Influenza Screening Using Patient-Generated Health Data in Post COVID-19 Pandemic

It is very important to ensure reliable performance of deep learning model for future dataset for healthcare. This is more pronounced in the case of patient generated health data such as patient reported symptoms, which are not collected in a controlled environment. Since there has been a big difference in influenza incidence since the COVID-19 pandemic, we evaluated whether the deep learning model can maintain sufficiently robust performance against these changes. We have collected 226,655 episodes from 110,893 users since June 2020 and tested the influenza screening model, our model showed 87.02% sensitivity and 0.8670 of AUROC. The results of COVID-19 pandemic are comparable to that of before COVID-19 pandemic.

Navigating the Search for Patient Generated Health Data

With massive amounts of mobile health data generated by patients, there is a growing amount of research conducted to understand their impact on patient care. The MeSH heading for patient generated health data was established in early 2018, complicating searches for PGHD research prior to 2018. In conducting a search of scientific databases, keywords are presented along with their degree of representation in the literature to help inform future searches.

Incorporating patient-generated contextual data into care: Clinician perspectives using the Consolidated Framework for Implementation Science

Patient contextual data (PCD), defined as patient's values, environment, or behavior influencing health, are essential to the proper care of patients, yet often are missing in the electronic health record (EHR). The current EHR structures and practice demands produce barriers to document PCD systemically. We sought to understand clinicians' perceived facilitators and barriers to use PCD using a consumer informatics technology integrated into the EHR. The PCD components include patient perceived pressures; joys; preferred approach to care; perceived health; health-goals; and visit agenda. We conducted semi-structured interviews of twenty primary care clinicians from an academic health system implementing a PCD initiative. The analysis included an inductive approach and a deductive a priori framework, the Consolidated Framework for Implementation Research (CFIR). Clinicians identified the following facilitators of adoption: reinforcement of patient engagement; a focus on enhancing team-based care; and communication around how the tool can be incorporated for individualized care. Clinicians identified barriers as: challenges incorporating PCD into the time-compressed visit and reviewing the tool involved another click in the EHR. The deductive results spanned four domains and seven constructs of CFIR, principally finding intervention source, relative advantage, organizational needs, and relative priority as facilitators with a need for ongoing leadership for the culture change. Overall, clinicians supported the adoption of a consumer informatics technology, as they reflected on the perceived value of a new data source to enhance patient-centered care and involvement in the development process. User-focused optimization efforts aided in the improved functionality and adoption of the application.

Cancer survivor perspectives on sharing patient-generated health data with central cancer registries

PURPOSE

Central cancer registries collect data and provide population-level statistics that can be tracked over time; yet registries may not capture the full range of clinically relevant outcomes. Patient-generated health data (PGHD) include health/treatment history, biometrics, and patient-reported outcomes (PROs). Collection of PGHD would broaden registry outcomes to better inform research, policy, and care. However, this is dependent on the willingness of patients to share such data. This study examines cancer survivors' perspectives about sharing PGHD with central cancer registries.

METHODS

Three U.S. central registries sampled colorectal, non-Hodgkin lymphoma, and metastatic breast cancer survivors 1-4 years after diagnosis, recruiting them via mail to participate in one of seven focus groups (n = 52). Group discussions were recorded, transcribed, and thematically analyzed.

RESULTS

Most survivor-participants were unaware of the existence of registries. After having registries explained, all participants expressed their willingness to share PGHD with them if treated confidentially. Participants were willing to provide information on a variety of topics (e.g., medical history, medications, symptoms, financial difficulties, quality of life, biometrics, nutrition, exercise, and mental health), with a focus on long-term effects of cancer and its treatment. Participants' preferred mode for providing data varied. Participants were also interested in receiving information from registries.

CONCLUSIONS

Our results suggest that registry-based collection of PGHD is acceptable to most cancer survivors and could facilitate registry-based efforts to collect PGHD/PROs. Central cancer registry-based collection of PGHD/PROs, especially on long-term effects, could enhance registry support of cancer control efforts including research and population health management.

Exchanging personal health data with electronic health records: A standardized information model for patient generated health data and observations of daily living

OBJECTIVE

The development of a middleware information model to facilitate better interoperability between Personal and Electronic Health Record systems in order to allow exchange of Patient Generated Health Data and Observations of Daily Leaving between patients and providers in order to encourage patient self-management.

MATERIALS AND METHODS

An information model based on HL7 standards for interoperability has been extended to support PGHD and ODL data types. The new information models uses HL7 CDA to represent data, is instantiated as a Protégé ontology and uses a set of mapping rules to transfer data between Personal and Electronic Health Record systems.

RESULTS

The information model was evaluated by executing a set of use case scenarios containing data exported from three consumer health apps, transformed to CDA according to developed mapping rules and validated against a CDA schema. This allowed various challenges to emerge as well as revealed gaps in current standards in use and the information model has been refined accordingly.

DISCUSSION AND CONCLUSION

Our proposed middleware solution offers a number of advantages. When modifications are made to either a Personal or Health Electronic Health Record system or any integrated consumer app, they can be incorporated by altering only the instantiation of the information model. Our proposition uses current standards in use such as CDA. The solution is applicable to any EHR system with HL7 CDA support.

Customization of the TRU-PBMT App (Technology Recordings to better Understand Pediatric Blood and Marrow Transplant)

PURPOSE

Our investigative team is integrating mobile health technologies into pediatric blood and marrow transplant (PBMT) care. We aim to evaluate whether patient-generated health data can be used to monitor health status and enhance symptom management. While there are numerous health-related apps, none address the symptoms or care needs specific to PBMT patients. This article describes development of the Technology Recording to better Understand Pediatric Blood and Marrow Transplant (TRU-PBMT) mobile application.

DESIGN AND METHODS

A one-time survey was distributed to PBMT clinicians, caregivers, and outpatients to elicit feedback and suggestions for the app's design.

RESULTS

Feedback from clinicians (n = 23), caregivers (n = 5), and PBMT outpatients (n = 4) indicated the app would be acceptable and useable with this group of patients between eight and eighteen years of age. Suggestions from respondents included: making the app language and graphics more child-friendly; adding symptoms such as fatigue, mucositis, bleeding; and a visual stool chart.

CONCLUSION

Patient, caregiver, and clinician feedback was valuable in creation of the TRU-PBMT app. We designed a pediatric friendly, PBMT-symptom-specific app, which we will test in future studies.

IMPLICATIONS FOR PRACTICE

This app facilitates patient-generated health data collection and informs health care plans.

OVERCOMING THE BARRIERS TO ACHIEVING UNIVERSAL HEALTH CARE IN THE ASIAN REGION

OBJECTIVES

The Health Technology Assessment International (HTAi) Asia Policy Forum (HAPF) met to discuss the challenges of achieving universal health care (UHC) in Asia.

METHODS

Group discussions and presentations at the 2017 HAPF, informed by a background paper, including a literature review and the results of pre-meeting surveys of health technology assessment (HTA) agencies and industry, formed the basis of this article.

RESULTS

Affordability was identified as the greatest barrier to establishing UHC; however, other impediments include the lack of political will to implement UHC, and the cultural issue of deference to expert opinion instead of evidence-based assessments. Although HTA was identified as an important prioritization tool when adding new technologies to benefit packages, it is used inconsistently in the region, resulting in a less transparent decision-making process for stakeholders. Although regional challenges exist around real-world data (RWD), including a lack of capacity to enable information and data sharing, most policy or funding decision makers in the region have access to data. However, there appears to be a disconnect with the experience of industry, whose representatives identify the lack of RWD as their primary issue. To overcome these issues, both HTA agencies and industry agree that collaboration and transparency should be fostered to support the development of robust evidence generation in the region.

CONCLUSIONS

There is a willingness for HTA agencies and industry to collaborate to develop HTA methodology for the prioritization of technologies in the Asia region that support healthcare systems to achieve the ultimate outcome of UHC.