Dataset Information

Independent real-world application of a clinical-grade automated prostate cancer detection system.

ABSTRACT: Artificial intelligence (AI)-based systems applied to histopathology whole-slide images have the potential to improve patient care through mitigation of challenges posed by diagnostic variability, histopathology caseload, and shortage of pathologists. We sought to define the performance of an AI-based automated prostate cancer detection system, Paige Prostate, when applied to independent real-world data. The algorithm was employed to classify slides into two categories: benign (no further review needed) or suspicious (additional histologic and/or immunohistochemical analysis required). We assessed the sensitivity, specificity, positive predictive values (PPVs), and negative predictive values (NPVs) of a local pathologist, two central pathologists, and Paige Prostate in the diagnosis of 600 transrectal ultrasound-guided prostate needle core biopsy regions ('part-specimens') from 100 consecutive patients, and to ascertain the impact of Paige Prostate on diagnostic accuracy and efficiency. Paige Prostate displayed high sensitivity (0.99; CI 0.96-1.0), NPV (1.0; CI 0.98-1.0), and specificity (0.93; CI 0.90-0.96) at the part-specimen level. At the patient level, Paige Prostate displayed optimal sensitivity (1.0; CI 0.93-1.0) and NPV (1.0; CI 0.91-1.0) at a specificity of 0.78 (CI 0.64-0.89). The 27 part-specimens considered by Paige Prostate as suspicious, whose final diagnosis was benign, were found to comprise atrophy (n = 14), atrophy and apical prostate tissue (n = 1), apical/benign prostate tissue (n = 9), adenosis (n = 2), and post-atrophic hyperplasia (n = 1). Paige Prostate resulted in the identification of four additional patients whose diagnoses were upgraded from benign/suspicious to malignant. Additionally, this AI-based test provided an estimated 65.5% reduction of the diagnostic time for the material analyzed. Given its optimal sensitivity and NPV, Paige Prostate has the potential to be employed for the automated identification of patients whose histologic slides could forgo full histopathologic review. In addition to providing incremental improvements in diagnostic accuracy and efficiency, this AI-based system identified patients whose prostate cancers were not initially diagnosed by three experienced histopathologists. © 2021 The Authors. The Journal of Pathology published by John Wiley & Sons, Ltd. on behalf of The Pathological Society of Great Britain and Ireland.

SUBMITTER: da Silva LM

PROVIDER: S-EPMC8252036 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:Background Explicit documentation of stage is an endorsed quality metric by the National Quality Forum. Clinical and pathological cancer staging is inconsistently recorded within clinical narratives but can be derived from text in the Electronic Health Record (EHR). To address this need, we developed a Natural Language Processing (NLP) solution for extraction of clinical and pathological TNM stages from the clinical notes in prostate cancer patients. Methods Data for patients diagnosed with prostate cancer between 2010 and 2018 were collected from a tertiary care academic healthcare system's EHR records in the United States. This system is linked to the California Cancer Registry, and contains data on diagnosis, histology, cancer stage, treatment and outcomes. A randomly selected sample of patients were manually annotated for stage to establish the ground truth for training and validating the NLP methods. For each patient, a vector representation of clinical text (written in English) was used to train a machine learning model alongside a rule-based model and compared with the ground truth. Results A total of 5,461 prostate cancer patients were identified in the clinical data warehouse and over 30% were missing stage information. Thirty-three to thirty-six percent of patients were missing a clinical stage and the models accurately imputed the stage in 21–32% of cases. Twenty-one percent had a missing pathological stage and using NLP 71% of missing T stages and 56% of missing N stages were imputed. For both clinical and pathological T and N stages, the rule-based NLP approach out-performed the ML approach with a minimum F1 score of 0.71 and 0.40, respectively. For clinical M stage the ML approach out-performed the rule-based model with a minimum F1 score of 0.79 and 0.88, respectively. Conclusions We developed an NLP pipeline to successfully extract clinical and pathological staging information from clinical narratives. Our results can serve as a proof of concept for using NLP to augment clinical and pathological stage reporting in cancer registries and EHRs to enhance the secondary use of these data.

Project description:PURPOSE:Matching patients to investigational therapies requires new tools to support physician decision making. We designed and implemented Precision Insight Support Engine (PRECISE), an automated, just-in-time, clinical-grade informatics platform to identify and dynamically track patients on the basis of molecular and clinical criteria. Real-world use of this tool was analyzed to determine whether PRECISE facilitated enrollment to early-phase, genome-driven trials. MATERIALS AND METHODS:We analyzed patients who were enrolled in genome-driven, early-phase trials using PRECISE at Memorial Sloan Kettering Cancer Center between April 2014 and January 2018. Primary end point was the proportion of enrolled patients who were successfully identified using PRECISE before enrollment. Secondary end points included time from sequencing and PRECISE identification to enrollment. Reasons for a failure to identify genomically matched patients were also explored. RESULTS:Data were analyzed from 41 therapeutic trials led by 19 principal investigators. In total, 755 patients were accrued to these studies during the period that PRECISE was used. PRECISE successfully identified 327 patients (43%) before enrollment. Patients were diagnosed with 29 tumor types and harbored alterations in 43 oncogenes, most commonly ERBB2 (21.3%), PIK3CA (14.1%), and BRAF (8.7%). Median time from sequencing to enrollment was 163 days (interquartile range, 66 to 357 days), and from PRECISE identification to enrollment 87 days (interquartile range, 37 to 180 days). Common reasons for failing to identify patients before enrollment included accrual on the basis of molecular alterations that did not match pre-established PRECISE genomic eligibility (140 [33%] of 428) and external sequencing not available for parsing (127 [30%] of 428). CONCLUSION:PRECISE identified 43% of all patients accrued to a diverse cohort of early-phase, genome-matched studies. Purpose-built informatics platforms represent a novel and potentially effective method for matching patients to molecularly selected studies.

Project description:PurposeNext-generation sequencing (NGS)-based tumor panel testing has been reimbursed by the Korean government since 2017. We evaluated the use of NGS-based tumor panel testing in real-world clinical practice, focusing on molecular profiling (MP)-guided breast cancer treatment.MethodsA total of 137 breast cancer patients underwent NGS panel testing between December 2017 and July 2020 at Seoul National University Bundang Hospital (SNUBH). Samples from patients were profiled using an in-house SNUBH pan-cancer panel. Sixty-four patients were profiled on SNUBH Pan_Cancer v1.0, targeting 89 genes, while 73 patients were profiled on SNUBH Pan_Cancer v2.0, targeting 546 genes.ResultsBreast cancer subtypes included hormone receptor+/human epidermal growth factor receptor 2 (HER2)- (n = 87), triple-negative (n = 44), and HER2+ (n = 6). Most patients had locally advanced or metastatic cancers (92%). Approximately 92% (126/137) of the patients had significant genomic alterations (tiers I and II), and 62% (85/137) had targetable genomic alterations. The most common targetable genomic alterations were PIK3CA (39%) and ESR1 mutations (9%), followed by ERBB2 (7%), PTEN (7%), BRCA2 (6%), and BRCA1 mutations (4%). Of the 81 patients with locally advanced/metastatic breast cancer with targetable genomic alterations, 6 (7.4%) received MP-guided treatments, including PARP inhibitor (n = 4), ERBB2-directed therapy (n = 1), and PI3K inhibitor (n = 1). Among these 6 patients, 4 participated in clinical trials, 1 underwent treatment at their own expense, and 1 received drugs through an expanded access program. The remaining 66 patients (81%) with targetable genomic alteration did not receive MP-guided treatment due to lack of matched drugs and/or clinical trials, poor performance status, and/or financial burden.ConclusionNGS panel testing allowed MP-guided treatment in only 4.7% (6/127) of patients with advanced breast cancer in a real-world setting. The availability of matched drugs is critical for the realistic implementation of personalized treatment.

Dataset Information

Independent real-world application of a clinical-grade automated prostate cancer detection system.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets