Bui, Marilyn M.

Context.— Machine learning applications in the pathology clinical domain are emerging rapidly. As decision support systems continue to mature, laboratories will increasingly need guidance to evaluate their performance in clinical practice. Currently there are no formal guidelines to assist pathology laboratories in verification and/or validation of such systems. These recommendations are being proposed for the evaluation of machine learning systems in the clinical practice of pathology. Objective.— To propose recommendations for performance evaluation of in vitro diagnostic tests on patient samples that incorporate machine learning as part of the preanalytical, analytical, or postanalytical phases of the laboratory workflow. Topics described include considerations for machine learning model evaluation including risk assessment, predeployment requirements, data sourcing and curation, verification and validation, change control management, human-computer interaction, practitioner training, and competency evaluation. Data Sources.— An expert panel performed a review of the literature, Clinical and Laboratory Standards Institute guidance, and laboratory and government regulatory frameworks. Conclusions.— Review of the literature and existing documents enabled the development of proposed recommendations. This white paper pertains to performance evaluation of machine learning systems intended to be implemented for clinical patient testing. Further studies with real-world clinical data are encouraged to support these proposed recommendations. Performance evaluation of machine learning models is critical to verification and/or validation of in vitro diagnostic tests using machine learning intended for clinical practice.

Gastrointestinal stromal tumors (GIST) are the most common type of soft tissue sarcoma that occur throughout the gastrointestinal tract. Most of these tumors are caused by oncogenic activating mutations in the KIT or PDGFRA genes. The NCCN Guidelines for GIST provide recommendations for the diagnosis, evaluation, treatment, and follow-up of patients with these tumors. These NCCN Guidelines Insights summarize the panel discussion behind recent important updates to the guidelines, including revised systemic therapy options for unresectable, progressive, or metastatic GIST based on mutational status, and updated recommendations for the management of GIST that develop resistance to specific tyrosine kinase inhibitors.

Soft tissue sarcomas (STS) are rare malignancies of mesenchymal cell origin that display a heterogenous mix of clinical and pathologic characteristics. STS can develop from fat, muscle, nerves, blood vessels, and other connective tissues. The evaluation and treatment of patients with STS requires a multidisciplinary team with demonstrated expertise in the management of these tumors. The complete NCCN Clinical Practice Guidelines in Oncology (NCCN Guidelines) for Soft Tissue Sarcoma provide recommendations for the diagnosis, evaluation, and treatment of extremity/superficial trunk/head and neck STS, as well as retroperitoneal/intra-abdominal STS, desmoid tumors, and rhabdomyosarcoma. This portion of the NCCN Guidelines discusses general principles for the diagnosis and treatment of retroperitoneal/intra-abdominal STS, outlines treatment recommendations, and reviews the evidence to support the guidelines recommendations.

The NCCN Guidelines for Soft Tissue Sarcoma provide recommendations for the diagnosis, evaluation, treatment, and follow-up for patients with soft tissue sarcomas. These NCCN Guidelines Insights summarize the panel discussion behind recent important updates to the guidelines, including the development of a separate and distinct guideline for gastrointestinal stromal tumors (GISTs); reconception of the management of desmoid tumors; inclusion of further recommendations for the diagnosis and management of extremity/body wall, head/neck sarcomas, and retroperitoneal sarcomas; modification and addition of systemic therapy regimens for sarcoma subtypes; and revision of the principles of radiation therapy for soft tissue sarcomas.

Context Although primary bone tumors are extremely rare, the literature suggests that there are variations in the epidemiologic characteristics in different populations. The most frequently cited epidemiologic characteristics of primary bone tumors are derived from a large US series (Mayo Clinic), with no comparable study thus far performed in China. Objective To identify any potential epidemiologic differences between Chinese patients and a US series of patients. Design We performed a comparison study between 9200 patients treated at Beijing Ji Shui Tan Hospital (JST) and 10 165 patients treated at Mayo Clinic (MC), Rochester Minnesota. Detailed epidemiologic features were analyzed. Results We found that giant cell tumor and osteosarcoma have significantly higher incidences in the JST than the MC patients (P < .001). However, JST patients had a significantly lower incidence of Ewing sarcoma, chordoma, fibrosarcoma, myeloma, and malignant lymphoma (P < .001). For most benign and malignant bone tumors, the Chinese cohort had a more distinct male predominance than the US cohort. Malignant bone tumors had a monomodal age distribution in the JST patient group, with a bimodal age distribution in the MC cohort. Also, there were was a predilection for tumors of the femur and tibia among the JST patients (P < .001). Conclusions Our data confirm that epidemiologic variations of primary bone tumors exist in different populations. Factors that may contribute to these observed differences are proposed and discussed.