Dermatopathologists' concerns and challenges with clinical information in the skin biopsy requisition form: a mixed-methods study

Expanding and Strengthening Your Referral Network

Dermatology referral utilization is increasing, with 15% of dermatology-related visits by primary care resulting in a dermatology referral. Given this, both strengthening an expanding a referral is a key component of a successful dermatology practice. In particular, effective communication is essential for efficient patient-oriented coordinated care. Written and/or verbal communication can help build a strong communication network and, in some instances, can be applied toward Merit-based Incentive Payment System (MIPS) reporting and billing for coding families that incorporate the coordination of care. Reaching out directly to referring clinics has also been shown to increase the quantity of referrals. This can include providing clinics with patient handouts on your clinic, education on what information is prioritized within the referral, and educating staff on how to complete their referrals effectively and efficiently. Social media can play an important role in referrals, especially for patients looking for cosmetic care. There are many different platforms, and these can serve as a marketing tool for physicians looking to bring in new patients.

What Your Dermatopathologist Wants You to Know

The skin biopsy and histologic examination are an important part of providing dermatologic care. Effective communication with your dermatopathologist on the biopsy requisition form helps provide clinicopathological correlation and facilitates accurate and timely histopathologic diagnosis of the biopsy.

A Clinico-Pathological Multidisciplinary Team Increases the Efficacy of Skin Biopsy and Reduces Clinical Risk in Dermatology

A clinical risk is an inherent risk in healthcare processes, including skin biopsy procedures, and may lead to misdiagnoses, increased healthcare costs and potential harm to patients. Indeed, clinical and histopathological data must be integrated if we are to reduce clinical risks and improve diagnostic accuracy in the diagnosis of dermatologic diseases. Although dermopathology services used to be part of a dermatologist's duty, the recent centralization of these laboratories has caused a loss of expertise and increased both complexity and safety issues. Some countries have implemented clinical-pathological correlation programs aimed at facilitating communication between clinicians and dermatopathologists. However, Italy has regulatory and cultural barriers that make the implementation of these programs difficult. Therefore, an internal analysis was carried out to assess the efficacy and impact that skin biopsy procedures for inflammatory and neoplastic conditions have on the quality of care in our dermatology department. As the analysis evidenced a high number of descriptive pathologic reports and discordant diagnoses, a multidisciplinary group of four dermatologists, four general pathologists and one dermatopathologist was set up. Herein, we present the results of this analysis and project and describe the structure of the multidisciplinary group. We also discuss the pros and cons, possibilities and limitations of our project, including the regulatory barriers of the Italian National Health System.

Deep multimodal fusion of image and non-image data in disease diagnosis and prognosis: a review

The rapid development of diagnostic technologies in healthcare is leading to higher requirements for physicians to handle and integrate the heterogeneous, yet complementary data that are produced during routine practice. For instance, the personalized diagnosis and treatment planning for a single cancer patient relies on various images (e.g. radiology, pathology and camera images) and non-image data (e.g. clinical data and genomic data). However, such decision-making procedures can be subjective, qualitative, and have large inter-subject variabilities. With the recent advances in multimodal deep learning technologies, an increasingly large number of efforts have been devoted to a key question: how do we extract and aggregate multimodal information to ultimately provide more objective, quantitative computer-aided clinical decision making? This paper reviews the recent studies on dealing with such a question. Briefly, this review will include the (a) overview of current multimodal learning workflows, (b) summarization of multimodal fusion methods, (c) discussion of the performance, (d) applications in disease diagnosis and prognosis, and (e) challenges and future directions.

After the Discontinuation of Step 2 CS: A Collaborative Statement from the Directors of Clinical Skills Education (DOCS)

Issue: The United States Medical Licensing Exam (USMLE) Step 2 Clinical Skills Examination (Step 2 CS), the only clinical skills competency testing required for licensure in the United States, has been discontinued. Evidence: This exam, though controversial, propelled a movement emphasizing the value of clinical skills instruction and assessment in undergraduate medical education. While disappointed by the loss of this national driver that facilitated standardization of clinical skills education, the Directors of Clinical Skills Education (DOCS) see prospects for educational innovation and growth. DOCS is a national organization and inclusive community of clinical skills education leaders. This statement from DOCS regarding the discontinuation of USMLE Step 2 CS has been informed by DOCS meetings, listserv discussions, an internal survey, and a review of recent literature. Implications: Rigorous clinical skills assessment remains central to effective and patient-centered healthcare. DOCS shares specific concerns as well as potential solutions. Now free from the external pressure to prepare students for success on Step 2 CS, clinical skills educators can reprioritize content and restructure clinical skills programs to best meet the needs of learners and the ever-evolving healthcare landscape. DOCS, as an organization of clinical skills leaders, makes the following recommendations: 1) Collaboration amongst institutions must be prioritized; clinical skills assessment consortia should be expanded. 2) Governing, accrediting, and licensing organizations should leverage their influence to support and require high quality clinical skills assessments. 3) UME clinical skills leaders should develop ways to identify students who perform with exceptional, borderline, and poor clinical skills at their local institutions. 4) UME leadership should fully commit resources and curricular time to graduate students with excellent clinical skills.

Artificial intelligence-based methods for fusion of electronic health records and imaging data

Healthcare data are inherently multimodal, including electronic health records (EHR), medical images, and multi-omics data. Combining these multimodal data sources contributes to a better understanding of human health and provides optimal personalized healthcare. The most important question when using multimodal data is how to fuse them-a field of growing interest among researchers. Advances in artificial intelligence (AI) technologies, particularly machine learning (ML), enable the fusion of these different data modalities to provide multimodal insights. To this end, in this scoping review, we focus on synthesizing and analyzing the literature that uses AI techniques to fuse multimodal medical data for different clinical applications. More specifically, we focus on studies that only fused EHR with medical imaging data to develop various AI methods for clinical applications. We present a comprehensive analysis of the various fusion strategies, the diseases and clinical outcomes for which multimodal fusion was used, the ML algorithms used to perform multimodal fusion for each clinical application, and the available multimodal medical datasets. We followed the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. We searched Embase, PubMed, Scopus, and Google Scholar to retrieve relevant studies. After pre-processing and screening, we extracted data from 34 studies that fulfilled the inclusion criteria. We found that studies fusing imaging data with EHR are increasing and doubling from 2020 to 2021. In our analysis, a typical workflow was observed: feeding raw data, fusing different data modalities by applying conventional machine learning (ML) or deep learning (DL) algorithms, and finally, evaluating the multimodal fusion through clinical outcome predictions. Specifically, early fusion was the most used technique in most applications for multimodal learning (22 out of 34 studies). We found that multimodality fusion models outperformed traditional single-modality models for the same task. Disease diagnosis and prediction were the most common clinical outcomes (reported in 20 and 10 studies, respectively) from a clinical outcome perspective. Neurological disorders were the dominant category (16 studies). From an AI perspective, conventional ML models were the most used (19 studies), followed by DL models (16 studies). Multimodal data used in the included studies were mostly from private repositories (21 studies). Through this scoping review, we offer new insights for researchers interested in knowing the current state of knowledge within this research field.

Reforms, Errors, and Dermatopathology Malpractice: Then and Now: A Comprehensive Retrospective

Medical malpractice occurs when a hospital, doctor, or other health care professional, through a negligent act or omission, causes an injury to a patient. The negligence might be the result of errors in diagnosis, treatment, aftercare, or health management. To be considered medical malpractice under the law, the claim must violate the standard of care, the injury must be caused by the negligence and, last but most certainly not least, the injury must result in significant damages. This review is an overview of medicolegal issues specific to the practice of Dermatopathology with the caveat that most are likely pertinent to other specialties of pathology as well. The safety of patients remains the priority in pathology as it does in any medical undertaking, and this is no different in the practice of Dermatopathology. The review is broadly divided in 2 parts-we begin with an overview of tort reforms, advocated by physicians to reduce costs associated with malpractice defense. In the second part we address practical issues specific to the practice of pathology and dermatopathology. These include among others, errors-related to the biopsy type, inadequacy of clinical information regarding the lesion that is biopsied, role of interstate dermatopathology as well as examples of select entities commonly misdiagnosed in dermatopathology. In the last decade, artificial intelligence (AI) has moved to the forefront of technology. While research into the uses of AI in pathology is promising, the use of AI in diagnostic practice is still somewhat uncommon. Given that AI is not fully integrated routinely as a diagnostic adjunct, its' impact on pathology-specific medicolegal issues cannot, as yet at least, be defined. Restriction of medical malpractice is of particular relevance in the COVID-19 era, a period that is anything but normal. The response of states with specific pandemic-related guidelines is addressed with the caveat that this particular issue is only covered in select states. Furthermore, given that the COVID pandemic is only a year old, while it does not appear to have had an immediate impact on pathology-specific medicolegal matters, it is possible that the role of COVID on this issue, if any at all, will and can only be fully defined a few years down the line.

Fusion of medical imaging and electronic health records using deep learning: a systematic review and implementation guidelines

Advancements in deep learning techniques carry the potential to make significant contributions to healthcare, particularly in fields that utilize medical imaging for diagnosis, prognosis, and treatment decisions. The current state-of-the-art deep learning models for radiology applications consider only pixel-value information without data informing clinical context. Yet in practice, pertinent and accurate non-imaging data based on the clinical history and laboratory data enable physicians to interpret imaging findings in the appropriate clinical context, leading to a higher diagnostic accuracy, informative clinical decision making, and improved patient outcomes. To achieve a similar goal using deep learning, medical imaging pixel-based models must also achieve the capability to process contextual data from electronic health records (EHR) in addition to pixel data. In this paper, we describe different data fusion techniques that can be applied to combine medical imaging with EHR, and systematically review medical data fusion literature published between 2012 and 2020. We conducted a systematic search on PubMed and Scopus for original research articles leveraging deep learning for fusion of multimodality data. In total, we screened 985 studies and extracted data from 17 papers. By means of this systematic review, we present current knowledge, summarize important results and provide implementation guidelines to serve as a reference for researchers interested in the application of multimodal fusion in medical imaging.

Quality assurance in dermatopathology: A review of report amendments

BACKGROUND

Systematic review of amended reports in surgical pathology has been recommended as a valuable exercise in promoting quality assurance and improvement. Examination of report amendments can identify defects in the surgical pathology process and inspire new approaches to decreasing error rates and improving overall patient care.

METHODS

We performed a retrospective review of all amended dermatopathology reports over a 1.5-year period at a large academic institution.

RESULTS

During the study period, 86 amended reports out of a total 7950 skin-specific reports were issued (1.08%). Of these amended reports, about 59% (51/86) were because of non-interpretative errors (eg, wrong site, chin vs shin, etc.) while 41% (35/86) were diagnostic misinterpretations. Of these 35, 24 were considered major diagnostic changes while six were minor. Five amendments provided additional diagnostic information. Of those amended reports with diagnostic misinterpretations, 14/35 involved melanocytic lesions, 8/35 involved non-melanoma skin cancers or keratinocyte atypia, 10/35 were inflammatory lesions and 3/35 involved other tumors.

CONCLUSION

Our review points to several quality improvement areas that can be targeted to potentially avoid diagnostic errors in dermatopathology, including standardizing certain anatomic sites to prevent misidentification and seeking out clinicopathologic correlation in challenging melanocytic cases.

Machine Learning in Dermatology: Current Applications, Opportunities, and Limitations

Machine learning (ML) has the potential to improve the dermatologist's practice from diagnosis to personalized treatment. Recent advancements in access to large datasets (e.g., electronic medical records, image databases, omics), faster computing, and cheaper data storage have encouraged the development of ML algorithms with human-like intelligence in dermatology. This article is an overview of the basics of ML, current applications of ML, and potential limitations and considerations for further development of ML. We have identified five current areas of applications for ML in dermatology: (1) disease classification using clinical images; (2) disease classification using dermatopathology images; (3) assessment of skin diseases using mobile applications and personal monitoring devices; (4) facilitating large-scale epidemiology research; and (5) precision medicine. The purpose of this review is to provide a guide for dermatologists to help demystify the fundamentals of ML and its wide range of applications in order to better evaluate its potential opportunities and challenges.

The corporatization of dermatopathology

The corporatization of dermatopathology has long preceded that of dermatology and has been driven by federal legislation and economic influences. Although the Clinical Laboratory Improvement Amendments and the Stark Law limited physician-owned laboratories, loopholes via the Safe Harbor Exemptions outlined in the Anti-Kickback Statute allowed corporate laboratories to flourish through relationships built by health information technology donations. The rise of corporatization has had widespread effects on the fields of dermatopathology and dermatology, resulting in reduced numbers of dermatology-trained dermatopathologists and decreased caseloads in academic institutions, potentially compromising dermatology residency education. Although there have been efforts to counteract these effects, more global changes will be required to alter the direction of this subspecialty.

Dermatopathologist assessment of "pathologist-to-dermatologist" communication for dermatopathology services

BACKGROUND

While patients are the ultimate beneficiaries of pathology services, pathologist to clinician communication is an essential component of excellent patient care.

OBJECTIVE

To survey dermatologists on how well pathologists communicate with them and to assess which aspects of pathologists' communication skills are deemed most significant to dermatologists, stratified by practice type.

METHODS

A survey-based instrument was developed and sent to dermatologists through various email listservs. Of the approximately 400 potential Association of Professors of Dermatology respondents, 64 returned the survey questionnaire (response rate 16%). Of the 79 state and regional dermatologic societies, seven agreed to distribute the survey on their listservs (response rate 9%).

RESULTS

Surveyed dermatologists believe that the pathologists with whom they work are meeting expectations in the areas of diagnostic accuracy, communicating pertinent information in a timely fashion, integrating written pathology reports into the electronic medical record, and making a clinically meaningful histopathologic interpretation. Discussion of cost of ancillary testing is an area of improvement. University affiliated dermatologists are more likely to use electronic medical records as their predominant mode of communication compared to community dermatologists with and without academic affiliations. Community dermatologists are more likely to use faxed written pathology reports as their predominant mode of communication.

CONCLUSION

Physician-to-physician communication is a key component of effective patient care. When it comes to dermatopathology services, dermatologists appear overall satisfied with the indicators examined, however, potential opportunities for improvement exist.

Characteristics and diagnostic performance of pathologists who enjoy interpreting melanocytic lesions

Diagnostic discrepancy among pathologists interpreting melanocytic skin lesions (MSL) is an ongoing concern for patient care. Given that job satisfaction could impact patient care, this study aimed to characterize which pathologists enjoy interpreting MSL and estimate the association between enjoyment and diagnostic accuracy. Pathologists' demographics, training, and experience were obtained by a cross-sectional survey. Associations between these characteristics and self-reported enjoyment when interpreting MSL were estimated by Pearson's Chi-square tests. Diagnostic accuracy was determined by comparing pathologists' MSL interpretations with reference standard diagnoses. Associations between enjoyment and diagnostic accuracy were evaluated by generalized estimating equations (GEE) models. One hundred and eighty-seven (90%) pathologists completed the study. Seventy percent agreed that interpreting MSL is enjoyable. Pathologists who enjoyed interpreting MSL were more likely to be board certified and/or fellowship trained in dermatopathology (P=0.008), have ?10 years of experience (P=0.010) and have an MSL caseload of ?60 per month (P=<0.001). After adjustment, there was no association between enjoyment and diagnostic accuracy. Our data suggest that job dissatisfaction does not adversely affect diagnostic accuracy in the interpretation of melanocytic lesions, which is of importance given the progressive increase in annual biopsy rates and the attendant work demands imposed on pathologists.

High-Yield Vulvar Histopathology for the Clinician

Certain adjustable factors may influence how helpful a pathology report is to the clinician. Different biopsy techniques may be preferable based on the type of lesion being biopsied and the background epithelial surface. Key observations from the history and physical examination, possibly with a clinical photograph, are helpful to the pathologist. When reading the pathology report, realize the difficulties arising from definitively classifying some diseases and how treatment can affect the tissue. Finally, avoid miscommunication with the pathologist by understanding current nomenclature of vulvar disease.

Measures of Completeness and Accuracy of Clinical Information in Skin Biopsy Requisition Forms: An Analysis of 249 Cases

OBJECTIVES

To define indices of completeness and accuracy of clinical information in the skin biopsy requisition form (RF) and correlate them with health care delivery outcomes and pathology service utilization.

METHODS

RFs in our pathology information system were reviewed and assessed for the presence of 10 clinical elements considered critical for dermatopathologic diagnosis. Accuracy was determined by reviewing corresponding clinical notes.

RESULTS

In total, 249 RFs were reviewed. In inflammatory dermatoses, provision of a clinical impression, provision of more than two elements, and achieving more than 75% accuracy were associated with improved outcomes and decreased utilization. For all nonlymphoproliferative cases, higher quality clinical information was associated with decreased turnaround time (P < .001). More clinical information was associated with increased utilization and turnaround time (P = .0235) for lymphoproliferative cases and higher resampling rates for melanocytic lesions (P = .0066).

CONCLUSIONS

In inflammatory dermatoses, providing high-quality clinical information on the RF promotes optimal histopathologic diagnostic performance and appropriate pathology service utilization.

Use of the term "rule out" in requisition forms may cause diagnostic delays in dermatopathology practice

BACKGROUND

Timely pathologic diagnosis relies on the communication of specific clinical information in the requisition form (RF). Clinical information may use nonspecific terms such as "rule out", the use of which may result in diagnostic delays and the unnecessary application of pathology stains and sections.

OBJECTIVE

This study was designed to evaluate the relationship between use of the term "rule out" and time to diagnosis, and the use of additional pathology stains and sections in integrated and non-integrated dermatopathology practices.

METHODS

A retrospective double-cohort study of 475 RFs from the integrated practice (of which 182 used the term "rule out" [RO] and 293 did not [NRO]) and 412 RFs from the non-integrated practice (RO, n = 126; NRO, n = 286) was performed.

RESULTS

No significant differences emerged between groups of patients with, respectively, RO and NRO RFs in the integrated practice with respect to time to diagnosis, and numbers of additional tissue sections or stains applied. By contrast, the use of RFs containing the term "rule out" was associated with significantly longer times to diagnosis and higher rates of use of pathology stains and sections in comparison with NRO RFs in the non-integrated practice. However, the study is limited by its status as a retrospective review of data sourced from a single institution.

CONCLUSIONS

Use of the term "rule out" in RFs may not significantly impact key care delivery outcomes in an integrated practice. However, it may cause diagnostic delays and the use of unnecessary pathology services in a non-integrated practice.

Rates of provision of clinical information in the skin biopsy requisition form and corresponding encounter visit note

BACKGROUND

The skin biopsy requisition form (RF) serves as a key communication tool for transfer of relevant information related to skin biopsy between clinicians and pathologists. Clinical information in the skin biopsy RF is frequently missing or incomplete.

OBJECTIVE

To determine the rates of provision of critical clinical information necessary for histopathologic interpretation in the skin biopsy RF and encounter visit note (EVN).

METHODS

A retrospective review of 300 RFs and corresponding EVNs from May 1 to 7, 2012, in a tertiary care dermatology practice.

RESULTS

Age (100%), lesion location (100%), and clinical impression (93%) were the most commonly supplied elements in the RF and EVN. Clinical elements that were commonly not provided in the RF but present in the EVN included sampling method - partial versus complete (46%), duration of lesion (54%), morphology of lesion (97%), clinical symptoms (63%), clinical photos (63%), previous clinical (97%), and dermatopathologic diagnoses (82%).

LIMITATIONS

Retrospective study design.

CONCLUSIONS

These data suggest that while missing critical clinical information in the RF is often present in the EVN, some information is still not present in either source.

Practical Strategies to Improve the Clinical Utility of the Dermatopathology Report

CONTEXT

-Dermatologists and subspecialty dermatopathologists, working together over many years, develop a common understanding of clinical information provided on the requisition and of terminology used in the pathology report. Challenges arise for pathologists without additional subspecialty training in dermatology/dermatopathology, and for any pathologist reporting skin biopsies for nondermatologists such as general practitioners or surgeons.

OBJECTIVE

-To provide practical strategies to improve efficiency of dermatopathology sign-out, at the same time providing the clinician with clear diagnostic and prognostic information to guide patient management.

DATA SOURCES

-The information outlined in this review is based on our own experiences with routine dermatopathology and dermatology practice, and review of English-language articles related to the selected topics discussed.

CONCLUSIONS

-Using generic diagnoses for some benign lesions, listing pertinent negatives in the pathology report, and using logical risk management strategies when reporting on basal cell carcinoma, partial biopsies, or specimens with incomplete clinical information allow the pathologist to convey relevant and useful diagnostic information to the treating clinician.

Optimizing Patient-centered Communication and Multidisciplinary Care Coordination in Emergency Diagnostic Imaging: A Research Agenda

Patient-centered emergency diagnostic imaging relies on efficient communication and multispecialty care coordination to ensure optimal imaging utilization. The construct of the emergency diagnostic imaging care coordination cycle with three main phases (pretest, test, and posttest) provides a useful framework to evaluate care coordination in patient-centered emergency diagnostic imaging. This article summarizes findings reached during the patient-centered outcomes session of the 2015 Academic Emergency Medicine consensus conference "Diagnostic Imaging in the Emergency Department: A Research Agenda to Optimize Utilization." The primary objective was to develop a research agenda focused on 1) defining component parts of the emergency diagnostic imaging care coordination process, 2) identifying gaps in communication that affect emergency diagnostic imaging, and 3) defining optimal methods of communication and multidisciplinary care coordination that ensure patient-centered emergency diagnostic imaging. Prioritized research questions provided the framework to define a research agenda for multidisciplinary care coordination in emergency diagnostic imaging.