Computational pathology in 2030: a Delphi study forecasting the role of AI in pathology within the next decade.

BACKGROUND: Artificial intelligence (AI) is rapidly fuelling a fundamental transformation in the practice of pathology. However, clinical integration remains challenging, with no AI algorithms to date in routine adoption within typical anatomic pathology (AP) laboratories. This survey gathered current expert perspectives and expectations regarding the role of AI in AP from those with first-hand computational pathology and AI experience. METHODS: Perspectives were solicited using the Delphi method from 24 subject matter experts between December 2020 and February 2021 regarding the anticipated role of AI in pathology by the year 2030. The study consisted of three consecutive rounds: 1) an open-ended, free response questionnaire generating a list of survey items; 2) a Likert-scale survey scored by experts and analysed for consensus; and 3) a repeat survey of items not reaching consensus to obtain further expert consensus. FINDINGS: Consensus opinions were reached on 141 of 180 survey items (78.3%). Experts agreed that AI would be routinely and impactfully used within AP laboratory and pathologist clinical workflows by 2030. High consensus was reached on 100 items across nine categories encompassing the impact of AI on (1) pathology key performance indicators (KPIs) and (2) the pathology workforce and specific tasks performed by (3) pathologists and (4) AP lab technicians, as well as (5) specific AI applications and their likelihood of routine use by 2030, (6) AI's role in integrated diagnostics, (7) pathology tasks likely to be fully automated using AI, and (8) regulatory/legal and (9) ethical aspects of AI integration in pathology. INTERPRETATION: This systematic consensus study details the expected short-to-mid-term impact of AI on pathology practice. These findings provide timely and relevant information regarding future care delivery in pathology and raise key practical, ethical, and legal challenges that must be addressed prior to AI's successful clinical implementation. FUNDING: No specific funding was provided for this study.

Decision Support to Enhance Automated Laboratory Testing by Leveraging Analytical Capabilities.

To achieve effective laboratory automation, analytical capabilities must be developed to support data analysis. This allows for effective development and deployment of decision support strategies within the automated laboratory. Practically, these take the form of dashboards, static and real time; workflow processes, such as autoverification; reflex protocols; and testing cascades, which reduce errors of omission and commission. This requires data from the LIS and middleware that enable sophisticated laboratory automation lines. This article addresses the historical, current, and future state of laboratory analytics using examples and offering a framework to organize thinking around analytical capabilities.

The Importance of eSlide Macro Images for Primary Diagnosis with Whole Slide Imaging.

INTRODUCTION: A whole slide image (WSI) is typically comprised of a macro image (low-power snapshot of the entire glass slide) and stacked tiles in a pyramid structure (with the lowest resolution thumbnail at the top). The macro image shows the label and all pieces of tissue on the slide. Many whole slide scanner vendors do not readily show the macro overview to pathologists. We demonstrate that failure to do so may result in a serious misdiagnosis. MATERIALS AND METHODS: Various examples of errors were accumulated that occurred during the digitization of glass slides where the virtual slide differed from the macro image of the original glass slide. Such examples were retrieved from pathology laboratories using different types of scanners in the USA, Canada, Europe, and Asia. RESULTS: The reasons for image errors were categorized into technical problems (e.g., automatic tissue finder failure, image mismatches, and poor scan coverage) and human operator mistakes (e.g., improper manual region of interest selection). These errors were all detected because they were highlighted in the macro image. CONCLUSION: Our experience indicates that WSI can be subject to inadvertent errors related to glitches in scanning slides, corrupt images, or mistakes made by humans when scanning slides. Displaying the macro image that accompanies WSIs is critical from a quality control perspective in digital pathology practice as this can help detect these serious image-related problems and avoid compromised diagnoses.

Career Paths of Pathology Informatics Fellowship Alumni.

BACKGROUND: The alumni of today's Pathology Informatics and Clinical Informatics fellowships fill diverse roles in academia, large health systems, and industry. The evolving training tracks and curriculum of Pathology Informatics fellowships have been well documented. However, less attention has been given to the posttraining experiences of graduates from informatics training programs. Here, we examine the career paths of subspecialty fellowship-trained pathology informaticians. METHODS: Alumni from four Pathology Informatics fellowship training programs were contacted for their voluntary participation in the study. We analyzed various components of training, and the subsequent career paths of Pathology Informatics fellowship alumni using data extracted from alumni provided curriculum vitae. RESULTS: Twenty-three out of twenty-seven alumni contacted contributed to the study. A majority had completed undergraduate study in science, technology, engineering, and math fields and combined track training in anatomic and clinical pathology. Approximately 30% (7/23) completed residency in a program with an in-house Pathology Informatics fellowship. Most completed additional fellowships (15/23) and many also completed advanced degrees (10/23). Common primary posttraining appointments included chief medical informatics officer (3/23), director of Pathology Informatics (10/23), informatics program director (2/23), and various roles in industry (3/23). Many alumni also provide clinical care in addition to their informatics roles (14/23). Pathology Informatics alumni serve on a variety of institutional committees, participate in national informatics organizations, contribute widely to scientific literature, and more than half (13/23) have obtained subspecialty certification in Clinical Informatics to date. CONCLUSIONS: Our analysis highlights several interesting phenomena related to the training and career trajectory of Pathology Informatics fellowship alumni. We note the long training track alumni complete in preparation for their careers. We believe flexible training pathways combining informatics and clinical training may help to alleviate the burden. We highlight the importance of in-house Pathology Informatics fellowships in promoting interest in informatics among residents. We also observe the many important leadership roles in academia, large community health systems, and industry available to early career alumni and believe this reflects a strong market for formally trained informaticians. We hope this analysis will be useful as we continue to develop the informatics fellowships to meet the future needs of our trainees and discipline.

Validation of claims data algorithms to identify nonmelanoma skin cancer.

Health maintenance organization (HMO) administrative databases have been used as sampling frames for ascertaining nonmelanoma skin cancer (NMSC). However, because of the lack of tumor registry information on these cancers, these ascertainment methods have not been previously validated. NMSC cases arising from patients served by a staff model medical group and diagnosed between 1 January 2007 and 31 December 2008 were identified from claims data using three ascertainment strategies. These claims data cases were then compared with NMSC identified using natural language processing (NLP) of electronic pathology reports (EPRs), and sensitivity, specificity, positive and negative predictive values were calculated. Comparison of claims data-ascertained cases with the NLP demonstrated sensitivities ranging from 48 to 65% and specificities from 85 to 98%, with ICD-9-CM ascertainment demonstrating the highest case sensitivity, although the lowest specificity. HMO health plan claims data had a higher specificity than all-payer claims data. A comparison of EPR and clinic log registry cases showed a sensitivity of 98% and a specificity of 99%. Validation of administrative data to ascertain NMSC demonstrates respectable sensitivity and specificity, although NLP ascertainment was superior. There is a substantial difference in cases identified by NLP compared with claims data, suggesting that formal surveillance efforts should be considered.

The Henry Ford Production System: reduction of surgical pathology in-process misidentification defects by bar code-specified work process standardization.

Misidentification defects are a potential patient safety issue in medicine, including in the surgical pathology laboratory. In addressing the Joint Commission's national patient safety goal of accurate patient and specimen identification, we focused our lens internally on our own laboratory processes, with measurement tools designed to identify potential misidentification defects and their root causes. Based on this knowledge, aligned with our lean work culture in the Henry Ford Production System, we redesigned our surgical pathology laboratory workflow with simplified connections and pathways reinforced by a bar code technology innovation to specify and standardize work processes. We also adopted just-in-time prestain slide labeling with solvent-impervious, bar-coded slide labels at the microtome station, eliminating the loop-back pathway of poststain, batch slide matching, and labeling with adhesive paper labels. These changes have enabled us to dramatically reduce the overall misidentification case rate by approximately 62% with an approximate 95% reduction in the more common histologic slide misidentification defects while increasing technical throughput at the histology microtomy station by 125%.

Structuring data in pathology reports: overcoming challenges with new tools.

Traditional pathology reports have been textual with a high degree of variability. Checklist based structured pathology reports contribute significantly towards standardization and error reduction. As implemented, most of these are text templates making data retrieval dependent on natural language search. We describe a toolset that has been used to construct Laboratory Information System (LIS)-integrated checklists with forward chaining inference capabilities and contextual decision support. Data is saved directly into the LIS database facilitating queries and reporting.

Informatics training in pathology residency programs: proposed learning objectives and skill sets for the new millennium.

CONTEXT: To be successful in tomorrow's health care environment, to make the most appropriate decisions for their laboratories, to optimize training and continuing medical education opportunities, and to advance pathology as a professional specialty, pathologists must possess basic informatics knowledge and proficiency. Traditional areas of anatomic and clinical pathology residency training employ learning objectives, knowledge expectations, and skill sets, but such items have not been as well developed or widely implemented for pathology informatics training. OBJECTIVE: We present a proposal that defines a standard and specific set of learning (knowledge) objectives and skill set (proficiency) expectations for resident training in pathology informatics. DESIGN: The proposal includes a comprehensive and detailed set of knowledge applications and proficiencies that will assist residency programs in developing basic pathology informatics training for residents. The content of the proposal is based on and compiled from existing successful pathology informatics training programs. Learning objectives include those related to general and enterprise computing as well as objectives related specifically to pathology informatics. Skill set expectations include the ability to use software that facilitates and adds value to the work of pathologists, including the use of a laboratory information system and of productivity software and other tools. Other topics include guidelines for evaluating residents' informatics competency, suggestions regarding curriculum structure and implementation, and recommendations for residents' computing infrastructure. CONCLUSION: This proposal provides a foundation for building effective and standard curricula for residency training in pathology informatics. These curricula will be able to meet increasing expectations and needs for pathologists to contribute to clinical information management.