridge, USA
| |
Collapse
|
8
|
Kaloiya GS, Kaur T, Ranjan P, Chopra S, Sarkar S, Kumari A, Bhatia H. Counselling and Behaviour Modification Techniques for the Management of Obesity in Postpartum and Midlife Women: A Practical Guide for Clinicians. J Obstet Gynaecol India 2022; 72:134-140. [PMID: 35492859 PMCID: PMC9008080 DOI: 10.1007/s13224-022-01652-9] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2021] [Accepted: 03/14/2022] [Indexed: 10/18/2022] Open
Abstract
Behaviour change is the basic foundation in the management of obesity. Such behaviour change is difficult to achieve due to several psychosocial and behavioural barriers that often remain unidentified and unaddressed in a weight management programme. This is even more challenging in postpartum and midlife women because of several biopsychosocial factors. The non-availability of psychologists or trained healthcare counsellors further complicates the attainment of behavioural changes. Therefore, clinicians, who are often the first point of contact for treating these population groups, are hamstrung by the lack of a multidisciplinary approach for weight reduction. Some of the common psychological, social and behavioural barriers have been identified in this article, and evidence-based techniques such as goal setting, stimulus control and cognitive restructuring are presented in a step-wise approach, to help clinicians cater to these population groups in a holistic manner.
Collapse
|
9
|
Wang S, Zhang C, Kröse B, van Hoof H. Optimizing Adaptive Notifications in Mobile Health Interventions Systems: Reinforcement Learning from a Data-driven Behavioral Simulator. J Med Syst 2021; 45:102. [PMID: 34664120 PMCID: PMC8523513 DOI: 10.1007/s10916-021-01773-0] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/04/2021] [Accepted: 09/20/2021] [Indexed: 11/19/2022]
Abstract
Mobile health (mHealth) intervention systems can employ adaptive strategies to interact with users. Instead of designing such complex strategies manually, reinforcement learning (RL) can be used to adaptively optimize intervention strategies concerning the user’s context. In this paper, we focus on the issue of overwhelming interactions when learning a good adaptive strategy for the user in RL-based mHealth intervention agents. We present a data-driven approach integrating psychological insights and knowledge of historical data. It allows RL agents to optimize the strategy of delivering context-aware notifications from empirical data when counterfactual information (user responses when receiving notifications) is missing. Our approach also considers a constraint on the frequency of notifications, which reduces the interaction burden for users. We evaluated our approach in several simulation scenarios using real large-scale running data. The results indicate that our RL agent can deliver notifications in a manner that realizes a higher behavioral impact than context-blind strategies.
Collapse
Affiliation(s)
- Shihan Wang
- Informatics Institute, University of Amsterdam, Amsterdam, Netherlands. .,Information and Computing Sciences, Utrecht University, Utrecht, Netherlands.
| | - Chao Zhang
- Department of Psychology, Utrecht University, Utrecht, Netherlands.,Human-Technology Interaction, Eindhoven University of Technology, Eindhoven, Netherlands
| | - Ben Kröse
- Informatics Institute, University of Amsterdam, Amsterdam, Netherlands.,Digital Life, Amsterdam University of Applied Sciences, Amsterdam, Netherlands
| | - Herke van Hoof
- Informatics Institute, University of Amsterdam, Amsterdam, Netherlands
| |
Collapse
|
10
|
Tomkins S, Liao P, Klasnja P, Murphy S. IntelligentPooling: Practical Thompson Sampling for mHealth. Mach Learn 2021; 110:2685-2727. [PMID: 34621105 DOI: 10.1007/s10994-021-05995-8] [Citation(s) in RCA: 2] [Impact Index Per Article: 0.7] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/25/2022]
Abstract
In mobile health (mHealth) smart devices deliver behavioral treatments repeatedly over time to a user with the goal of helping the user adopt and maintain healthy behaviors. Reinforcement learning appears ideal for learning how to optimally make these sequential treatment decisions. However, significant challenges must be overcome before reinforcement learning can be effectively deployed in a mobile healthcare setting. In this work we are concerned with the following challenges: 1) individuals who are in the same context can exhibit differential response to treatments 2) only a limited amount of data is available for learning on any one individual, and 3) non-stationary responses to treatment. To address these challenges we generalize Thompson-Sampling bandit algorithms to develop IntelligentPooling. IntelligentPooling learns personalized treatment policies thus addressing challenge one. To address the second challenge, IntelligentPooling updates each user's degree of personalization while making use of available data on other users to speed up learning. Lastly, IntelligentPooling allows responsivity to vary as a function of a user's time since beginning treatment, thus addressing challenge three.
Collapse
|
11
|
Job JR, Eakin EG, Reeves MM, Fjeldsoe BS. Evaluation of the Healthy Living after Cancer text message-delivered, extended contact intervention using the RE-AIM framework. BMC Cancer 2021; 21:1081. [PMID: 34620115 PMCID: PMC8496009 DOI: 10.1186/s12885-021-08806-4] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/22/2021] [Accepted: 09/20/2021] [Indexed: 12/04/2022] Open
Abstract
Background Text message-delivered interventions have potential to prevent weight regain and maintain diet and physical activity behaviours through extending contact with participants following initial weight loss, lifestyle interventions. Using the RE-AIM Framework, this study evaluated the adoption, reach, implementation, effectiveness, and maintenance of an extended contact text-message intervention following the Healthy Living after Cancer (HLaC) program. HLaC was a 6-month, telephone-delivered intervention targeting healthy diet, physical activity and weight loss for adult cancer survivors, offered by Cancer Councils (CCs) in Australia. Methods HLaC completers (n = 182) were offered extended contact via text messages for 6-months (HLaC+Txt). Text message content/frequency was individually tailored to participant’s preferences, ascertained through two telephone-tailoring interviews with CC staff. Adoption (HLaC+Txt uptake among eligible CCs), reach (uptake by HLaC completers) and implementation (intervention cost/length; text dose) were assessed. The effectiveness of extended contact relative to historic controls was quantified by pre-to-post HLaC+Txt changes in self-reported: weight, moderate-vigorous physical activity (MVPA), fruit and vegetable intake, fat and fibre behaviour. Maintenance, following 6-months of noncontact for the intervention cohort, was assessed for these same variables. Semi-structured interviews with CC staff and participants contextualised outcomes. Results HLaC+Txt was adopted by all four CCs who had delivered HLaC. In total, 115 participants commenced HLaC+Txt, with reach ranging across CCs from 47 to 80% of eligible participants. The mean number of weeks participants received the text message intervention ranged across CCs from 18.5–22.2 weeks. Participants received (median, 25th,75th percentile) 83 (48, 119) texts, ranging across CCs from 40 to 112. The total cost of HLaC+Txt delivery was on average $AUD85.00/participant. No meaningful (p < 0.05) differences in self-reported outcomes were seen between HLaC+Txt and control cohorts. After 6-months no contact the intervention cohort had maintained weight, fruit intake, fat and fibre index scores relative to end of HLaC+Txt outcomes. Participants/CC staff perceived an important intervention component was maintaining accountability. Conclusions While feasible to implement, HLaC+Txt was not effective in the short term. However, intervention effects during the non-contact period suggest the program supports longer term maintenance of weight and diet behaviour. Intervention delivery in this real-world context highlighted key considerations for future implementation. Trial registration Australian and New Zealand Clinical Trials Registry (ANZCTR) - ACTRN12615000882527 (registered on 24/08/2015). Supplementary Information The online version contains supplementary material available at 10.1186/s12885-021-08806-4.
Collapse
Affiliation(s)
- Jennifer R Job
- Faculty of Medicine, School of Public Health, The University of Queensland, Brisbane, Australia. .,CHSRI, The University of Queensland, RBWH, Level 8, Health Sciences Building, Herston, Q 4029, Australia.
| | - Elizabeth G Eakin
- Faculty of Medicine, School of Public Health, The University of Queensland, Brisbane, Australia
| | - Marina M Reeves
- Faculty of Medicine, School of Public Health, The University of Queensland, Brisbane, Australia
| | - Brianna S Fjeldsoe
- Faculty of Medicine, School of Public Health, The University of Queensland, Brisbane, Australia
| |
Collapse
|
12
|
Sun X, Bee YM, Lam SW, Liu Z, Zhao W, Chia SY, Abdul Kadir H, Wu JT, Ang BY, Liu N, Lei Z, Xu Z, Zhao T, Hu G, Xie G. Effective Treatment Recommendations for Type 2 Diabetes Management Using Reinforcement Learning: Treatment Recommendation Model Development and Validation. J Med Internet Res 2021; 23:e27858. [PMID: 34292166 PMCID: PMC8367185 DOI: 10.2196/27858] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/09/2021] [Revised: 03/30/2021] [Accepted: 05/06/2021] [Indexed: 01/26/2023] Open
Abstract
Background Type 2 diabetes mellitus (T2DM) and its related complications represent a growing economic burden for many countries and health systems. Diabetes complications can be prevented through better disease control, but there is a large gap between the recommended treatment and the treatment that patients actually receive. The treatment of T2DM can be challenging because of different comprehensive therapeutic targets and individual variability of the patients, leading to the need for precise, personalized treatment. Objective The aim of this study was to develop treatment recommendation models for T2DM based on deep reinforcement learning. A retrospective analysis was then performed to evaluate the reliability and effectiveness of the models. Methods The data used in our study were collected from the Singapore Health Services Diabetes Registry, encompassing 189,520 patients with T2DM, including 6,407,958 outpatient visits from 2013 to 2018. The treatment recommendation model was built based on 80% of the dataset and its effectiveness was evaluated with the remaining 20% of data. Three treatment recommendation models were developed for antiglycemic, antihypertensive, and lipid-lowering treatments by combining a knowledge-driven model and a data-driven model. The knowledge-driven model, based on clinical guidelines and expert experiences, was first applied to select the candidate medications. The data-driven model, based on deep reinforcement learning, was used to rank the candidates according to the expected clinical outcomes. To evaluate the models, short-term outcomes were compared between the model-concordant treatments and the model-nonconcordant treatments with confounder adjustment by stratification, propensity score weighting, and multivariate regression. For long-term outcomes, model-concordant rates were included as independent variables to evaluate if the combined antiglycemic, antihypertensive, and lipid-lowering treatments had a positive impact on reduction of long-term complication occurrence or death at the patient level via multivariate logistic regression. Results The test data consisted of 36,993 patients for evaluating the effectiveness of the three treatment recommendation models. In 43.3% of patient visits, the antiglycemic medications recommended by the model were concordant with the actual prescriptions of the physicians. The concordant rates for antihypertensive medications and lipid-lowering medications were 51.3% and 58.9%, respectively. The evaluation results also showed that model-concordant treatments were associated with better glycemic control (odds ratio [OR] 1.73, 95% CI 1.69-1.76), blood pressure control (OR 1.26, 95% CI, 1.23-1.29), and blood lipids control (OR 1.28, 95% CI 1.22-1.35). We also found that patients with more model-concordant treatments were associated with a lower risk of diabetes complications (including 3 macrovascular and 2 microvascular complications) and death, suggesting that the models have the potential of achieving better outcomes in the long term. Conclusions Comprehensive management by combining knowledge-driven and data-driven models has good potential to help physicians improve the clinical outcomes of patients with T2DM; achieving good control on blood glucose, blood pressure, and blood lipids; and reducing the risk of diabetes complications in the long term.
Collapse
Affiliation(s)
- Xingzhi Sun
- Ping An Healthcare Technology, Beijing, China
| | - Yong Mong Bee
- Department of Endocrinology, Singapore General Hospital, Singapore, Singapore.,SingHealth Duke-NUS Diabetes Centre, Singapore Health Services, Singapore, Singapore
| | - Shao Wei Lam
- Health Services Research Centre, Singapore Health Services, Singapore, Singapore.,Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
| | - Zhuo Liu
- Ping An Healthcare Technology, Beijing, China
| | - Wei Zhao
- Ping An Healthcare Technology, Beijing, China
| | - Sing Yi Chia
- Health Services Research Unit, Singapore General Hospital, Singapore, Singapore
| | - Hanis Abdul Kadir
- Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore.,Health Services Research Unit, Singapore General Hospital, Singapore, Singapore
| | - Jun Tian Wu
- Health Services Research Centre, Singapore Health Services, Singapore, Singapore
| | - Boon Yew Ang
- Health Services Research Centre, Singapore Health Services, Singapore, Singapore
| | - Nan Liu
- Health Services Research Centre, Singapore Health Services, Singapore, Singapore.,Health Services and Systems Research, Duke-NUS Medical School, Singapore, Singapore
| | - Zuo Lei
- Ping An Healthcare Technology, Beijing, China
| | - Zhuoyang Xu
- Ping An Healthcare Technology, Beijing, China
| | | | - Gang Hu
- Ping An Healthcare Technology, Beijing, China
| | - Guotong Xie
- Ping An Healthcare Technology, Beijing, China.,Ping An Healthcare and Technology Co, Ltd, Shanghai, China.,Ping An International Smart City Technology Co, Ltd, Shenzhen, China
| |
Collapse
|
13
|
Wang S, Sporrel K, van Hoof H, Simons M, de Boer RDD, Ettema D, Nibbeling N, Deutekom M, Kröse B. Reinforcement Learning to Send Reminders at Right Moments in Smartphone Exercise Application: A Feasibility Study. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2021; 18:6059. [PMID: 34199880 PMCID: PMC8200090 DOI: 10.3390/ijerph18116059] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 04/06/2021] [Revised: 05/30/2021] [Accepted: 05/31/2021] [Indexed: 11/16/2022]
Abstract
Just-in-time adaptive intervention (JITAI) has gained attention recently and previous studies have indicated that it is an effective strategy in the field of mobile healthcare intervention. Identifying the right moment for the intervention is a crucial component. In this paper the reinforcement learning (RL) technique has been used in a smartphone exercise application to promote physical activity. This RL model determines the 'right' time to deliver a restricted number of notifications adaptively, with respect to users' temporary context information (i.e., time and calendar). A four-week trial study was conducted to examine the feasibility of our model with real target users. JITAI reminders were sent by the RL model in the fourth week of the intervention, while the participants could only access the app's other functionalities during the first 3 weeks. Eleven target users registered for this study, and the data from 7 participants using the application for 4 weeks and receiving the intervening reminders were analyzed. Not only were the reaction behaviors of users after receiving the reminders analyzed from the application data, but the user experience with the reminders was also explored in a questionnaire and exit interviews. The results show that 83.3% reminders sent at adaptive moments were able to elicit user reaction within 50 min, and 66.7% of physical activities in the intervention week were performed within 5 h of the delivery of a reminder. Our findings indicated the usability of the RL model, while the timing of the moments to deliver reminders can be further improved based on lessons learned.
Collapse
Affiliation(s)
- Shihan Wang
- Informatics Institute, University of Amsterdam, 1090 GH Amsterdam, The Netherlands; (H.v.H.); (B.K.)
- Department of Information and Computing Sciences, Utrecht University, 3584 CC Utrecht, The Netherlands
| | - Karlijn Sporrel
- Department of Human Geography and Spatial Planning, Utrecht University, 3584 CS Utrecht, The Netherlands; (K.S.); (D.E.)
| | - Herke van Hoof
- Informatics Institute, University of Amsterdam, 1090 GH Amsterdam, The Netherlands; (H.v.H.); (B.K.)
| | - Monique Simons
- Consumption & Healthy Lifestyles Group, Wageningen University & Research, 6700 HB Wageningen, The Netherlands;
| | - Rémi D. D. de Boer
- Digital Life Centre, Amsterdam University of Applied Science, 1091 GC Amsterdam, The Netherlands;
| | - Dick Ettema
- Department of Human Geography and Spatial Planning, Utrecht University, 3584 CS Utrecht, The Netherlands; (K.S.); (D.E.)
| | - Nicky Nibbeling
- Centre of Expertise Urban Vitality, Amsterdam University of Applied Science, 1097 DZ Amsterdam, The Netherlands;
| | - Marije Deutekom
- Faculty of Health, Sports and Welfare, Inholland University of Applied Sciences, 2015 CE Haarlem, The Netherlands;
| | - Ben Kröse
- Informatics Institute, University of Amsterdam, 1090 GH Amsterdam, The Netherlands; (H.v.H.); (B.K.)
- Digital Life Centre, Amsterdam University of Applied Science, 1091 GC Amsterdam, The Netherlands;
| |
Collapse
|
14
|
Chew HSJ, Ang WHD, Lau Y. The potential of artificial intelligence in enhancing adult weight loss: a scoping review. Public Health Nutr 2021; 24:1993-2020. [PMID: 33592164 PMCID: PMC8145469 DOI: 10.1017/s1368980021000598] [Citation(s) in RCA: 11] [Impact Index Per Article: 3.7] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/14/2020] [Revised: 01/12/2021] [Accepted: 02/03/2021] [Indexed: 11/07/2022]
Abstract
OBJECTIVE To present an overview of how artificial intelligence (AI) could be used to regulate eating and dietary behaviours, exercise behaviours and weight loss. DESIGN A scoping review of global literature published from inception to 15 December 2020 was conducted according to Arksey and O'Malley's five-step framework. Eight databases (CINAHL, Cochrane-Central, Embase, IEEE Xplore, PsycINFO, PubMed, Scopus and Web of Science) were searched. Included studies were independently screened for eligibility by two reviewers with good interrater reliability (k = 0·96). RESULTS Sixty-six out of 5573 potential studies were included, representing more than 2031 participants. Three tenets of self-regulation were identified - self-monitoring (n 66, 100 %), optimisation of goal setting (n 10, 15·2 %) and self-control (n 10, 15·2 %). Articles were also categorised into three AI applications, namely machine perception (n 50), predictive analytics only (n 6) and real-time analytics with personalised micro-interventions (n 10). Machine perception focused on recognising food items, eating behaviours, physical activities and estimating energy balance. Predictive analytics focused on predicting weight loss, intervention adherence, dietary lapses and emotional eating. Studies on the last theme focused on evaluating AI-assisted weight management interventions that instantaneously collected behavioural data, optimised prediction models for behavioural lapse events and enhance behavioural self-control through adaptive and personalised nudges/prompts. Only six studies reported average weight losses (2·4-4·7 %) of which two were statistically significant. CONCLUSION The use of AI for weight loss is still undeveloped. Based on the current study findings, we proposed a framework on the applicability of AI for weight loss but cautioned its contingency upon engagement and contextualisation.
Collapse
Affiliation(s)
- Han Shi Jocelyn Chew
- Alice Lee Centre for Nursing Studies, Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical Dr, Singapore 117597, Singapore
| | - Wei How Darryl Ang
- Alice Lee Centre for Nursing Studies, Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical Dr, Singapore 117597, Singapore
| | - Ying Lau
- Alice Lee Centre for Nursing Studies, Yong Loo Lin School of Medicine, National University of Singapore, 10 Medical Dr, Singapore 117597, Singapore
| |
Collapse
|
15
|
Hussain AA, Bouachir O, Al-Turjman F, Aloqaily M. AI Techniques for COVID-19. IEEE ACCESS : PRACTICAL INNOVATIONS, OPEN SOLUTIONS 2020; 8:128776-128795. [PMID: 34976554 PMCID: PMC8545328 DOI: 10.1109/access.2020.3007939] [Citation(s) in RCA: 36] [Impact Index Per Article: 9.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/25/2020] [Accepted: 07/04/2020] [Indexed: 05/18/2023]
Abstract
Artificial Intelligence (AI) intent is to facilitate human limits. It is getting a standpoint on human administrations, filled by the growing availability of restorative clinical data and quick progression of insightful strategies. Motivated by the need to highlight the need for employing AI in battling the COVID-19 Crisis, this survey summarizes the current state of AI applications in clinical administrations while battling COVID-19. Furthermore, we highlight the application of Big Data while understanding this virus. We also overview various intelligence techniques and methods that can be applied to various types of medical information-based pandemic. We classify the existing AI techniques in clinical data analysis, including neural systems, classical SVM, and edge significant learning. Also, an emphasis has been made on regions that utilize AI-oriented cloud computing in combating various similar viruses to COVID-19. This survey study is an attempt to benefit medical practitioners and medical researchers in overpowering their faced difficulties while handling COVID-19 big data. The investigated techniques put forth advances in medical data analysis with an exactness of up to 90%. We further end up with a detailed discussion about how AI implementation can be a huge advantage in combating various similar viruses.
Collapse
Affiliation(s)
- Adedoyin Ahmed Hussain
- Department of Computer EngineeringNear East University99138NicosiaMersin 10Turkey
- Research Centre for AI and IoTDepartment of Artificial Intelligence EngineeringNear East University99138NicosiaMersin 10Turkey
| | - Ouns Bouachir
- Department of Computer EngineeringZayed UniversityDubaiUnited Arab Emirates
- College of Technological InnovationZayed UniversityDubaiUnited Arab Emirates
| | - Fadi Al-Turjman
- Research Centre for AI and IoTDepartment of Artificial Intelligence EngineeringNear East University99138NicosiaMersin 10Turkey
| | - Moayad Aloqaily
- College of EngineeringAl Ain UniversityAl AinUnited Arab Emirates
| |
Collapse
|
16
|
Liao P, Greenewald K, Klasnja P, Murphy S. Personalized HeartSteps: A Reinforcement Learning Algorithm for Optimizing Physical Activity. PROCEEDINGS OF THE ACM ON INTERACTIVE, MOBILE, WEARABLE AND UBIQUITOUS TECHNOLOGIES 2020; 4:18. [PMID: 34527853 PMCID: PMC8439432 DOI: 10.1145/3381007] [Citation(s) in RCA: 29] [Impact Index Per Article: 7.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 10/24/2022]
Abstract
With the recent proliferation of mobile health technologies, health scientists are increasingly interested in developing just-in-time adaptive interventions (JITAIs), typically delivered via notifications on mobile devices and designed to help users prevent negative health outcomes and to promote the adoption and maintenance of healthy behaviors. A JITAI involves a sequence of decision rules (i.e., treatment policies) that take the user's current context as input and specify whether and what type of intervention should be provided at the moment. In this work, we describe a reinforcement learning (RL) algorithm that continuously learns and improves the treatment policy embedded in the JITAI as data is being collected from the user. This work is motivated by our collaboration on designing an RL algorithm for HeartSteps V2 based on data collected HeartSteps V1. HeartSteps is a physical activity mobile health application. The RL algorithm developed in this work is being used in HeartSteps V2 to decide, five times per day, whether to deliver a context-tailored activity suggestion.
Collapse
|
17
|
Abstract
PURPOSE OF REVIEW This review synthesizes recent research on remotely delivered interventions for obesity treatment, including summarizing outcomes and challenges to implementing these treatments as well as outlining recommendations for clinical implementation and future research. RECENT FINDINGS There are a wide range of technologies used for delivering obesity treatment remotely. Generally, these treatments appear to be acceptable and feasible, though weight loss outcomes are mixed. Engagement in these interventions, particularly in the long term, is a significant challenge. Newer technologies are rapidly developing and enable tailored and adaptable interventions, though research in this area is in its infancy. Further research is required to optimize potential benefits of remotely delivered interventions for obesity.
Collapse
Affiliation(s)
- Lauren E Bradley
- Department of Psychiatry and Behavioral Sciences, Rush University Medical Center, 1645 W. Jackson Blvd. Suite 400, Chicago, IL, 60612, USA.
| | - Christine E Smith-Mason
- Department of Psychiatry and Behavioral Sciences, Rush University Medical Center, 1645 W. Jackson Blvd. Suite 400, Chicago, IL, 60612, USA
| | - Joyce A Corsica
- Department of Psychiatry and Behavioral Sciences, Rush University Medical Center, 1645 W. Jackson Blvd. Suite 400, Chicago, IL, 60612, USA
| | - Mackenzie C Kelly
- Department of Psychiatry and Behavioral Sciences, Rush University Medical Center, 1645 W. Jackson Blvd. Suite 400, Chicago, IL, 60612, USA
| | - Megan M Hood
- Department of Psychiatry and Behavioral Sciences, Rush University Medical Center, 1645 W. Jackson Blvd. Suite 400, Chicago, IL, 60612, USA
| |
Collapse
|