Page 33 - IMDR Journal 2025
P. 33

Research Article
            LITERATURE REVIEW                                 Looking ahead, smarter AI could better understand what
                                                              patients need and become a key tool in digital healthcare.
            1.  "A  Review  of  the  Role  of  Artificial  Intelligence  in
            Healthcare”                                       3."Exploring Patient Perspectives on How They Can and
                                                              Should  Be  Engaged  in  the  Development  of  Artificial
            Published in Journal of Healthcare Informatics Research,
                                                              Intelligence (AI) Applications in Health Care”
            2023
                                                              Published in BMC Health Services Research, 2023
                                                 2,3
                                   1
            Authors: Ahmed Al Kuwaiti  ,*, Khalid Nazer  , Abdullah
                    4
                                                     6,7
                                   5
            Al-Reedy , Shaher Al- Shehri , Afnan  Al-Muhanna  , Arun    Authors Samira Adus, Jillian Macklin & Andrew Pinto
                            8
                                               9
            Vijay   Subbarayalu  , Dhoha   Al Muhanna  , Fahad A Al-  This study explores the role of patient involvement in the
            Muhanna  10,11                                    development of AI-driven healthcare applications, arguing
            This paper investigates the revolutionary impact of Artificial   that patient-centric AI models lead to better engagement and
            Intelligence (AI) in different parts of healthcare, such as   trust. The research is based on qualitative interviews with
            diagnostics, administrative tasks, and patient interaction. It   patients,  healthcare  professionals,  and  AI  developers,
            demonstrates  how  artificial  intelligence  improves   identifying  key  concerns  and  expectations  regarding  AI
            operational efficiency by automating routine operations like   adoption  in  healthcare.  Patients  emphasize  the  need  for
            scheduling,  documentation,  and  patient  communication.   transparency  in  AI  decision-making,  particularly  in
            The research focuses on AI-powered chatbots and virtual   diagnosis,  treatment  recommendations,  and  data
            assistants, which boost patient engagement by offering real-  management. The study reveals that patient engagement in
            time  support,  appointment  reminders,  and  personalized   AI development fosters greater acceptance and adherence to
            health  advice.  Furthermore,  it  explores  how  predictive   AI-driven healthcare solutions. Moreover, it discusses how
            analytics  can  help  identify  high-risk  patients  and  initiate   AI applications can be more effective when designed with
            early interventions, resulting in better health outcomes and   patient feedback, ensuring that features such as symptom
            fewer hospital readmissions. The essay also looks at the   checkers,  chatbots,  and  predictive  analytics  align  with
            ethical concerns and obstacles that come with AI adoption,   actual user needs. Ethical considerations, including bias in
            such  as  data  privacy,  bias  in AI  systems,  and  regulatory   AI models and the potential depersonalization of healthcare,
            compliance.  By  analysing  case  studies  and  real-world   are also addressed. The study concludes that incorporating
            applications,  the  review  underscores  AI’s  potential  in   patient perspectives in AI design enhances personalization,
            optimizing patient retention strategies through automated   improves healthcare outcomes, and strengthens long-term
            follow-ups and tailored content delivery. While AI presents   patient-  provider  relationships.  It  recommends  that
            significant  benefits,  the  study  emphasizes  the  need  for   healthcare  organizations  adopt  participatory  design
            stringent data governance and patient- centric approaches to   approaches, where patients actively contribute to shaping AI
            ensure ethical and effective AI deployment in healthcare   technologies that directly impact their care experiences.
            marketing. The findings suggest that AI-driven innovations   4.  "Challenges  in  Participant  Engagement  and  Retention
            will  continue  to  reshape  healthcare  delivery,  making   Using Mobile Health Apps Literature Review”
            personalized  and  proactive  patient  engagement  a  core   Published in Journal of Medical Internet Research, 2022
            strategy for healthcare providers.
                                                              Authors Saki  Amagai1 ; Sarah  Pila1 ; Aaron  J  Kaat1 ;
            2.  "Patient  Engagement  with  Conversational  Agents  in   Cindy  J Nowinski1 ; Richard C Gershon1
            Health Applications 2016– 2022 A Systematic Review and
            Meta-Analysis”                                    This literature review examines the challenges associated
                                                              with  patient  engagement  and  retention  in  mobile  health
            Published in Journal of Medical Systems, 2024
                                                              (mHealth)  applications,  identifying  factors  that  influence
            Authors Kevin E. Cevasco, Rachel E. Morrison Brown,   user adherence and drop-off rates. The study looks at how
            Rediet Woldeselassie & Seth Kaplan                mobile  health  (mHealth)  apps  help  patients.These  apps
            Morrison Brown, Rediet Woldeselassie, and Seth Kaplan   make healthcare easier to access. But keeping users engaged
            studied how chatbots help in healthcare. They studied 50   for a long time is still a big problem. The study points out
            case and clinical trials done in the years 2016 to 2022. The   three main types of barriers: tech issues, user behavior, and
            majorly focus was to involve the patients and ensure their   system-level problems. Tech barriers include apps that are
            care.                                             hard to use, not personalized, or don’t protect privacy well.
                                                              Behavioral  barriers  involve  low  motivation,  poor  health
            The  chatbots  helped  in  identifying  symptoms,  timely   knowledge,  and  not  sticking  to  app  routines.  Systemic
            reminders to the patients for consuming the medicines, and   barriers come from weak links between apps and doctors,
            giving mental health support. They answered quickly and   and from health rules that limit what apps can do.The study
            gave  personal  advice.  This  made  patients  feel  more   says smart features like changing the app look based on the
            connected  and  helped  them  stick  to  their  treatment. The
            chatbots assisted in the follow-up messages and giving the   user, guessing user needs, or using game-like tools can help.
            health tips which helped patients stay on track with their   Sending reminders, helpful tips, and custom content also
            health.  But  there  are  downsides.  AI  chatbots  don’t   keeps users more engaged.The findings emphasize that for
                                                              AI-  powered  mHealth  applications  to  be  successful,
            understand emotions well, and there are worries about how
                                                              developers  must  prioritize  user  experience,  maintain
            they  handle  private  health  data. The  study  says  the  best   transparency in data usage, and ensure interoperability with
            results come from a mix of AI and human support.
                                                              existing  healthcare  systems  to  foster  long-term  patient
                                                              engagement.
                                                                                                    24
   28   29   30   31   32   33   34   35   36   37   38