Ritterhouse, Lauren L.

Abstract Background Laboratory medicine has reached the era where promises of artificial intelligence and machine learning (AI/ML) seem palpable. Currently, the primary responsibility for risk-benefit assessment in clinical practice resides with the medical director. Unfortunately, there is no tool or concept that enables diagnostic quality assessment for the various potential AI/ML applications. Specifically, we noted that an operational definition of laboratory diagnostic quality – for the specific purpose of assessing AI/ML improvements – is currently missing. Methods A session at the 3rd Strategic Conference of the European Federation of Laboratory Medicine in 2022 on “ AI in the Laboratory of the Future” prompted an expert roundtable discussion. Here we present a conceptual diagnostic quality framework for the specific purpose of assessing AI/ML implementations. Results The presented framework is termed diagnostic quality model (DQM) and distinguishes AI/ML improvements at the test, procedure, laboratory, or healthcare ecosystem level. The operational definition illustrates the nested relationship among these levels. The model can help to define relevant objectives for implementation and how levels come together to form coherent diagnostics. The affected levels are referred to as scope and we provide a rubric to quantify AI/ML improvements while complying with existing, mandated regulatory standards. We present 4 relevant clinical scenarios including multi-modal diagnostics and compare the model to existing quality management systems. Conclusions A diagnostic quality model is essential to navigate the complexities of clinical AI/ML implementations. The presented diagnostic quality framework can help to specify and communicate the key implications of AI/ML solutions in laboratory diagnostics.

We describe 22 examples of a novel, usually paratubal, adnexal tumor associated with Peutz-Jeghers syndrome in nearly 50% of cases that harbored STK11 alterations in all tested (n=21). The patients ranged from 17 to 66 years (median=39 y) and the tumors from 4.5 to 25.5 cm (median=11 cm). Most (n=18) were paratubal, with metastases noted in 11/22 (50%) and recurrences in 12/15 (80%). Morphologically, they were characterized by interanastomosing cords and trabeculae of predominantly epithelioid cells, set in a variably prominent myxoid to focally edematous stroma, that often merged to form tubular, cystic, cribriform, and microacinar formations, reminiscent of salivary gland-type tumors. The tumor cells were uniformly atypical, often with prominent nucleoli and a variable mitotic index (median=9/10 HPFs). The tumors were usually positive to a variable extent for epithelial (CAM5.2, AE1/AE3, cytokeratin 7), sex cord (calretinin, inhibin, WT1), and mesothelial (calretinin, D2-40) markers, as well as hormone receptors. PAX8, SF1, and GATA-3 were rarely positive, while claudin-4, FOXL2, and TTF-1 were consistently negative. All sequenced tumors (n=21) harbored alterations in STK11, often with a loss of heterozygosity event. There were no other recurrently mutated genes. Recurrent copy number alterations included loss of 1p and 11q, and gain of 1q, 15q, and 15p. Despite an extensive morphologic, immunohistochemical, and molecular evaluation, we are unable to determine with certainty the histogenesis of this unique tumor. Wolffian, sex cord stromal, epithelial, and mesothelial origins were considered. We propose the term STK11 adnexal tumor to describe this novel entity and emphasize the importance of genetic counseling in these patients as a significant number of neoplasms occur in association with Peutz-Jeghers syndrome.