Assessment of a large language model's utility in helping pathology professionals answer general knowledge pathology questions.

OBJECTIVES: To assess the utility and performance of the large language model ChatGPT 4.0 regarding accuracy, completeness, and its potential as a time-saving tool for pathologists and laboratory directors. METHODS: A deidentified database of questions previously sent to pathology residents from health care providers was used as a source of general knowledge-type pathology questions. These questions were submitted to the large language model and the responses graded by subject matter experts in different pathology subspecialties. The grading criteria assessed accuracy, completeness, and the potential time savings for helping the pathologist craft the response. RESULTS: Overall, respondents thought that most of the answers would take less than 5 minutes of additional work to be used (85%). Accuracy and completeness for the 61 questions was high, with 98% of responses being at least "completely or mostly accurate" and 82% of responses "containing all relevant information." Of the respondents, 97% stated that the response would have "zero or near-zero potential for medical harm," and all thought the tool had potential to save time in constructing answers to health care providers' queries. Performance was similar in both Anatomic Pathology (AP) and Clinical Pathology (CP), with the only exception being some relevant information was excluded in 46% of AP answers vs only 10% in CP (P < .01). CONCLUSIONS: ChatGPT version 4.0 gave responses that were predominantly accurate and complete for general knowledge-type pathology questions. With further research and when reviewed by a pathologist or laboratorian, this could facilitate its use as a pathologist's aid in answering questions from health care providers.

A generative adversarial network model alternative to animal studies for clinical pathology assessment.

Animal studies are unavoidable in evaluating chemical and drug safety. Generative Adversarial Networks (GANs) can generate synthetic animal data by learning from the legacy animal study results, thus may serve as an alternative approach to assess untested chemicals. AnimalGAN, a GAN method to simulate 38 rat clinical pathology measures, was developed with significant robustness even for the drugs that vary significantly from these used during training, both in terms of chemical structure, drug class, and the year of FDA approval. AnimalGAN showed comparable results in hepatotoxicity assessment as using the real animal data and outperformed 12 conventional quantitative structure-activity relationship approaches. Using AnimalGAN, a virtual experiment of 100,000 rats ranked hepatotoxicity of three structurally similar drugs in a similar trend that has been observed in human population. AnimalGAN represented a significant step with artificial intelligence towards the global effort in replacement, reduction, and refinement (3Rs) of animal use.

Fellowship Board Pass Rates Rising: Analysis of Pathology Subspecialty Board Examination Performance.

CONTEXT.­: The American Board of Pathology (ABPath) publishes annual performance data for the anatomic pathology (AP) and clinical pathology (CP) board examinations, as well as for ABPath subspecialty examinations. Overall board pass rates for all AP and CP board examinees have increased during the past decade; however, no study has analyzed the board pass rates for pathology subspecialty examinations, and whether these follow the same trend. OBJECTIVE.­: To evaluate ABPath subspecialty examination pass rates to assess the trend in certification. DESIGN.­: We analyzed the total number of first-time test takers and board pass rates for 11 pathology subspecialties recognized by the ABPath from 2007 to 2021, acquired from annual reports published by the ABPath. We compared the pass rates in 5-year intervals (2007-2011, 2012-2016, 2017-2021) for each individual specialty. We also analyzed the pass rate of CP subspecialties compared with AP subspecialties. RESULTS.­: The overall mean pass rate for ABPath subspecialty examinations during the previous 15 years was 89% (range, 78.9%-100%), with the overall pass rate being significantly higher in 2017-2021 (P = .02). The contemporary overall rate of passing was significantly higher for AP subspecialty examinations (P < .001) and was higher, though not significantly, for CP subspecialties (P = .13). There were significant differences between first-time test takers' mean pass rate (92.1%), repeat test takers' mean pass rate (54.5%), and the overall rate (P < .001). CONCLUSIONS.­: Contemporary pathology subspecialty board examination pass rates are significantly higher than historic rates, possibly reflecting continuously improving and readily available preparatory materials.

Preanalytic Competency Assessment: A Q-Probes Study Involving 46 Health Care Institutions, 447 Blood Collectors/Phlebotomists, and 2212 Individual Assessments.

CONTEXT.­: Health care organizations face a challenge of assessing preanalytic competency of blood collectors/phlebotomists (BC/Ps). OBJECTIVE.­: To pilot a novel methodology for BC/P preanalytic competency assessment and identify potential areas for improvement. DESIGN.­: Study participants identified preanalytic errors present in 5 blood collection video vignettes. Submitted error descriptions were categorized and then consolidated into a list of standardized required errors for evaluation. RESULTS.­: The correct identification of required error rates across all videos viewed by 447 BC/Ps from 46 institutions ranged from 0.7% to 91.9%. The median phlebotomist score across all 5 videos was 55.9% for 440 eligible blood collectors and ranged between 38.2% (10th percentile) and 70.6% (90th percentile). The median institutional score from 42 eligible institutions was 55.9% (range, 43.3%-65.3% for the 10th to 90th percentiles). There were no significant associations between any laboratory practice characteristics and the institutional average overall phlebotomist scores. The following phlebotomist characteristics were significantly associated with overall phlebotomist scores: level of education (P = .01), having phlebotomy technician (American Society for Clinical Pathology) certification compared with no or other certifications (P = .002), years of experience in collecting blood specimens (P = .01), and higher average number of venipuncture specimens collected per shift (P = .001). CONCLUSIONS.­: Improvement of the awareness and knowledge of correct blood collection practices is needed, because the best performers (90th percentile) did not recognize approximately one-third of the errors. Using hypothetical blood collection scenarios that incorporate performance errors may be a way to assess preanalytic competency of BC/Ps and create opportunities for continuous improvement.

Smartphone adapter time trial analysis: A low-cost, time-efficient method to disseminate quality photomicrographs at the microscope.

BACKGROUND: Within the field of pathology there is a need for a uniform low-cost option for securing high-quality photomicrographs. Advances in smartphone photography and 3D-printing technology allow for custom adapters to be designed for the purpose of photomicrograph capture. METHODS: Photomicrograph acquisition was performed using four core modalities: a novel 3D-printed smartphone-to-microscope adapter, freehand smartphone-to-microscope technique, a commercial adaptor (LabCam Pro), and a microscope-mounted digital camera. Eight skin diagnoses were photographed using each of the modalities and time to image capture was measured. The photomicrographs were blindly reviewed by two academic dermatopathologists and one pathologist using a side-by-side comparison technique to determine the image quality. Cost assessments were evaluated by obtaining free pricing information on manufacturer websites. RESULTS: The 3D-printed adapter was the most efficient method of capturing a high-quality photomicrograph in addition to being budget neutral. The microscope-mounted camera produced the highest quality photomicrographs followed by the 3D-printed adapter. CONCLUSIONS: The 3D-printed smartphone-to-microscope adapter offers a low-cost, time-efficient method of capturing high-quality photomicrographs.

Automated assessment of Ki-67 proliferation index in neuroendocrine tumors by deep learning.

The Ki-67 proliferation index (PI) is a prognostic factor in neuroendocrine tumors (NETs) and defines tumor grade. Analysis of Ki-67 PI requires calculation of Ki-67-positive and Ki-67-negative tumor cells, which is highly subjective. To overcome this, we developed a deep learning-based Ki-67 PI algorithm (KAI) that objectively calculates Ki-67 PI. Our study material consisted of NETs divided into training (n = 39), testing (n = 124), and validation (n = 60) series. All slides were digitized and processed in the Aiforia® Create (Aiforia Technologies, Helsinki, Finland) platform. The ICC between the pathologists and the KAI was 0.89. In 46% of the tumors, the Ki-67 PIs calculated by the pathologists and the KAI were the same. In 12% of the tumors, the Ki-67 PI calculated by the KAI was 1% lower and in 42% of the tumors on average 3% higher. The DL-based Ki-67 PI algorithm yields results similar to human observers. While the algorithm cannot replace the pathologist, it can assist in the laborious Ki-67 PI assessment of NETs. In the future, this approach could be useful in, for example, multi-center clinical trials where objective estimation of Ki-67 PI is crucial.

Use of some cost-effective technologies for a routine clinical pathology laboratory.

Classically, the need for highly sophisticated instruments with important economic costs has been a major limiting factor for clinical pathology laboratories, especially in developing countries. With the aim of making clinical pathology more accessible, a wide variety of free or economical technologies have been developed worldwide in the last few years. 3D printing and Arduino approaches can provide up to 94% economical savings in hardware and instrumentation in comparison to commercial alternatives. The vast selection of point-of-care-tests (POCT) currently available also limits the need for specific instruments or personnel, as they can be used almost anywhere and by anyone. Lastly, there are dozens of free and libre digital tools available in health informatics. This review provides an overview of the state-of-the-art on cost-effective alternatives with applications in routine clinical pathology laboratories. In this context, a variety of technologies including 3D printing and Arduino, lateral flow assays, plasmonic biosensors, and microfluidics, as well as laboratory information systems, are discussed. This review aims to serve as an introduction to different technologies that can make clinical pathology more accessible and, therefore, contribute to achieve universal health coverage.

The utility of digital pathology in improving the diagnostic skills of pathology trainees in commonly encountered pigmented cutaneous lesions during the COVID-19 pandemic: A single academic institution experience.

Digital pathology has become an integral part of pathology education in recent years, particularly during the COVID-19 pandemic, for its potential utility as a teaching tool that augments the traditional 1-to-1 sign-out experience. Herein, we evaluate the utility of whole slide imaging (WSI) in reducing diagnostic errors in pigmented cutaneous lesions by pathology fellows without subspecialty training in dermatopathology. Ten cases of 4 pigmented cutaneous lesions commonly encountered by general pathologists were selected. Corresponding whole slide images were distributed to our fellows, along with two sets of online surveys, each composed of 10 multiple-choice questions with 4 answers. Identical cases were used for both surveys to minimize variability in trainees' scores depending on the perceived level of difficulty, with the second set being distributed after random shuffling. Brief image-based teaching slides as self-assessment tool were provided to trainees between each survey. Pre- and post-self-assessment scores were analyzed. 61% (17/28) and 39% (11/28) of fellows completed the first and second surveys, respectively. The mean score in the first survey was 5.2/10. The mean score in the second survey following self-assessment increased to 7.2/10. 64% (7/11) of trainees showed an improvement in their scores, with 1 trainee improving his/her score by 8 points. No fellow scored less post-self-assessment than on the initial assessment. The difference in individual scores between two surveys was statistically significant (p = 0.003). Our study demonstrates the utility of WSI-based self-assessment learning as a source of improving diagnostic skills of pathology trainees in a short period of time.

Improving Ki67 assessment concordance by the use of an artificial intelligence-empowered microscope: a multi-institutional ring study.

AIMS: The nuclear proliferation biomarker Ki67 plays potential prognostic and predictive roles in breast cancer treatment. However, the lack of interpathologist consistency in Ki67 assessment limits the clinical use of Ki67. The aim of this article was to report a solution utilising an artificial intelligence (AI)-empowered microscope to improve Ki67 scoring concordance. METHODS AND RESULTS: We developed an AI-empowered microscope in which the conventional microscope was equipped with AI algorithms, and AI results were provided to pathologists in real time through augmented reality. We recruited 30 pathologists with various experience levels from five institutes to assess the Ki67 labelling index on 100 Ki67-stained slides from invasive breast cancer patients. In the first round, pathologists conducted visual assessment on a conventional microscope; in the second round, they were assisted with reference cards; and in the third round, they were assisted with an AI-empowered microscope. Experienced pathologists had better reproducibility and accuracy [intraclass correlation coefficient (ICC) = 0.864, mean error = 8.25%] than inexperienced pathologists (ICC = 0.807, mean error = 11.0%) in visual assessment. Moreover, with reference cards, inexperienced pathologists (ICC = 0.836, mean error = 10.7%) and experienced pathologists (ICC = 0.875, mean error = 7.56%) improved their reproducibility and accuracy. Finally, both experienced pathologists (ICC = 0.937, mean error = 4.36%) and inexperienced pathologists (ICC = 0.923, mean error = 4.71%) improved the reproducibility and accuracy significantly with the AI-empowered microscope. CONCLUSION: The AI-empowered microscope allows seamless integration of the AI solution into the clinical workflow, and helps pathologists to obtain higher consistency and accuracy for Ki67 assessment.

[Assessment of aptitude for anatomic-clinic correlation in pediatric pathology]. / Evaluación de la aptitud para la correlación anatomo-clínica en patología pediátrica.

Introduction: In the 18th Century, Giovanni Battista Morgagni demonstrated that localized injuries to different organs caused a great variety of clinical symptoms and signs. Since then, medical practice has evolved considerably and maintains the correlation of pathological changes with the signs and symptoms of the disease as part of the academic activity known as "anatomic-clinical session". The evaluation of the aptitude for the anatomic-clinical correlation has not been empirically estimated in pediatric pathology. Objective: Construct and validate an evaluation instrument to quantitatively estimate the aptitude for the anatomical-clinical correlation in pediatric pathology (AA-CCPP). Method: Analytical cross-sectional study. An evaluation instrument was constructed with 90 true, false and I don't know type statements, grouped based on three indicators: I, diagnostic integration; II, identification of pathogenic mechanisms and III, identification of clinical and paraclinical data. The instrument was applied to three groups of residents. The Kruskal-Wallis test was used to compare the results between the groups. Results: The AA-CCPP grade was very low in most residents. When comparing the global scores between the different groups, the pediatric pathology group was the highest. The indicator that obtained the best results was that of Diagnostic Integration. Conclusions: The level of development of the AA-CCPP observed allows us to deduce that the learning strategy known as clinical-pathological conference should be strengthened.

Introducción: En el siglo xviii, Giovanni Battista Morgagni demostró que las lesiones localizadas en diferentes órganos condicionaban gran variedad de síntomas y signos clínicos. Desde entonces, la práctica médica evolucionó considerablemente y conserva la correlación de los cambios anatomopatológicos con los signos y síntomas de la enfermedad como parte de la actividad académica conocida como «sesión anatomoclínica¼. La evaluación de la aptitud para la correlación anatomo-clínica no ha sido estimada empíricamente en patología pediátrica. Objetivo: Construir y validar un instrumento de evaluación para estimar de manera cuatitativa la aptitud para la correlación anatomo-clínica en patología pediátrica (ACA-CPP). Método: Estudio tranversal analítico. Se construyó un instrumento de evaluación con 90 enunciados tipo verdadero, falso y no sé, agrupados en tres indicadores: I) integración diagnóstica; II) identificación de mecanismos patogénicos; y III) identificación de datos clínicos y paraclínicos. Se aplicó el instrumento a tres grupos de residentes. Para comparar los resultados entre los grupos se utilizó la prueba de Kruskal-Wallis. Resultados: El grado de ACA-CPP fue muy bajo en la mayoría de los residentes. Al comparar las puntuaciones globables entre los diferentes grupos, el de patología pediátrica fue el más alto. El indicador que obtuvo mejores resultados fue el de integración diagnóstica. Conclusiones: El nivel de desarrollo de la ACA-CPP observado permite deducir que la estrategia de aprendizaje conocida como sesión anatomo-clínica debe fortalecerse.

Highlights and Perspectives From a Collaborative Global Health Pathology Experience in Trinidad and Tobago.

OBJECTIVES: Global health education is important during residency training in exposing doctors to conditions that are not common in the United States and developing their awareness of global health care disparities. Most medical decisions are based on results from anatomic or clinical pathology laboratories, which are essential services for appropriate medical care in international settings. Nevertheless, US pathology residency trainees have limited global health exposure and thus are rarely exposed to diagnostic services in these settings. Moreover, literature documenting what is needed to create a global health elective in pathology is limited. METHODS: We designed an international pathology elective in Trinidad and Tobago involving one main public hospital site and several off-site laboratories. Objectives and goals were established before the rotation. Apart from daily mentor-led education sessions, the trainee participated in teaching, quality improvement projects, and cultural experiences. Engagement with medical officers, personnel staff, and people in the community was encouraged.Results: Challenges encountered included funding, transportation, limited laboratory resources, medical registration, and malpractice insurance. These were mitigated through carefully planned steps, including communicating with registration bodies and liaising with pathology organizations for funding. CONCLUSIONS: Overall, the global health rotation was successful. We provide a detailed roadmap for other pathology training programs interested in establishing similar global health electives.

Laboratory medicine: The exemplar for value-based healthcare.

Value-Based Healthcare (VBHC) aims to improve the overall quality, safety, and sustainability of healthcare while reducing delivery costs of more effective care. Despite advantages associated with VBHC transformation, the road to its adoption has been lengthy. Laboratory Medicine (LM) is in a prime position to lead the transition to VBHC because of its key role in diagnosis and treatment of patients. Laboratory medicine results inform/influence 50% to 70% of all clinical decisions. This article summarizes some issues associated with adoption of VBHC and related healthcare innovations and suggests potential approaches using LM-specific examples to help accelerate adoption. Laboratory medicine is both a useful model for VBHC implementation and facilitator for related innovation adoption by helping to target patient populations that would benefit most from specific interventions. The critical value of rapidly adopted diagnostic technologies used during the COVID-19 pandemic and economic recovery provide important insights about the need to embrace and accelerate VBHC implementation.

A Department-Sponsored, Hospital-Based Pathology Education Symposium Is a Cost-Effective Method to Provide Laboratory Staff With Highly Rated Continuing Education Experiences.

CONTEXT.­: Continuing education improves the quality of medical care and is a required part of most health care professions. Although a variety of educational modules are available online or at external conferences, completion of these activities can be expensive and time-consuming. In addition, externally produced modules may have limited applicability to a local practice. OBJECTIVE.­: To assess the ability of an economically efficient, locally produced, department-wide pathology educational seminar to efficiently meet education requirements for a large number of employees in a large health system. DESIGN.­: A multiday continuing education symposium was produced annually from 2013 through 2019 at no cost to participants. Metrics related to attendance, number of educational sessions available for registration, and participant satisfaction were tabulated, trended, and compared with similar metrics tabulated from an external continuing education conference that was offered from 2011 through 2012. RESULTS.­: The production of an internal, hospital-based educational symposium increased employee attendance (mean of 635 attendees per year versus 247 at the external program; P < .001) while reducing mean annual cost per attendee ($51 versus $140, P < .001). The number of sessions produced for the internal symposium was 39 per year on average, compared with 12 per year at the external program. Technical staff, residents, fellows, and faculty all contributed to internal educational programming, helping to build a team culture in the department. Overall employee satisfaction was 96.2%. CONCLUSIONS.­: An internal educational pathology symposium led to cost-efficient distribution of continuing education credits to a large number of technical staff, with a high degree of reported employee satisfaction.

Establishment of a remote diagnostic histopathology service using whole slide imaging (digital pathology).

BACKGROUND: Whole slide imaging (WSI) has diverse applications in modern pathology practice, including providing histopathology services to remote locations. MATERIALS AND METHODS: Utilising an existing contractual partnership with a Northern Ontario group of hospitals, the feasibility of using WSI for primary diagnostic services from Toronto was explored by the dedicated working group. All aspects explored from information technology (IT), laboratory information system (LIS) integration, scanning needs, laboratory workflow and pathologist needs and training, were taken into account in the developing the rationale and business case. RESULTS: The financial outlay for a scanner was $CA180K (approximately £105.6 k) after discounts. There were no human resource requirements as staff were reorganised to cater for slide scanning. Additional IT/LIS costs were not incurred as existing connectivity was adapted to allow two site groups (gastrointestinal and skin) to pilot this study. Scanned slides were available for pathologist review 24-96 hours sooner than glass slides; there was a 2-day improvement for final authorised cases, and per annum savings were: $CA26 000 (£15.2 k) in courier costs, $CA60 000 (£35.2 k) travel and $CA45 000 (£26.4 k) in accommodation, meals and car rental expense. CONCLUSION: WSI is a viable solution to provide timely, high-quality and cost efficient histopathology services to underserviced, remote areas.

American Society for Clinical Pathology's 2019 Wage Survey of Medical Laboratories in the United States.

OBJECTIVES: To inform the pathology and laboratory field of the most recent national wage data. Historically, the results of this biennial survey have served as a basis for additional research on laboratory recruitment, retention, education, marketing, certification, and advocacy. METHODS: The 2019 Wage Survey was conducted through collaboration of the American Society for Clinical Pathology (ASCP) Institute of Science, Technology, and Policy in Washington, DC, and the ASCP Board of Certification in Chicago, Illinois. RESULTS: Compared with 2017, results show an overall increase in salaries for most laboratory occupations surveyed except cytogenetic technologists, laboratory information systems personnel, and performance improvement or quality assurance personnel. Geographically, laboratory professionals from urban areas earned more than their rural counterparts. CONCLUSIONS: As retirement rates continue to increase, the field needs to intensify its efforts on recruiting the next generation of laboratory personnel. To do so, the report urged the field to highlight advocacy for better salaries for laboratory personnel at the local and national levels when developing recruitment and retention strategies.

Dialogs in the assessment of neonatal cholestatic liver disease.

Neonatal cholestatic liver disease is rarely encountered by pathologists outside of specialized pediatric centers and navigating the long list of potential diseases can be daunting. However, the differential diagnosis can be rapidly narrowed through open conversations between the pathologist and pediatric gastroenterologist. The dialog should ideally begin before obtaining the liver biopsy and continue through the rendering of the final pathologic diagnosis. Such dialogs are necessary to first ensure the proper handling of the precious sample and then to allow for synthesis of the clinical, laboratory, imaging, and genetic data in the context of the histologic features seen in the liver biopsy. In this review, we aim to provide a broad template on which such dialogs may be based and pitfalls that may be encountered on both the clinical and pathologic sides. This review will focus on non-biliary atresia etiologies of neonatal cholestasis, including select infectious, genetic, and metabolic entities.