Challenges in Communication from Referring Clinicians to Pathologists in the Electronic Health Record Era

Abstract

We report on the role played by electronic health record inbox messages (EHRmsg) in a safety event involving pathology. Evolving socio-cultural norms led to the coopting of EHRmsg for alternate use and oversight of a clinician to pathologist request. We retrospectively examined EHR inbox messages to pathologists over a 3 month block. 36 messages from 22 pathologists were assessed. 26 pertained to patient care including requests for report corrections and additional testing. 88% of requests had gone unaddressed. Clinicians assumed that pathologists used EHRmsg as clinical care team members, however, pathologists rarely did. Communication gaps exist between primary clinicians and pathologists in the EHR era and they have potential to result in patient harm. Different sociocultural norms and practice patterns between specialties underlie some of the breakdowns. Health information technology implementation needs to proactively look for new sociotechnical failure modes to avoid patient harm from communication lapses.

Physician and Surgeon Communication Assessed via the Pathology Requisition in a Regional Laboratory Over Ten Years

“…The computerization of medical records presents ongoing challenges and opportunities in communication with pathology [ 17 ]. Measuring communication is becoming easier with the further computerization of medical records.…”

Deep Learning Approaches in Histopathology

“…Bearing in mind the divergent patterns of lung adenocarcinoma cell growth that have been linked to patient clinical results, the CNN model designed by Gertych et al [ 50 ] and Wei et al [ 51 ] was used to classify every single image tile considering the pattern of growth for each individual and produce a likelihood map for the WSI, making it easier for pathologists to describe the principal and malignant elements of lung adenocarcinoma, including papillary, micropapillary, solid, and acinar components, quantitatively. Cervical squamous cell carcinoma, colorectal polyp [ 13 ], thyroid tumor [ 58 ], ovarian cancer [ 62 ], and breast tumor [ 21 ] were all multi-classified using a DL-based AI. This ability allowed the AI-based models to identify the different lung cancer histological subtypes with a precision of 60% to 89% based on cytological images [ 48 ].…”

“…An AI-based model could detect the presence of programmed death-ligand 1 (PD-L1; positive or negative) by using hematoxylin and eosin (H&E)-stained images of adenocarcinoma or squamous carcinoma lung cancers with an AUC of 0.80. The result was reasonable compared to pathologist assessments depending on PD-L1 immunohistochemistry images to identify possible patients who may have sensitivity to pembrolizumab medication [ 13 ]. A DL-based AI model evaluated biomarkers engaged in the prognosis, diagnosis, and prediction of drug interactions depending on immunohistochemical dye or fluorescent dye WSIs and HE dye WSIs.…”

“…Barbieri et al found in their designed algorithm for colorectal cancer detection that the developed model reduces the time of diagnosis by almost half. Moreover, the algorithm reduced the computational cost by four times less than the typical normal diagnosis process while maintaining a 94.8% higher output result [ 13 ]. Finally, DL models offer more advanced processor technology, allowing more accurate diagnostic abilities in a shorter time [ 14 ].…”

Classification Of X-ray COVID-19 Image Using Convolutional Neural Network

“…In the development and application of systems to automatically classify, especially in the medical field, it is rapidly growing and gaining popularity by making additional medical practitioners' tools [11]- [13]. Deep learning, an artificial intelligence (AI) research area, enables modelling using input data without the need for manual feature extraction.…”