The Compelling Need for Shared Responsibility of AI Oversight: Lessons From Health IT Certification.

This Viewpoint highlights the potential for artificial intelligence (AI) health care tools to introduce unintended patient harm; calls for an efficient, rigorous approach to AI testing and certification that is the shared responsibility of developers and users; and makes recommendations to inform such an approach.

Translating Between Standardization and Local Fit in Health Information Technology.

The design of health information technology (HIT) requires balancing standardization and local adjustment. Preliminary study findings show that interactions between stakeholder shared attention and HIT translational 'boundary object' features ensure that HIT serves diverse stakeholders' purposes and needs. This can support subsequent implementation and patient safety.

Challenges and practices identification in complex outsourcing relationships: A systematic literature review.

Complex IT outsourcing relationships aptitude several benefits such as increased cost likelihood and lowered costs, higher scalability and flexibility upon demand. However, by virtue of its complexity, the complex outsourcing typically necessitates the interactions among various stakeholders from diverse regions and cultures, making it significantly more challenging to manage than traditional outsourcing. Furthermore, when compared to other types of outsourcing, complex outsourcing is extremely difficult because it necessitates a variety of control and coordination mechanisms for project management, which proportionally increases the risk of project failure. In order to overcome the failure of projects in complex outsourcing relationships, there is a need of robust systematic research to identify the key challenges and practices in this area. Therefore, this research implements systematic literature review as a research method and works as a pioneer attempt to accomplish the aforementioned objectives. Upon furnishing the SLR results, the authors identified 11 major challenges with 67 practices in hand from a total of 85 papers. Based on these findings, the authors intend to construct a comprehensive framework in the future by incorporating robust methodologies such as AHP and fuzzy logic, among others.

Patient Empowerment During the COVID-19 Pandemic by Ensuring Safe and Fast Communication of Test Results: Implementation and Performance of a Tracking System.

BACKGROUND: Overcoming the COVID-19 crisis requires new ideas and strategies for online communication of personal medical information and patient empowerment. Rapid testing of a large number of subjects is essential for monitoring and delaying the spread of SARS-CoV-2 in order to mitigate the pandemic's consequences. People who do not know that they are infected may not stay in quarantine and, thus, risk infecting others. Unfortunately, the massive number of COVID-19 tests performed is challenging for both laboratories and the units that conduct throat swabs and communicate the results. OBJECTIVE: The goal of this study was to reduce the communication burden for health care professionals. We developed a secure and easy-to-use tracking system to report COVID-19 test results online that is simple to understand for the tested subjects as soon as these results become available. Instead of personal calls, the system updates the status and the results of the tests automatically. This aims to reduce the delay when informing testees about their results and, consequently, to slow down the virus spread. METHODS: The application in this study draws on an existing tracking tool. With this open-source and browser-based online tracking system, we aim to minimize the time required to inform the tested person and the testing units (eg, hospitals or the public health care system). The system can be integrated into the clinical workflow with very modest effort and avoids excessive load to telephone hotlines. RESULTS: The test statuses and results are published on a secured webpage, enabling regular status checks by patients; status checks are performed without the use of smartphones, which has some importance, as smartphone usage diminishes with age. Stress tests and statistics show the performance of our software. CTest is currently running at two university hospitals in Germany-University Hospital Ulm and University Hospital Tübingen-with thousands of tests being performed each week. Results show a mean number of 10 (SD 2.8) views per testee. CONCLUSIONS: CTest runs independently of existing infrastructures, aims at straightforward integration, and aims for the safe transmission of information. The system is easy to use for testees. QR (Quick Response) code links allow for quick access to the test results. The mean number of views per entry indicates a reduced amount of time for both health care professionals and testees. The system is quite generic and can be extended and adapted to other communication tasks.

"Ask a Doctor About Coronavirus": How Physicians on Social Media Can Provide Valid Health Information During a Pandemic.

In the wake of the COVID-19 pandemic, the information stream has overflowed with accurate information, misinformation, and constantly changing guidelines. There is a great need for guidance on the identification of trustworthy health information, and official channels are struggling to keep pace with this infodemic. Consequently, a Facebook group was created where volunteer medical physicians would answer laypeople's questions about the 2019 novel coronavirus. There is not much precedence in health care professional-driven Facebook groups, and the framework was thus developed continuously. We ended up with an approach without room for debate, which fostered a sense of calmness, trust, and safety among the questioners. Substantial moderator effort was needed to ensure high quality and consistency through collaboration among the presently >200 physicians participating in this group. At the time of writing, the group provides a much-needed service to >58,000 people in Denmark during this crisis.

Evaluation of Online Information on Complementary and Alternative Treatments for Dry Eye Disease.

SIGNIFICANCE: Dry eye disease is a common condition with many complementary and alternative therapies promoted online. Patients may inquire about these therapies, and clinicians should be aware of the existence, safety, and efficacy of these therapies, as well as the quality of available online information. PURPOSE: Complementary and alternative medicine is a multibillion-dollar industry with increasing popularity. Dry eye disease is a chronic condition with many complementary and alternative therapies described online. Patients may inquire about and elect to forgo conventional treatments in favor of these therapies. This study identified alternative treatments for dry eye disease described online and evaluated the Web sites that described them. METHODS: An Internet search algorithm identified Web sites describing complementary and alternative therapies for dry eye disease. Web site quality was assessed using the Sandvik score to evaluate Web site ownership, authorship, source, currency, interactivity, navigability, and balance. The potential risk of Web sites to patients was assessed using a risk scoring system. A list of described therapies was compiled. RESULTS: Eight Web sites describing complementary and alternative therapies for dry eye disease were assessed. The Sandvik score classified more than half of the Web sites as "satisfactory" and none as "poor." The overall mean risk score was low at 0.9. One Web site displayed information that discouraged the use of conventional medicine, whereas no Web sites discouraged adhering to clinicians' advice. The Web sites listed 12 therapies with a further 32 found in Web site comments. The most common therapies were acupuncture, vitamin supplements, homeopathic eye drops, castor oil, coconut oil, and chamomile eye wash. CONCLUSIONS: The majority of analyzed Web sites were of satisfactory quality with a low potential risk to patients. However, some Web sites were biased toward their own therapies, lacked proper referencing, and/or did not identify authorship. Further research is required to ascertain the efficacy and safety of these therapies.

Outcomes of a health informatics technology-supported behavioral activation training for care managers in a collaborative care program.

INTRODUCTION: Health informatics-supported strategies for training and ongoing support may aid the delivery of evidence-based psychotherapies. The objective of this study was to describe the development, implementation, and practice outcomes of a scalable health informatics-supported training program for behavioral activation for patients who screened positive for posttraumatic stress disorder and/or bipolar disorder. METHOD: We trained 34 care managers in 12 rural health centers. They used a registry checklist to document the delivery of 10 behavioral activation skills for 4,632 sessions with 455 patients. Care managers received performance feedback based on registry data. Using encounter-level data reported by care managers, we described the implementation outcomes of patient reach and care manager skill adoption. We used cross-classified multilevel modeling to explore variation in skill delivery accounting for patient characteristics, provider characteristics, and change over time. RESULTS: Care managers engaged 88% of patients in behavioral activation and completed a minimum course for 57%. The average patient received 5.9 skills during treatment, with substantial variation driven more by providers (63%) than patients (29%). Care managers significantly increased the range of skills offered to patients over time. DISCUSSION: The registry-based checklist was a feasible training and support tool for community-based providers to deliver behavioral activation. Providers received data-driven performance feedback and demonstrated skill improvement over time, promoting sustainment. Future research will examine patient-level outcomes. Results underscore the potential public health impact of a simple registry-based skills checklist coupled with a scalable remote training program for evidence-based psychotherapy. (PsycInfo Database Record (c) 2021 APA, all rights reserved).

Impact of health information technology optimization on clinical quality performance in health centers: A national cross-sectional study.

BACKGROUND: Delivery of preventive care and chronic disease management are key components of a high functioning primary care practice. Health Centers (HCs) funded by the Health Resources and Services Administration (HRSA) have been delivering affordable and accessible primary health care to patients in underserved communities for over fifty years. This study examines the association between health center organization's health information technology (IT) optimization and clinical quality performance. METHODS AND FINDINGS: Using 2016 Uniform Data System (UDS) data, we performed bivariate and multivariate analyses to study the association of Meaningful Use (MU) attestation as a proxy for health IT optimization, patient centered medical home (PCMH) recognition status, and practice size on performance of twelve electronically specified clinical quality measures (eCQMs). Bivariate analysis demonstrated performance of eleven out of the twelve preventive and chronic care eCQMs was higher among HCs attesting to MU Stage 2 or above. Multivariate analysis demonstrated that Stage 2 MU or above, PCMH status, and larger practice size were positively associated with performance on cancer screening, smoking cessation counseling and pediatric weight assessment and counseling eCQMs. CONCLUSIONS: Organizational advancement in MU stages has led to improved quality of care that augments HCs patient care capacity for disease prevention, health promotion, and chronic care management. However, rapid technological advancement in health care acts as a potential source of disparity, as considerable resources needed to optimize the electronic health record (EHR) and to undertake PCMH transformation are found more commonly among larger HCs practices. Smaller practices may lack the financial, human and educational assets to implement and to maintain EHR technology. Accordingly, targeted approaches to support small HCs practices in leveraging economies of scale for health IT optimization, clinical decision support, and clinical workflow enhancements are critical for practices to thrive in the dynamic value-based payment environment.

A Sociotechnical Framework for Safety-Related Electronic Health Record Research Reporting: The SAFER Reporting Framework.

Electronic health record (EHR)-based interventions to improve patient safety are complex and sensitive to who, what, where, why, when, and how they are delivered. Success or failure depends not only on the characteristics and behaviors of individuals who are targeted by an intervention, but also on the technical characteristics of the intervention and the culture and environment of the health system that implements it. Current reporting guidelines do not capture the complexity of sociotechnical factors (technical and nontechnical factors, such as workflow and organizational issues) that confound or influence these interventions. This article proposes a methodological reporting framework for EHR interventions targeting patient safety and builds on an 8-dimension sociotechnical model previously developed by the authors for design, development, implementation, use, and evaluation of health information technology. The Safety-related EHR Research (SAFER) Reporting Framework enables reporting of patient safety-focused EHR-based interventions while accounting for the multifaceted, dynamic sociotechnical context affecting intervention implementation, effectiveness, and generalizability. As an example, an EHR-based intervention to improve communication and timely follow-up of subcritical abnormal test results to operationalize the framework is presented. For each dimension, reporting should include what sociotechnical changes were made to implement an EHR-related intervention to improve patient safety, why the intervention did or did not lead to safety improvements, and how this intervention can be applied or exported to other health care organizations. A foundational list of research and reporting recommendations to address implementation, effectiveness, and generalizability of EHR-based interventions needed to effectively reduce preventable patient harm is provided. The SAFER Reporting Framework is not meant to replace previous research reporting guidelines, but rather provides a sociotechnical adjunct that complements their use.

Domains, tasks, and knowledge for health informatics practice: results of a practice analysis.

OBJECTIVE: To develop a comprehensive and current description of what health informatics (HI) professionals do and what they need to know. MATERIALS AND METHODS: Six independent subject-matter expert panels drawn from and representative of HI professionals contributed to the development of a draft HI delineation of practice (DoP). An online survey was distributed to HI professionals to validate the draft DoP. A total of 1011 HI practitioners completed the survey. Survey respondents provided domain, task, knowledge and skill (KS) ratings, qualitative feedback on the completeness of the DoP, and detailed professional background and demographic information. RESULTS: This practice analysis resulted in a validated, comprehensive, and contemporary DoP comprising 5 domains, 74 tasks, and 144 KS statements. DISCUSSION: The HI practice analysis defined "health informatics professionals" to include practitioners with clinical (eg, dentistry, nursing, pharmacy), public health, and HI or computer science training. The affirmation of the DoP by reviewers and survey respondents reflects the emergence of a core set of tasks performed and KSs used by informaticians representing a broad spectrum of those currently practicing in the field. CONCLUSION: The HI practice analysis represents the first time that HI professionals have been surveyed to validate a description of their practice. The resulting HI DoP is an important milestone in the maturation of HI as a profession and will inform HI certification, accreditation, and education activities.

YouTube as a source of information on COVID-19 and rheumatic disease link.

INTRODUCTION/OBJECTIVES: The current 2019 novel coronavirus outbreak is continuing to spread rapidly despite all efforts. Patients with rheumatic disease may have higher levels of anxiety due to their disease characteristics and medications. The web-based platforms are widely used sources for gaining medical information. YouTube presents a wide range of medical information, but there are concerns on its quality. Therefore, we aimed to evaluate the quality of the YouTube videos about COVID-19 and rheumatic diseases link. METHOD: This is a descriptive study. A total of 360 videos listed by the YouTube search engine (www.youtube.com) in response to six search terms were evaluated. The Global Quality Scale (GQS) was performed to evaluate video quality. Three groups were formed according to GQS scores: high quality, moderate quality, and low quality. Video parameters were compared between these groups. RESULTS: After the exclusion criteria, 46 videos were reviewed. Of the videos, 41.4% (n = 19) were of high-quality group, 21.7% (n = 10) were moderate-quality group, and 36.9% (n = 17) were of low-quality group. Significant difference was detected between the quality groups in terms of views per day (p = 0.004). No significant difference was detected in comments per day (p = 0.139) and like ratio (p = 0.232). CONCLUSIONS: Besides high-quality videos, there were substantially low-quality videos that could cause misleading information to spread rapidly during the pandemic. Videos from trustworthy sources such as universities, academics, and physicians should be kept in the foreground.Key Points•Web-based platforms have become an important source of health-related information. One of the most important online sources is YouTube because it is easy accessible and free.•Of the videos evaluating the link between COVID-19 and rheumatic diseases, 41.4% (n = 19) were of high quality.•The main sources of high-quality videos were academics/universities and physicians.•The most frequently discussed topics in videos were the place of hydroxychloroquine in the treatment of COVID-19 and whether to continue the use of existing rheumatological drugs.

Detecting modeling inconsistencies in SNOMED CT using a machine learning technique.

SNOMED CT is a comprehensive and evolving clinical reference terminology that has been widely adopted as a common vocabulary to promote interoperability between Electronic Health Records. Owing to its importance in healthcare, quality assurance becomes an integral part of the lifecycle of SNOMED CT. While, manual auditing of every concept in SNOMED CT is difficult and labor intensive, identifying inconsistencies in the modeling of concepts without any context can be challenging. Algorithmic techniques are needed to identify modeling inconsistencies, if any, in SNOMED CT. This study proposes a context-based, machine learning quality assurance technique to identify concepts in SNOMED CT that may be in need of auditing. The Clinical Finding and the Procedure hierarchies are used as a testbed to check the efficacy of the method. Results of auditing show that the method identified inconsistencies in 72% of the concept pairs that were deemed inconsistent by the algorithm. The method is shown to be effective in both maximizing the yield of correction, as well as providing a context to identify the inconsistencies. Such methods, along with SNOMED International's own efforts, can greatly help reduce inconsistencies in SNOMED CT.

The Implementation Chasm Hindering Genome-informed Health Care.

The promises of precision medicine are often heralded in the medical and lay literature, but routine integration of genomics in clinical practice is still limited. While the "last mile' infrastructure to bring genomics to the bedside has been demonstrated in some healthcare settings, a number of challenges remain - both in the receptivity of today's health system and in its technical and educational readiness to respond to this evolution in care. To improve the impact of genomics on health and disease management, we will need to integrate both new knowledge and new care processes into existing workflows. This change will be onerous and time-consuming, but hopefully valuable to the provision of high quality, economically feasible care worldwide.

Developing an FHIR-Based Computational Pipeline for Automatic Population of Case Report Forms for Colorectal Cancer Clinical Trials Using Electronic Health Records.

PURPOSE: The Fast Healthcare Interoperability Resources (FHIR) is emerging as a next-generation standards framework developed by HL7 for exchanging electronic health care data. The modeling capability of FHIR in standardizing cancer data has been gaining increasing attention by the cancer research informatics community. However, few studies have been conducted to examine the capability of FHIR in electronic data capture (EDC) applications for effective cancer clinical trials. The objective of this study was to design, develop, and evaluate an FHIR-based method that enables the automation of the case report forms (CRFs) population for cancer clinical trials using real-world electronic health records (EHRs). MATERIALS AND METHODS: We developed an FHIR-based computational pipeline of EDC with a case study for modeling colorectal cancer trials. We first leveraged an existing FHIR-based cancer profile to represent EHR data of patients with colorectal cancer, and then we used the FHIR Questionnaire and QuestionnaireResponse resources to represent the CRFs and their data population. To test the accuracy of and overall quality of the computational pipeline, we used synoptic reports of 287 Mayo Clinic patients with colorectal cancer from 2013 to 2019 with standard measures of precision, recall, and F1 score. RESULTS: Using the computational pipeline, a total of 1,037 synoptic reports were successfully converted as the instances of the FHIR-based cancer profile. The average accuracy for converting all data elements (excluding tumor perforation) of the cancer profile was 0.99, using 200 randomly selected records. The average F1 score for populating nine questions of the CRFs in a real-world colorectal cancer trial was 0.95, using 100 randomly selected records. CONCLUSION: We demonstrated that it is feasible to populate CRFs with EHR data in an automated manner with satisfactory performance. The outcome of the study provides helpful insight into future directions in implementing FHIR-based EDC applications for modern cancer clinical trials.

Expert-augmented machine learning.

Machine learning is proving invaluable across disciplines. However, its success is often limited by the quality and quantity of available data, while its adoption is limited by the level of trust afforded by given models. Human vs. machine performance is commonly compared empirically to decide whether a certain task should be performed by a computer or an expert. In reality, the optimal learning strategy may involve combining the complementary strengths of humans and machines. Here, we present expert-augmented machine learning (EAML), an automated method that guides the extraction of expert knowledge and its integration into machine-learned models. We used a large dataset of intensive-care patient data to derive 126 decision rules that predict hospital mortality. Using an online platform, we asked 15 clinicians to assess the relative risk of the subpopulation defined by each rule compared to the total sample. We compared the clinician-assessed risk to the empirical risk and found that, while clinicians agreed with the data in most cases, there were notable exceptions where they overestimated or underestimated the true risk. Studying the rules with greatest disagreement, we identified problems with the training data, including one miscoded variable and one hidden confounder. Filtering the rules based on the extent of disagreement between clinician-assessed risk and empirical risk, we improved performance on out-of-sample data and were able to train with less data. EAML provides a platform for automated creation of problem-specific priors, which help build robust and dependable machine-learning models in critical applications.