Establishing priorities for implementation of large language models in pathology and laboratory medicine.

Artificial intelligence and machine learning have numerous applications in pathology and laboratory medicine. The release of ChatGPT prompted speculation regarding the potentially transformative role of large-language models (LLMs) in academic pathology, laboratory medicine, and pathology education. Because of the potential to improve LLMs over the upcoming years, pathology and laboratory medicine clinicians are encouraged to embrace this technology, identify pathways by which LLMs may support our missions in education, clinical practice, and research, participate in the refinement of AI modalities, and design user-friendly interfaces that integrate these tools into our most important workflows. Challenges regarding the use of LLMs, which have already received considerable attention in a general sense, are also reviewed herein within the context of the pathology field and are important to consider as LLM applications are identified and operationalized.

Direct Secure Messaging in Practice: Addressing Workflow Challenges.

Direct Secure Messaging (DSM) is a sender-initiated communication technology for exchanging patient-specific information among clinicians and disparate healthcare organizations. As DSM adoption increases it becomes more difficult for clinicians and staff to manage the volume and variety of external data received. This can lead to information hazards that can produce cognitive overload and decrease the ability of clinicians to process patient data when reviewing multiple sources. While DSM is one of many options for electronically exchanging health information, we have found that poor user awareness of DSM features and variable EHR capabilities for sending, receiving, and managing messages and their contents demonstrate that additional work is needed to achieve DSM's potential as a low-barrier, ubiquitous option for clinical interoperability. This paper reviews these problems from end-user perspective and offers best-practices for both senders and recipients of DSM.

Governance of Electronic Health Record Modification at U.S. Academic Medical Centers.

OBJECTIVES: A key aspect of electronic health record (EHR) governance involves the approach to EHR modification. We report a descriptive study to characterize EHR governance at academic medical centers (AMCs) across the United States. METHODS: We conducted interviews with the Chief Medical Information Officers of 18 AMCs about the process of EHR modification for standard requests. Recordings of the interviews were analyzed to identify categories within prespecified domains. Responses were then assigned to categories for each domain. RESULTS: At our AMCs, EHR requests were governed variably, with a similar number of sites using quantitative scoring systems (7, 38.9%), qualitative systems (5, 27.8%), or no scoring system (6, 33.3%). Two (11%) organizations formally review all requests for their impact on health equity. Although 14 (78%) organizations have trained physician builders/architects, their primary role was not for EHR build. Most commonly reported governance challenges included request volume (11, 61%), integrating diverse clinician input (3, 17%), and stakeholder buy-in (3, 17%). The slowest step in the process was clarifying end user requests (14, 78%). Few leaders had identified metrics for the success of EHR governance. CONCLUSION: Governance approaches for managing EHR modification at AMCs are highly variable, which suggests ongoing efforts to balance EHR standardization and maintenance burden, while dealing with a high volume of requests. Developing metrics to capture the performance of governance and quantify problems may be a key step in identifying best practices.

Effect of Recent Abortion Legislation on Twitter User Engagement, Sentiment, and Expressions of Trust in Clinicians and Privacy of Health Information: Content Analysis.

BACKGROUND: The Supreme Court ruling in Dobbs v Jackson Women's Health Organization (Dobbs) overrules precedents established by Roe v Wade and Planned Parenthood v Casey and allows states to individually regulate access to abortion care services. While many states have passed laws to protect access to abortion services since the ruling, the ruling has also triggered the enforcement of existing laws and the creation of new ones that ban or restrict abortion. In addition to denying patients the full spectrum of reproductive health care, one major concern in the medical community is how the ruling will undermine trust in the patient-clinician relationship by influencing perceptions of the privacy of patient health information. OBJECTIVE: This study aimed to study the effect of recent abortion legislation on Twitter user engagement, sentiment, expressions of trust in clinicians, and privacy of health information. METHODS: We scraped tweets containing keywords of interest between January 1, 2020, and October 17, 2022, to capture tweets posted before and after the leak of the Supreme Court decision. We then trained a Latent Dirichlet Allocation model to select tweets pertinent to the topic of interest and performed a sentiment analysis using Robustly Optimized Bidirectional Encoder Representations from Transformers Pre-training Approach model and a causal impact time series analysis to examine engagement and sentiment. In addition, we used a Word2Vec model to study the terms of interest against a latent trust dimension to capture how expressions of trust for our terms of interest changed over time and used term frequency, inverse-document frequency to measure the volume of tweets before and after the decision with respect to the negative and positive sentiments that map to our terms of interest. RESULTS: Our study revealed (1) a transient increase in the number of daily users by 576.86% (95% CI 545.34%-607.92%; P<.001), tweeting about abortion, health care, and privacy of health information postdecision leak; (2) a sustained and statistically significant decrease in the average daily sentiment on these topics by 19.81% (95% CI -22.98% to -16.59%; P=.001) postdecision leak; (3) a decrease in the association of the latent dimension of trust across most clinician-related and health information-related terms of interest; (4) an increased frequency of tweets with these clinician-related and health information-related terms and concomitant negative sentiment in the postdecision leak period. CONCLUSIONS: The study suggests that the Dobbs ruling has consequences for health systems and reproductive health care that extend beyond denying patients access to the full spectrum of reproductive health services. The finding of a decrease in the expression of trust in clinicians and health information-related terms provides evidence to support advocacy and initiatives that proactively address concerns of trust in health systems and services.

Laboratory Results Release to Patients under the 21st Century Cures Act: The Eight Stakeholders Who Should Care.

A major aim of the 21st Century Cures Act is to support patients' access to their electronic health data and to prevent information blocking practices by health care organizations and health information technology developers. Prior to the Cures Act, significant variation existed in patient access to laboratory test results, key pieces of health data which enable timely self-management and engagement in care. Although many health care systems began releasing test results immediately through patient portals because of the Cures Act, implementation remains challenging due to variations in state regulations around electronic results release, local interpretations of allowable exceptions to Cures information blocking, concerns about privacy of sensitive laboratory results, and technological limitations. This paper outlines the eight stakeholder groups involved in implementation of electronic laboratory result release to patients and describes recommendations for these groups to consider in achieving the Cures Act goals to support a patient's access to their health information and control of their health care.

Development and Implementation of a Standard Format for Clinical Laboratory Test Results.

OBJECTIVES: Surprisingly, laboratory results, the principal output of clinical laboratories, are not standardized. Thus, laboratories frequently report results with identical meaning in different formats. For example, laboratories report a positive pregnancy test as "+," "P," or "Positive." To assess the feasibility of a widespread implementation of a result standard, we (1) developed a standard result format for common laboratory tests and (2) implemented a feedback system for clinical laboratories to view their unstandardized results. METHODS: In the largest integrated health care system in America, 130 facilities had the opportunity to collaboratively develop the standard. For 15 weeks, clinical laboratories received a weekly report of their unstandardized results. At the study's conclusion, laboratories were compared with themselves and their peers by metrics that reflected their unstandardized results. RESULTS: We rereviewed 156 million test results and observed a 51% decline in the rate of unstandardized results. The number of facilities with fewer than 23 unstandardized results per 100,000 (Six Sigma σ > 5) increased by 58% (52 to 82 facilities; ß = 1.79; P < .001). CONCLUSIONS: This study demonstrated significant improvement in the standardization of clinical laboratory results in a relatively short time. The laboratory community should create and promulgate a standardized result format.

Searching Full-Text Anatomic Pathology Reports Using Business Intelligence Software.

Although the laboratory information system has largely solved the problem of storing anatomic pathology reports and disseminating their contents across the healthcare system, the retrospective query of anatomic pathology reports remains an area for improvement across laboratory information system vendors. Our institution desired the ability to query our repository of anatomic pathology reports for clinical, operational, research, and educational purposes. To address this need, we developed a full-text anatomic pathology search tool using the business intelligence software, Tableau. Our search tool allows users to query the 333,685 anatomic pathology reports from our institutional clinical relational database using the business intelligence tool's built-in regular expression functionality. Users securely access the search tool using any web browser, thereby avoiding the cost of installing or maintaining software on users' computers. This tool is laboratory information system vendor agnostic and as many institutions already subscribe to business intelligence software, we believe this solution could be easily reproduced at other institutions and in other clinical departments.

The 21st Century Cures Act and Multiuser Electronic Health Record Access: Potential Pitfalls of Information Release.

Although the Office of The National Coordinator for Health Information Technology's (ONC) Information Blocking Provision in the Cures Act Final Rule is an important step forward in providing patients free and unfettered access to their electronic health information (EHI), in the contexts of multiuser electronic health record (EHR) access and proxy access, concerns on the potential for harm in adolescent care contexts exist. We describe how the provision could erode patients' (both adolescent and older patients alike) trust and willingness to seek care. The rule's preventing harm exception does not apply to situations where the patient is a minor and the health care provider wishes to restrict a parent's or guardian's access to the minor's EHI to avoid violating the minor's confidentiality and potentially harming patient-clinician trust. This may violate previously developed government principles in the design and implementation of EHRs for pediatric care. Creating legally acceptable workarounds by means such as duplicate "shadow charting" will be burdensome (and prohibitive) for health care providers. Under the privacy exception, patients have the opportunity to request information to not be shared; however, depending on institutional practices, providers and patients may have limited awareness of this exception. Notably, the privacy exception states that providers cannot "improperly encourage or induce a patient's request to block information." Fearing being found in violation of the information blocking provisions, providers may feel that they are unable to guide patients navigating the release of their EHI in the multiuser or proxy access setting. ONC should provide more detailed guidance on their website and targeted outreach to providers and their specialty organizations that care for adolescents and other individuals affected by the Cures Act, and researchers should carefully monitor charting habits in these multiuser or proxy access situations.

Clinical and Biologic Characteristics and Outcomes in Young and Middle-Aged Patients With Laryngeal Cancer: A Retrospective Cohort Analysis.

OBJECTIVE: To describe the clinical and biologic characteristics and outcomes of young and middle-aged (YMA; <65 years) patients according to the presence or absence of traditional risk factors for laryngeal cancer. STUDY DESIGN: Retrospective cohort analysis. SETTING: Single-institution academic medical center. METHODS: Patients without a history of clinically significant tobacco use or heavy alcohol use were defined as "nontraditional": ≤5 pack-years, ≤5 years smoked, ≤14 alcoholic drinks per week, and ≥15-year interval from last tobacco abuse use to diagnosis. Remaining patients were categorized as "traditional." Select tumor samples were evaluated for bacterial and viral DNA by multiplex polymerase chain reaction. RESULTS: Seventy-eight YMA patients with primary laryngeal squamous cell carcinoma were identified, 23% (n = 18) of whom were nontraditional. Nontraditional patients were younger than traditional patients (median age, 51 vs 59 years; P < .001). Twenty-eight tumors were prospectively tested for human papillomavirus (HPV), and nontraditional patients were more likely to exhibit high-risk HPV (57% vs 5%, P < .01). Among 17 select tumors (nontraditional, n = 8; traditional, n = 9), 35% exhibited HPV16 (nontraditional, 63%; traditional, 11%; P = .05). Other viruses were identified but did not differ according to risk status: herpesviruses (40%) and Merkel cell polyomavirus (7%). Chlamydia, ß-HPV, and γ-HPV DNA was not detected in any samples. Median length of follow-up was 42 months. On adjusted analyses, nontraditional patients exhibited nonsignificantly improved overall survival (hazard ratio, 0.24 [95% CI, 0.03-1.82]; P = .17) and disease-free survival (hazard ratio, 0.34 [95% CI, 0.10-1.23]; P = .08) as compared with traditional patients. CONCLUSION: Almost one-quarter of YMA patients lacked characteristic risk factors for laryngeal squamous cell carcinoma, and their tumors exhibited a higher prevalence of high-risk HPV. The significance of HPV16 and other tumor viruses with outcomes in nontraditional patients should be evaluated further.

Survey of Hospital Chargemaster Transparency.

BACKGROUND: In January 2019, the Centers for Medicare & Medicaid Services (CMS) required hospitals to list their standard charges (chargemasters) publicly in an effort to increase price transparency in health care. Surveying hospital chargemasters may be informative to assess the implementation of this rule and its utility to consumers. OBJECTIVE: We aimed to compare hospital chargemaster data within a local hospital market where patients would reasonably try to shop or compare services. METHODS: We identified and aggregated Dallas County hospital chargemasters available in a database compatible format in May 2019. We manually examined a convenience sampling of 10 common laboratory tests, medications, and procedures. RESULTS: Thirteen hospital chargemasters were identified. Eleven hospitals had chargemasters available in a database compatible format (xlsx or csv). These 11 chargemasters were aggregated into a single file containing 155,576 chargeable items, prices, and descriptions. We observed heterogeneous names and descriptions of synonymous items across institutions, preventing automated comparisons. The examined items revealed a high variation in charges. The largest charge variation for laboratory tests examined included a 2,606% difference (partial thromboplastin time: $18.70-506.00), for medications an 18,617% difference (5-mg tablet of amlodipine: $0.23-43.05), and for procedures a 2,889% difference (circumcision: $252.00-7,532.10). One institution accounted for 27% of the lowest prices and another accounted for 60% of the highest prices. CONCLUSION: Chargemaster data presentation varied among the hospitals surveyed, making automatic comparison impossible. Chargemaster data are difficult to interpret for health care decisions. Refining the minimum requirements for publishing chargemaster data could increase their utility.

Smart Glasses as a Surgical Pathology Grossing Tool.

CONTEXT.­: Smart glasses are a wearable technology that enable hands-free data acquisition and entry. OBJECTIVE.­: To develop a surgical pathology grossing application on a smart glass platform. DESIGN.­: An existing logistics software for the Google Glass Enterprise smart glass platform was used to create surgical pathology grossing protocols. The 2 grossing protocols were developed to simulate grossing a complex (heart) and a simple (kidney) specimen. For both protocols, users were visually prompted by the smart glass device to perform each task, record measurements, or document the field of view. In addition to measuring the total time of the protocol performance, each substep within the protocol was automatically recorded. Subsequently, a report was generated that contained the dictation, images, voice recordings, and the timing of each step. The application was tested by 3 users using the 2 grossing protocols. The users were tracked across 3 grossing procedures for each protocol. RESULTS.­: For the complex specimen grossing the average time across repeated procedures was not significantly different between users (P > .99). However, when grossing times of the complex specimen were compared for repeated performances of the same user, a significant reduction in grossing times was observed with each repetition (P = .002). For the simple specimen, the average grossing time across multiple attempts was different among users (P = .03); however, no improvement in grossing time was observed with repeated performance (P = .499). CONCLUSIONS.­: Augmented reality based grossing applications can provide automated data collection to track the changes in grossing performance over time.

Medicare Trends in Pathologist Participation, Service Utilization, and Payments.

OBJECTIVES: Quantifying pathologist participation in Medicare services may be informative for the prediction of future workforce needs and reimbursement. METHODS: A retrospective examination was performed of pathologist professional (Part B) Medicare billings and payments from 2012 to 2017. The Medicare Provider Utilization and Payment Data: Physician and Other Supplier Public Use File was the primary data source. RESULTS: From 2012 to 2017, there was an increase (3.7%; 11,215 up to 11,627) in pathologists providing Medicare Part B services. Female pathologists increased from 36.10% to 40.8% of pathologists during this time period. Normalized per pathologist, there was an increase (7.8%; 1,382 up to 1,489) in beneficiaries served as well as an increase (4.1%; 2,442 up to 2,543) in services performed. The top 10 pathology Part B services performed in a facility were all surgical pathology. Although services increased, the overall payment of Part B pathology services decreased (3%; $996,519,358 down to $966,615,856) during the study period. CONCLUSIONS: Although there is increasing pathologist participation in Medicare, the workload per pathologist has increased.