Digital health tools and technologies are transforming health care and making significant impacts on how health and care information are collected, used, and shared to achieve best outcomes. As most of the efforts are still focused on clinical settings, the wealth of health information generated outside of clinical settings is not being fully tapped. This is especially true for children with medical complexity (CMC) and their families, as they frequently spend significant hours providing hands-on medical care within the home setting and coordinating activities among multiple providers and other caregivers. In this paper, a multidisciplinary team of stakeholders discusses the value of health information generated at home, how technology can enhance care coordination, and challenges of technology adoption from a patient-centered perspective. Voice interactive technology has been identified to have the potential to transform care coordination for CMC. This paper shares opinions on the promises, limitations, recommended approaches, and challenges of adopting voice technology in health care, especially for the targeted patient population of CMC. (J Med Internet Res 2020;22(2):e14202) doi: 10.2196/14202 KEYWORDS care coordination; self-management; children with medical complexity; voice technology; voice assistant; digital health; conversational agents settings and are not systematically documented and integrated Introduction into the clinical systems. Such a practice limits the information captured per patient, which may lead to adverse effects in Immense efforts have been placed on capturing health clinical decision making. This is especially concerning for information electronically, thereby modernizing health children with special health care needs (CSHCN). CSHCN is communications. The majority of these efforts are provider defined by the federal Maternal and Child Health Bureau driven and center around traditional clinical settings. However, (MCHB) as children who have or are at an increased risk for a lot of health and care activities happen outside of clinical chronic physical, developmental, behavioral, or emotional https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 1 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al conditions and who also require health and related services of with technology dependence, the use of life-sustaining a type or amount beyond that required by children generally technologies such as ventilation, tube feeding, and intravenous . About 23% of US households have at least one CSHCN medications. Highly relevant and valuable information generated , and their needs include, but are not limited to, prescription in the home setting is not currently captured systematically in drugs (86%); specialty care (47.5%); vision care (35.3%); mental electronic medical records (EMRs), but it can be of great help health services (27.6%); occupational, physical, and speech in enabling effective care coordination and improving clinical therapy (26.6%); medical equipment (11.3%); hearing aids or decision making and treatment planning. Collecting relevant care (5.2%); mobility aids (4.6%); and communication aids and complete health information at home is challenging. Some (2.5%) . CMC might have physical impairments that prevent them from participating in clinical information gathering and decision Children with medical complexity (CMC), a subset of CSHCN, making in a traditional way. Parents of CMC may be very busy have significant health issues that occur outside of the clinic, with meeting routine and unscheduled on-demand care needs and they require complex home care provided by parents and at home, making it difficult to consistently and accurately other caregivers in addition to nurses . CMC have medical document or provide health updates. These situations suggest fragility, medical technology dependence, functional that there is a need to find a different approach that is easier for impairment, and intensive care needs that are not easily met by the patients and caregivers to provide relevant health information existing care models . Common characteristics of CMC are to the clinical team on a timely basis. as follows: (1) they are one of the most frequently hospitalized populations; (2) follow-ups are more complex compared with Helping CMC and families provide the right home-administered regular patients, requiring multiple specialties; (3) they use treatments at the right time, promptly documenting clinical multiple medications; and (4) they are more likely to have events (medication, therapy, oxygen treatment, etc), recording complications post discharge. These characteristics highlight symptoms as they happen, and reaching out for timely assistance the critical needs for effective care management outside of are critical to promote self-management and coordinated care clinical settings, timely health information sharing, and skills and for successful care coordination . Within the scope sophisticated care coordination for CMC. The literature also of home care and use of technologies for care coordination, we supports the need to improve care coordination [4,5], which is identified 3 problematic care coordination gaps to be addressed: the process of linking patients and caregivers to necessary (1) untimely and incomplete capture of health events at home, services and resources in a coordinated effort for providing (2) lack of home care coordination tools, (3) long term adoption optimal health care . problem for health care apps. A team (coauthors), consisting of caregivers of CMC; a clinician Untimely and Incomplete Capture of Health Events who specializes in treating CMC; a care coordinator who assists at Home CMC and their families; a user experience designer; an It is commonly observed in clinical practice that patients and application developer; and scientists and researchers who are families do not have accurate recall of symptoms, clinical events, experienced in clinical informatics, participatory design, and or usage of over-the-counter medications . Patients and digital health, was formed at Nationwide Children’s Hospital. families also frequently delay reporting of time-sensitive health The team identified gaps in care coordination for CMC and issues because of the burden of communication resulting from their families, how various technologies can fill these gaps, and health care disparities . Untimely and inaccurate how they could be implemented and adopted, all from a communication with health care providers may result in patient-centered perspective. The team discussed the value of misdiagnosis, mistreatment, extra visits, and extra cost . To health information generated at home and the challenges and fill the gap, symptom tracking and monitoring apps have been barriers associated with capturing that information. The team developed over the years to help patients document health events developed recommendations to improve not only record keeping outside of clinical environments [10-13]. of patient care at home but also communication among patients, ...I couldn’t remember how many times I have given caregivers, and care providers through technological solutions. my daughter Albuterol treatments in the last two The purpose of this paper was to present our opinions on weeks… [Caregiver] employing emergent voice interactive technology to capture real-time health information and to enhance care coordination, However, many of these apps fail to promote timely the associated challenges in adopting this technology, and documentation of health-related information because of desired future development. cumbersome user interfaces, lack of functionality, or not providing evidence-based and personalized content. In many Challenges in Care Coordination for cases, the perceived value does not overcome the burden of using the apps [12,13]. Existing technology-based solutions are Children With Medical Complexity typically screen driven, requiring users to navigate through the For CMC, the role of care coordination is highly valuable hierarchy of symptoms with multiple clicks or touches to find because the responsibilities (time spent, effort, and financial the right place, then users may be presented with a prepopulated burden) are higher and navigating services is more difficult . list of choices from which to select. They do not allow natural, Most health-related events occur within a patient’s home. These unstructured recording of symptoms and clinical events. The include the occurrences of symptoms; medication time and effort needed to document creates a burden, which administrations; home therapies; and, in the case of patients prohibits the adoption of these tools. It is particularly https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 2 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al burdensome for CMC as they experience more symptoms and are designed primarily to capture encounters with providers and for longer periods. For instance, patients discharged from the to bill for services. Most EMR systems do not provide useful neonatal intensive care unit might need to be closely monitored tools for a patient-initiated medical diary. Most patient-facing at home. Their conditions might change quickly, heralded only EMR utilities provide access to limited clinical information, by fluctuations in heart rate or oxygen saturation, with illnesses sending or receiving an email to/from one provider at each ranging from a minor viral infection to a bowel obstruction. instance, and completing predesigned health assessment Caregivers might have their hands full when symptoms occur, questionnaires. Often, parents of CMC need to discuss a problem making it difficult to record real time, especially if typing is with multiple providers, who also need to discuss among required. Therefore, documentation activities are postponed and themselves. For instance, if a child receiving in-home ventilation potentially forgotten while providing care, which can lead to experiences respiratory symptoms, the parent may want to adverse events and low or inaccurate recall of events when inform and discuss these symptoms with the primary care communicating with the clinical team. An integrated, provider, the pulmonologist, and the otolaryngology surgeon easy-to-use, real-time, low-burden tool for health logging at at the same time and on the same thread, which would improve home would be highly beneficial. the efficiency of resolving the problem. Unfortunately, there is limited literature addressing care Lack of Home Care Coordination Tools coordination technologies and their utilities for CSHCN or CMC Families of CMC could be apprehensive about leaving the and caregivers in home setting. A majority of the studies focus clinical setting because of the complexity of their medical care on the use of health communication technologies (Web-based responsibilities. Care coordination services could be supportive and mobile tools) in self-care, and the results show limited and helpful for transitioning after discharge. evidence regarding care coordination outcomes . ...when we were going home (after NICU discharge), Long-Term Adoption Problem for Health Care Apps I wasn’t ready to go home. [Caregiver] The most commonly used and accessible health care For care coordination services in the home setting, generic technologies are mobile apps. In general, long-term sustained emailing and messaging apps and special-purpose nonmedical usage of health care apps is low . care apps (reminders for medications, diaper changes, feedings, etc) have been commonly used. However, care coordination The app takes too many taps to get to the right screen. apps are limited or nonexistent for complex services, lacking I stopped using it after a month... [Caregiver] functionalities such as allowing multiple users to communicate Many existing apps have the potential to deliver great value to and coordinate or providing on-demand coaching of home care end users but have failed to keep users engaged long enough to skills . Lack of care coordination among caregivers can reach that potential . This long-term adoption problem is result in high indirect health care costs and poor outcomes, such notable in user ratings and comments of apps that are currently as overmedicating or undermedicating, medication errors, safety available. Many hours go into the development, marketing, and issues, and emotional stress . Providing relevant and timely maintenance of these apps. If the apps are not used long term, instructions on caregiving procedures at home during time of there is a great deal of waste involved. Keeping the patient and need will also reduce the demand to connect with care families engaged for the long term is critical to maximize the coordinators, build home care skills, and avoid costly mistakes. true adoption and value of a health care tool. Considering A patient-centered and easily accessible tool that facilitates real-world scenarios, improving the convenience of utilizing coordination among home caregivers would reduce the technology should increase adoption and sustained miscommunications, delays, and stress, thus reducing costs engagement in the home setting. resulting from errors and improving outcomes. On the provider side, EMR systems have become a common It is common practice to use a verbal or informal note as a tool with digitized clinical records, and their use has been handoff to communicate during transitions between caregivers. mandated. However, patient engagement and caregiver However, this requires extra effort and coordination, as there engagement depend on the perceived value and whether value can be adverse events when the notes are not written, illegible, outweighs burden of use. Today, many caregivers use paper or lost, or not noticed. Transcribing handwritten notes manually other analog, nonunified, unshared, nonsystematic methods to into patient records is also cumbersome, time consuming, and capture medical events and subsequently rely on one-to-one error prone. This inefficient flow of information during transition direct communication with providers to coordinate care. An times may lead to additional caregiver burden and reduced alternate strategy to promote communication would be to make quality of care . The use of digital tools, such as mobile it easier for caregivers to report and capture medical events. phone apps and Web services, would be preferable but might Millions of homes have adopted voice interactive devices, such be inconvenient if the interaction with the apps requires the as Amazon Alexa, because they are easy and convenient to use. physical and visual focus to shift away from caregiving Voice-enabled technology can be leveraged to more accurately activities. Most of the current digital tools lack integration with report medication compliance, event documentation, and care EMR systems, which prevents timely 2-way communication coaching. In line with that, our previous study demonstrated between provider and caregiver. Critical health information that voice interactive technologies are expected to promote captured at home should flow seamlessly into EMR for a timely adherence in health tracking and increase adoption of response from the clinical team. EMR systems are preferred as communication technologies for care management among the major hub for personal health information. However, they https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 3 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al caregivers and CSHCN . Toward the effort to reduce the way, enabling hands-free voice interactivity, which might be adoption problem, we offer an alternative method to mostly critical for people who have physical limitations and are not manual and error-prone methods in home care, such as delayed able to type in information. Shifting to an audio diary with voice event note taking. We hypothesize that gradual replacement of interaction could increase adherence in keeping a log, current in-home methods with the use of tailored and low-burden specifically when a diary is prescribed to record the frequency technologies, such as audio-interactive ambient communication of seizures, follow-up with diabetic laboratory tests, or to track tools, in the home setting could potentially increase effectiveness general medical symptoms. of care management and coordination for CMC. The ease of leveraging natural voice documentation needs to be supported with strong natural language processing (NLP) Recommendations for both voice transcription to text and information extraction from the unstructured text. NLP, together with advanced data To address the previously identified gaps in the current apps science methodologies, has been developed and continues to and tools landscape, it is essential to engage all stakeholders of be improved to take full advantage of the richness of contextual CMC using human-centered design principles to create an information presented in natural narratives . It can be used accessible and interoperable solution. Our multistakeholder to extract relevant information related to symptoms associated team did not focus on finding the silver bullet, but rather, it with diagnoses, identify signs of worsening conditions, and focused on identifying a potential solution to nudge patients, record medication compliance, all to facilitate the care caregivers, and medical providers in a direction that will achieve coordination process. Given the current practices utilizing better coordination at home. Focusing on reducing challenges, machine learning in digital health, user differentiation and blending in with daily routines, increasing engagement, enabling identification, pattern and characteristic recognition, medical convenient communication, and tracking/coaching in the home alert and prescription reminders, and emerging needs prediction setting, the team recommends the adoption of voice interaction are all potential scenarios once an adequate amount of voice technologies for in-home documentation and information data are acquired for training the algorithms. Collectively, delivery to enhance ease of use and technology adoption. speech and audio inputs have the potential to be used as digital Leverage Voice Recognition and Interaction biomarkers in the future for detecting and predicting disorders, diseases, and acute deterioration events . Voice interactive devices and apps are currently embraced and used in daily life by millions of people. The technology is not Extend the System Architecture to Incorporate Voice a passing eccentricity but rather has multiple embodiments from Interactive Technology major technology companies, including Amazon Alexa, Google The recommended solution framework is illustrated in Figure Assistant, Apple’s Siri, Samsung’s Bixby, and other Internet of 1. In the home, a patient and caregiver can interact with the Things– and mobile-based platforms. These apps have just solution system via voice, allowing convenient engagement in started gaining attraction in health care . There are studies a naturalistic setting. The voice interaction would facilitate investigating the feasibility of voice-activated devices and voice information exchanges among devices or components in the assistants in medical data collection and accuracy in user network, promoting a personalized digital ecosystem understanding medical terms [21,22]. In addition, research has (services such as If This Then That and Apple Health enable shown that users are increasingly adopting voice interactive such information exchange). The data will be processed (eg, devices and apps that can blend seamlessly into their daily lives voice can be transcribed and converted into text with established . Considering the ease of using in voice interaction to access and secure services such as Amazon Transcribe or SiriKit; text Web-based information, the adoption of these new technologies can be further processed into structured data using NLP services may be higher by caregivers . However, documented use such as Amazon Comprehend); information collected can be of voice interaction in care coordination is limited, especially integrated with clinical care and management systems at the in pediatric care. Multimedia Appendix 1 summarizes some of backend using interoperable standard of fast health care the voice interactive tools currently available in the market for interoperability resources. The proposed system can be care assistance. implemented to make summarized and curated data available Voice interaction is particularly successful when the nature of to providers and care coordinators at the next visit. Considering interaction does not require any visual or tactile feedback, real-world use cases and current needs, we have anticipated key thereby removing personal attention to the device. Users simply functionalities that would be required. Features have been speak to the app naturally, and information will be captured or grouped according to 3 identified challenges (Textbox 1). recorded. The app can allow caregivers to provide details of Textbox 2 provides 3 real-world user stories suggesting the symptoms and health events in the most natural and narrative potential use of voice interaction in care coordination. https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 4 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al Figure 1. An ecosystem of voice interactive care coordination unifying homecare with health care institutions. EMR: electronic medical record; IoT: Internet of Things. Textbox 1. Example functionalities of voice interactive tool. 1. Timely capture of complete and accurate health information at home Voice enabled for natural unstructured, real-time health information capture Can record audio (such as coughing) and video to communicate with care provider team User validates and edits text transcribed from voice to address transcription inaccuracy and privacy Direct free-text documentation is also available to accommodate multiple input modalities Register care needs using trigger words to notify the care coordination team 2. Facilitate coordination among caregivers at home Allow multiple users with different level of access Segment health information to reflect privacy preferences (public, shared, private, etc) Voice-enabled retrieval of recent care history using predefined trigger keywords Provide instructions or coaching on relevant home treatment procedures 3. Foster adoption of the app and long-term engagement of users Integrate with electronic health record to pull clinical information and push home care information back Enroll patients to use this app and help them to set up linkage at clinical visit Reminders for medications, next scheduled visits, and updating of symptoms Customized reports to patients periodically to provide value to them and to keep them engaged Leverage Health Insurance Portability and Accountability Act–compliant Web servers and services for data storing and analysis Raw captured data are distilled to represent succinct and relevant historical clinical information 4. Integrate the solution with the health care delivery system for care coordination Receive feedback from the care coordination center Adopt fast health care interoperability resources application program interfaces for interoperability Demonstrate integration with a health care delivery system including care coordination https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 5 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al Textbox 2. User stories with voice interaction in care coordination. User story 1: Incomplete information on symptoms and health events at home Who: Parent of a child who has asthma What: Cannot recall how often he has been given Albuterol in the last 3 months and how many times the child has woken up because of night time coughing Why: The above missing information is needed to assess asthma severity and recommend the right treatment plan Solution: Using the app, the parent documented the child’s asthma symptoms and treatment as they occurred. The parent clicked the links to review and update Albuterol dosage and treatment times. Also, increased coughing events at night were noted. A week later at the doctor’s appointment, the parent filled out questionnaire on symptoms referencing the records in the app. Doctor: “Do you have any concerns over the last 3 months?” The parent pulled out the app to review the list of concerns and the relevant symptom histories User story 2: Complexity of care coordination among caregivers Who: Parents and a child with multiple health problems including cerebral palsy, epilepsy, tracheostomy, and gastrostomy who uses a wheelchair What: Have trouble coordinating complex care at home (tracheostomy tube changes and medication administration, etc) Why: Not knowing whether the previous caregiver has given antiepileptic, at what time and dosage, if it could be dangerous and negatively impact health outcome Solution: Mom: “Alexa, Depakote 5mL given to Ben” (timestamp captured and recorded) Amazon Alexa: “Depakote 5mL given to Ben. Got it” Mom “Alexa. Ben Trach changed” Amazon Alexa: “Trach changed for Ben. Got it” Dad: “Alexa. When was the Trach changed last for Ben?” Amazon Alexa: “Trach was last changed at 3:05 pm today for Ben.” User story 3: Stress of care coordination between youth and parents Who: A diabetic teenager who needs daily insulin shots and caring parents What: The teenager gets agitated when parents check in daily to make sure medications are taken Why: The teenager perceives parents’ medication monitoring and reinforcements as nagging Solution: Teenager: “Hey Siri. Insulin given” (timestamp captured and recorded) Apple watch: “Got it. Insulin given at <current time>”. Parents are also authorized to see the records and would need to “nag” the teenager a lot less, resulting in less stress and better teenager-parent relationship. The teenager can also view her compliance of treatments and glucose levels over time. She begins to take responsibility for monitoring her own health but continues to have oversight by parents. artificial intelligence (AI) and NLP methods would be employed. Define and Measure Outcome Metrics Annotated notes, number of user-validated transcriptions and Outcome metrics for voice interaction could be slightly different notes, and number of retaken or corrected notes could be used from other technologies because of the nature of information to test the performance of AI. Precision and recall rates could processing and technology interaction. Therefore, it is important be used to assess the accuracy of NLP methods in predicting to consider the differences and adjust the metrics. In voice and providing note highlights. Engagement assessment could interaction, outcome metrics could be collected and assessed be done for adoption of technology services and utilization of in 2 categories: technical and engagement. To validate the knowledge provided. The quantitative log data, such as number technical performance of the technology, accuracy testing of of users per patient (eg, care coordinator, medical provider, or https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 6 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al caregiver), audio notes taken, number of transcriptions reviewed Potential Limitations and Implementation Challenges or edited, and number of parent instructions used, could be As shown in Figure 2 (Adapted from ), the utilization of employed to assess user adoption. In addition to that, usability voice interactive services is in the early stage, and it would testing of voice interaction to understand the narratives, eventually advance from information-level services (eg, co-design sessions for creating the voice interface, and educational content and internet search) to assistance (eg, technology adoption interviews and surveys could be utilized guidance and instruction, reminders, and alerts and tracking), to comprehensively analyze the adoption and correlating factors. then to assessment (eg, identification and detection, prediction Utilization of the knowledge provided would be assessed in the with biomarkers, and management), and eventually to support long term, such as through comparison of families using digital (substituting or supplementing the medication and therapy tools). health versus nonusers in terms of emergency department visits Currently, the implementations are moving from information and hospitalizations. The observable results based on the use to assistance level in a low-risk and limited-service approach, of suggestions at home would imply utilization by patients and such as medical reminders and other messages used only in the caregivers. The number of times speech-to-text notes are pulled hospital setting, similar to the current state of voice assistants from the EMR and reviewed by providers would be indicators in self-management . However, as the use of voice of utilization by the providers. The assessment of the outcome interactive devices and services grows, both their impact on requires multilayered and multitheoretical research plans to health care and the risks on privacy and security increase. understand the impact and implications of the proposed technology. Figure 2. Spectrum of applications of voice assistants. Within this context, voice assistants in care coordination, as the developers and researchers with user consent, which can envisioned solution in this paper, may have implemental, ethical, be used for improving health services. regulatory, and technical limitations. Although significant • Not all health care services are HIPAA compliant and have progress has been made in terms of compliance of services (eg, limited security and privacy protocols related to Health Insurance Portability and Accountability Act [HIPAA] audio-formatted health data transmission, processing, and compliance of Amazon Alexa), consumer-facing voice storage. interactive device apps currently have limited abilities to be • There is relatively lower demand in the market compared used in health care. Some of the emerging limitations for with other communication technologies (eg, mobile apps). leveraging voice are as follows: • Access to voice-enabled devices is affected by the social economic status and may create inequality in access to the • Mainstream vendors are not providing full access and solution (eg, requirement for compatible device and data control of the voice input (eg, transcript and raw data) to plan). https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 7 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al • There is a major progress in voice recognition in the English Considering the increasing investments in health care and voice language but limited efforts on foreign-accent recognition technologies and the current trajectory of voice interactive and lack of availability and analytical capability in a large device adoption , it is expected that voice interactive selection of other languages. platforms will have an impact as household health • New methods are needed for designing voice services in communication tools or as telemedicine tools in the long term. health care. Translating mobile or Web services to voice Limitations could be mitigated by policy changes such as may be limited in terms of functionality and navigation. reducing cost and increasing accessibility by potentially collaborating with accountable care organizations ; Conversely, integration of unstructured patient-reported data promoting employer-based health insurance coverage for voice with the health care system could create a systematic burden assistants; and inclusion in digital health policy and regulations, and may be hard to control and use in decision making . such as the Food and Drug Administration’s Digital Health These unstructured data need to be coupled with NLP and AI Innovation Action Plan . to extract and present the relevant information to the providers. This is not a new problem as physician’s patient notes constitute Conclusions the majority of unstructured data within the EMR . However, integrating care and health information collected at home needs In this paper, we have shared the challenges and strategic planning and providers’ buy-in. At a time when recommendations regarding the use of technology to promote physician burnout and alert fatigue are such pressing issues, coordination of the care of CMC in a home setting. We argue additional information streaming from a patient’s home into the that the use of voice interactive technologies in the home setting EMR needs to be distilled to support clinical decision making could enhance communication of health events and improve . In addition, clinical workflow may need to be modified coordination. Although the current literature is limited in relation to balance the tradeoff of a timely response to urgent issues and to voice assistant use in care, our report contributes to the to reduce potential clinician burnout. literature suggesting potential health informatics solutions, which address information needs for coordination . Acknowledgments Care Coordination for CSHCN Grand Challenge, sponsored by MCHB of the Health Resources and Services Administration, motivated the formulation of this multistakeholder team and pursuit of this proposed solution. Our team has been awarded as one of the phase I and II winners. The authors would also like to acknowledge Carrie Robinson for constructively reading the manuscript. Authors' Contributions All authors contributed to the ideation, solution development, and the writing of this paper. ES led the manuscript preparation, writing, and coordinating the authors. YH supervised and led the solution development. The authors contributed with their viewpoints as, physician (GN), nurse scientist (VS), caregiver (AE), care coordinator (KC), digital health scientist and clinical informaticians (ES, YH, SL, SR, and AC), developer (MB), and designer (RS). Conflicts of Interest None declared. Multimedia Appendix 1 Voice interactive assistants in the market. [PDF File (Adobe PDF File), 547 KB-Multimedia Appendix 1] References 1. McPherson M, Arango P, Fox H, Lauver C, McManus M, Newacheck PW, et al. A new definition of children with special health care needs. Pediatrics 1998 Jul;102(1 Pt 1):137-140. [doi: 10.1542/peds.102.1.137] [Medline: 9714637] 2. US Department of Health and Human Services, Health Resources and Services Administration, Maternal and Child Health Bureau. Rockville, Maryland: US Department of Health and Human Services; 2013. The National Survey of Children with Special Health Care Needs Chartbook 2009-2010 URL: https://mchb.hrsa.gov/cshcn0910/more/pdf/nscshcn0910.pdf 3. Cohen E, Kuo DZ, Agrawal R, Berry JG, Bhagat SK, Simon TD, et al. Children with medical complexity: an emerging population for clinical and research initiatives. Pediatrics 2011 Mar;127(3):529-538 [FREE Full text] [doi: 10.1542/peds.2010-0910] [Medline: 21339266] 4. Amir O, Grosz BJ, Gajos KZ, Swenson SM, Sanders LM. From care plans to care coordination: opportunities for computer support of teamwork in complex healthcare. In: Proceedings of the 33rd Annual ACM Conference on Human Factors in Computing Systems. 2014 Mar Presented at: ACM Conference on Human Factors in Computing Systems; April 18-23, 2015; Seoul, Republic of Korea p. 101-104 URL: https://dl.acm.org/citation.cfm?id=2702320 [doi: 10.1145/2702123.2702320] https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 8 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al 5. Council on Children with Disabilities Medical Home Implementation Project Advisory Committee. Patient- and family-centered care coordination: a framework for integrating care for children and youth across multiple systems. Pediatrics 2014 May;133(5):e1451-e1460. [doi: 10.1542/peds.2014-0318] [Medline: 24777209] 6. Ziring PR, Brazdziunas D, Cooley WC, Kastner TA, Kummer ME, Gonzalez de Pijem L, et al. American Academy of Pediatrics. Committee on Children With Disabilities. Care coordination: integrating health and related systems of care for children with special health care needs. Pediatrics 1999 Oct;104(4 Pt 1):978-981. [Medline: 10506246] 7. Ranade-Kharkar P, Weir C, Norlin C, Collins SA, Scarton LA, Baker GB, et al. Information needs of physicians, care coordinators, and families to support care coordination of children and youth with special health care needs (CYSHCN). J Am Med Inform Assoc 2017 Sep 01;24(5):933-941. [doi: 10.1093/jamia/ocx023] [Medline: 28371887] 8. Glick AF, Farkas JS, Nicholson J, Dreyer BP, Fears M, Bandera C, et al. Parental management of discharge instructions: a systematic review. Pediatrics 2017 Aug;140(2):e20164165 [FREE Full text] [doi: 10.1542/peds.2016-4165] [Medline: 28739657] 9. Diette GB, Rand C. The contributing role of health-care communication to health disparities for minority patients with asthma. Chest 2007 Nov;132(5 Suppl):802S-809S. [doi: 10.1378/chest.07-1909] [Medline: 17998344] 10. Wesley K, Fizur P. A review of mobile applications to help adolescent and young adult cancer patients. Adolesc Health Med Ther 2015 Aug;6:141-148. [doi: 10.2147/ahmt.s69209] [Medline: 26316835] 11. Masterson Creber RM, Maurer M, Reading M, Hiraldo G, Hickey K, Iribarren S. Review and analysis of existing mobile phone apps to support heart failure symptom monitoring and self-care management using the Mobile Application Rating Scale (mars). JMIR Mhealth Uhealth 2016 Jun 14;4(2):e74 [FREE Full text] [doi: 10.2196/mhealth.5882] [Medline: 27302310] 12. Tinschert P, Jakob R, Barata F, Kramer J, Kowatsch T. The potential of mobile apps for improving asthma self-management: a review of publicly available and well-adopted asthma apps. JMIR Mhealth Uhealth 2017 Aug 02;5(8):e113 [FREE Full text] [doi: 10.2196/mhealth.7177] [Medline: 28768606] 13. Kao C, Liebovitz D. Consumer mobile health apps: current state, barriers, and future directions. PM R 2017 May;9(5S):S106-S115. [doi: 10.1016/j.pmrj.2017.02.018] [Medline: 28527495] 14. Baysari MT, Westbrook JI. Mobile applications for patient-centered care coordination: a review of human factors methods applied to their design, development, and evaluation. Yearb Med Inform 2015 Aug 13;10(1):47-54 [FREE Full text] [doi: 10.15265/IY-2015-011] [Medline: 26293851] 15. Peter S, Chaney G, Zappia T, Van Veldhuisen C, Pereira S, Santamaria N. Care coordination for children with complex care needs significantly reduces hospital utilization. J Spec Pediatr Nurs 2011 Oct;16(4):305-312. [doi: 10.1111/j.1744-6155.2011.00303.x] [Medline: 21951356] 16. Kim CH, Kim MS. Ventilator use, respiratory problems, and caregiver well-being in korean patients with amyotrophic lateral sclerosis receiving home-based care. J Neurosci Nurs 2014 Oct;46(5):E25-E32. [doi: 10.1097/JNN.0000000000000075] [Medline: 25188688] 17. Sutcliffe P, Martin S, Sturt J, Powell J, Griffiths F, Adams A, et al. Systematic review of communication technologies to promote access and engagement of young people with diabetes into healthcare. BMC Endocr Disord 2011 Jan 06;11:1 [FREE Full text] [doi: 10.1186/1472-6823-11-1] [Medline: 21210964] 18. Fiks AG, DuRivage N, Mayne SL, Finch S, Ross ME, Giacomini K, et al. Adoption of a portal for the primary care management of pediatric asthma: a mixed-methods implementation study. J Med Internet Res 2016 Jun 29;18(6):e172 [FREE Full text] [doi: 10.2196/jmir.5610] [Medline: 27357835] 19. Sezgin E, Weiler M, Weiler A, Lin S. Proposing an ecosystem of digital health solutions for teens with chronic conditions transitioning to self-management and independence: exploratory qualitative study. J Med Internet Res 2018 Sep 06;20(9):e10285 [FREE Full text] [doi: 10.2196/10285] [Medline: 30190253] 20. Glatter R. Forbes. 2017. Why Hospitals Are In Pursuit Of The Ideal Amazon Alexa App URL: https://www.forbes.com/ sites/robertglatter/2017/06/26/why-hospitals-are-in-pursuit-of-the-ideal-amazon-alexa-app [accessed 2019-03-03] 21. Palanica A, Thommandram A, Lee A, Li M, Fossat Y. Do you understand the words that are comin outta my mouth? Voice assistant comprehension of medication names. NPJ Digit Med 2019 Jun 20;2(1). [doi: 10.1038/s41746-019-0133-x] 22. Jadczyk T, Kiwic O, Khandwalla RM, Grabowski K, Rudawski S, Magaczewski P, et al. Feasibility of a voice-enabled automated platform for medical data collection: CardioCube. Int J Med Inform 2019 Sep;129:388-393. [doi: 10.1016/j.ijmedinf.2019.07.001] [Medline: 31445282] 23. Sciuto A, Saini A, Forlizzi J, Hong JI. "Hey Alexa, What's Up?": a mixed-methods studies of in-home conversational agent usage. In: Proceedings of the 2018 Designing Interactive Systems Conference. New York: ACM Press; 2018 Presented at: Designing Interactive Systems Conference; June 09-13, 2018; Hong Kong, China URL: http://dl.acm.org/citation. cfm?doid=3196709.3196772 [doi: 10.1145/3196709.3196772] 24. Plantin L, Daneback K. Parenthood, information and support on the internet. A literature review of research on parents and professionals online. BMC Fam Pract 2009 May 18;10:34 [FREE Full text] [doi: 10.1186/1471-2296-10-34] [Medline: 19450251] https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 9 (page number not for citation purposes) XSL FO RenderX JOURNAL OF MEDICAL INTERNET RESEARCH Sezgin et al 25. Kreimeyer K, Foster M, Pandey A, Arya N, Halford G, Jones S, et al. Natural language processing systems for capturing and standardizing unstructured clinical information: a systematic review. J Biomed Inform 2017 Sep;73:14-29 [FREE Full text] [doi: 10.1016/j.jbi.2017.07.012] [Medline: 28729030] 26. Torous J, Kiang MV, Lorme J, Onnela JP. New tools for new research in psychiatry: a scalable and customizable platform to empower data driven smartphone research. JMIR Ment Health 2016 May 05;3(2):e16 [FREE Full text] [doi: 10.2196/mental.5165] [Medline: 27150677] 27. Orbita. 2018. URL: https://tinyurl.com/updj6hx [accessed 2019-03-03] 28. Sezgin E, Militello L, Huang Y, Lin S. A scoping review of patient-facing, behavioral health interventions with voice assistant technology targeting self-management and healthy lifestyle behaviors. Transl Behav Med 2020:1-20 (forthcoming). [doi: 10.1093/tbm/ibz141] 29. Lavallee DC, Chenok KE, Love RM, Petersen C, Holve E, Segal CD, et al. Incorporating patient-reported outcomes into health care to engage patients and enhance care. Health Aff (Millwood) 2016 Apr;35(4):575-582. [doi: 10.1377/hlthaff.2015.1362] [Medline: 27044954] 30. Jha A. The promise of electronic records: around the corner or down the road? J Am Med Assoc 2011 Aug 24;306(8):880-881. [doi: 10.1001/jama.2011.1219] [Medline: 21862751] 31. Gregory ME, Russo E, Singh H. Electronic health record alert-related workload as a predictor of burnout in primary care providers. Appl Clin Inform 2017 Jul 05;8(3):686-697 [FREE Full text] [doi: 10.4338/ACI-2017-01-RA-0003] [Medline: 28678892] 32. Centers for Medicare and Medicaid Services. 2019. Accountable Care Organizations (ACOs) URL: https://www.cms.gov/ Medicare/Medicare-Fee-for-Service-Payment/ACO/index [accessed 2019-03-03] 33. US Food and Drug Administration. 2019 May. Digital Health Innovation Action Plan URL: https://www.fda.gov/ MedicalDevices/DigitalHealth/ [accessed 2019-03-03] Abbreviations AI: artificial intelligence CSHCN: children with special health care needs CMC: children with medical complexity EMR: electronic medical record HIPAA: Health Insurance Portability and Accountability Act MCHB: Maternal and Child Health Bureau NLP: natural language processing Edited by G Eysenbach; submitted 29.03.19; peer-reviewed by M Hoy, J Halamka, E Staton, C Jacob, S D'Arcy, B Gibson; comments to author 06.08.19; revised version received 02.12.19; accepted 16.12.19; published 13.02.20 Please cite as: Sezgin E, Noritz G, Elek A, Conkol K, Rust S, Bailey M, Strouse R, Chandawarkar A, von Sadovszky V, Lin S, Huang Y Capturing At-Home Health and Care Information for Children With Medical Complexity Using Voice Interactive Technologies: Multi-Stakeholder Viewpoint J Med Internet Res 2020;22(2):e14202 URL: https://www.jmir.org/2020/2/e14202 doi: 10.2196/14202 PMID: ©Emre Sezgin, Garey Noritz, Alexander Elek, Kimberly Conkol, Steve Rust, Matthew Bailey, Robert Strouse, Aarti Chandawarkar, Victoria von Sadovszky, Simon Lin, Yungui Huang. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 13.02.2020. This is an open-access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work, first published in the Journal of Medical Internet Research, is properly cited. The complete bibliographic information, a link to the original publication on http://www.jmir.org/, as well as this copyright and license information must be included. https://www.jmir.org/2020/2/e14202 J Med Internet Res 2020 | vol. 22 | iss. 2 | e14202 | p. 10 (page number not for citation purposes) XSL FO RenderX
Journal of Medical Internet Research – Pubmed Central
Published: Feb 13, 2020
It’s your single place to instantly
discover and read the research
that matters to you.
Enjoy affordable access to
over 18 million articles from more than
15,000 peer-reviewed journals.
All for just $49/month
Query the DeepDyve database, plus search all of PubMed and Google Scholar seamlessly
Save any article or search result from DeepDyve, PubMed, and Google Scholar... all in one place.
Get unlimited, online access to over 18 million full-text articles from more than 15,000 scientific journals.
Read from thousands of the leading scholarly journals from SpringerNature, Elsevier, Wiley-Blackwell, Oxford University Press and more.
All the latest content is available, no embargo periods.
“Hi guys, I cannot tell you how much I love this resource. Incredible. I really believe you've hit the nail on the head with this site in regards to solving the research-purchase issue.”Daniel C.
“Whoa! It’s like Spotify but for academic articles.”@Phil_Robichaud
“I must say, @deepdyve is a fabulous solution to the independent researcher's problem of #access to #information.”@deepthiw
“My last article couldn't be possible without the platform @deepdyve that makes journal papers cheaper.”@JoseServera