Surgical pathology and the patient: a systematic review evaluating the primary audience of pathology reports

Bridging the gap: Evaluating ChatGPT-generated, personalized, patient-centered prostate biopsy reports

OBJECTIVE

The highly specialized language used in prostate biopsy pathology reports coupled with low rates of health literacy leave some patients unable to comprehend their medical information. Patients' use of online search engines can lead to misinterpretation of results and emotional distress. Artificial intelligence (AI) tools such as ChatGPT (OpenAI) could simplify complex texts and help patients. This study evaluates patient-centered prostate biopsy reports generated by ChatGPT.

METHODS

Thirty-five self-generated prostate biopsy reports were synthesized using National Comprehensive Cancer Network guidelines. Each report was entered into ChatGPT, version 4, with the same instructions, and the explanations were evaluated by 5 urologists and 5 pathologists.

RESULTS

Respondents rated the AI-generated reports as mostly accurate and complete. All but 1 report was rated complete and grammatically correct by the majority of physicians. Pathologists did not rate any reports as having severe potential for harm, but 1 or more urologists rated severe concern in 20% of the reports. For 80% of the reports, all 5 pathologists felt comfortable sharing them with a patient or another clinician, but all 5 urologists reached the same consensus for only 40% of reports. Although every report required edits, all physicians agreed that they could modify the ChatGPT report faster than they could write an original report.

CONCLUSIONS

ChatGPT can save physicians substantial time by generating patient-centered reports appropriate for patient and physician audiences with low potential to cause harm. Surveyed physicians have confidence in the overall utility of ChatGPT, supporting further investigation of how AI could be integrated into physicians' workflows.

The development and comparative effectiveness of a patient-centered pathology report for breast cancer care: a randomized clinical trial

PURPOSE

Pathology reports contain complex medical terminology that may be confusing or overwhelming for patients newly diagnosed with breast cancer. We evaluated the effectiveness of patient-centered pathology reports (PCPRs), which translate pathology results into patient-friendly language.

METHODS

Sixty-six participants newly diagnosed with breast cancer were randomized to receive either a PCPR and standard pathology report (intervention arm) or a standard pathology report alone (control arm). Patients were surveyed at initial pathology disclosure and 1 month later to assess breast cancer knowledge and ratings of decisional confidence, conflict, and self-efficacy for treatment decision-making. Knowledge was assessed for four pathology domains independently.

RESULTS

Accuracy of breast cancer knowledge across all domains trended higher for the intervention group compared with the control group (66% vs. 50%, p = 0.11); cancer type and surgical margin status knowledge domains exceeded 75% accuracy for the intervention group. No significant differences between groups were observed for patient-reported ratings of communication, decisional conflict, and decision self-efficacy.

CONCLUSIONS

PCPRs in lay language appeared to improve patients' knowledge of their breast cancer diagnosis, were acceptable to patients and providers, and have the potential to be broadly applied in an effort to improve patient knowledge and improve the patient experience surrounding a breast cancer diagnosis.

Knowledge and Worry Following Review of Standard vs Patient-Centered Pathology Reports

This study compares knowledge of diagnosis and worry among adults presented with prostate biopsy reports in a patient-centered format, which presents important clinical data in plain language, vs standard report format.

The dermatopathologist-patient consultation program: A pilot study on patient perspectives and interest

BACKGROUND

Despite the integral contribution of dermatopathologists in diagnosing skin lesions, their role often remains unclear to patients, likely due to little face-to-face interaction. More healthcare systems have begun introducing patient-pathologist consultation programs that allow patients to discuss results with a pathologist and view tissue under a microscope. To our knowledge, only one study has been published exploring patient perspectives of these programs and no studies exist regarding interest in dermatopathology.

METHODS

An anonymous survey was distributed via online support groups for various dermatologic diagnoses.

RESULTS

Patients demonstrated a high level of interest in the dermatopathologist-patient consultation program, with 81.3% expressing at least moderate interest in discussing their diagnosis with a dermatopathologist and 79.2% expressing at least moderate interest in examining their tissue under the microscope with a dermatopathologist. The rationale for interest included various themes: (1) knowledge/understanding, (2) empowerment, (3) emotional support, (4) general interest, and (5) improved trust.

CONCLUSIONS

Patients with cancerous and non-cancerous dermatologic diagnoses demonstrate high interest in a dermatopathologist-patient consultation program. Efforts to pilot this type of program can build upon the infrastructure of current pathologist consultation programs. Future efforts should be taken by hospital leadership, clinicians, and dermatopathologists to determine physician interest and address logistical challenges to the implementation of these programs.

Enhancing doctor-patient communication using large language models for pathology report interpretation

BACKGROUND

Large language models (LLMs) are increasingly utilized in healthcare settings. Postoperative pathology reports, which are essential for diagnosing and determining treatment strategies for surgical patients, frequently include complex data that can be challenging for patients to comprehend. This complexity can adversely affect the quality of communication between doctors and patients about their diagnosis and treatment options, potentially impacting patient outcomes such as understanding of their condition, treatment adherence, and overall satisfaction.

MATERIALS AND METHODS

This study analyzed text pathology reports from four hospitals between October and December 2023, focusing on malignant tumors. Using GPT-4, we developed templates for interpretive pathology reports (IPRs) to simplify medical terminology for non-professionals. We randomly selected 70 reports to generate these templates and evaluated the remaining 628 reports for consistency and readability. Patient understanding was measured using a custom-designed pathology report understanding level assessment scale, scored by volunteers with no medical background. The study also recorded doctor-patient communication time and patient comprehension levels before and after using IPRs.

RESULTS

Among 698 pathology reports analyzed, the interpretation through LLMs significantly improved readability and patient understanding. The average communication time between doctors and patients decreased by over 70%, from 35 to 10 min (P < 0.001), with the use of IPRs. The study also found that patients scored higher on understanding levels when provided with AI-generated reports, from 5.23 points to 7.98 points (P < 0.001), with the use of IPRs. indicating an effective translation of complex medical information. Consistency between original pathology reports (OPRs) and IPRs was also evaluated, with results showing high levels of consistency across all assessed dimensions, achieving an average score of 4.95 out of 5.

CONCLUSION

This research demonstrates the efficacy of LLMs like GPT-4 in enhancing doctor-patient communication by translating pathology reports into more accessible language. While this study did not directly measure patient outcomes or satisfaction, it provides evidence that improved understanding and reduced communication time may positively influence patient engagement. These findings highlight the potential of AI to bridge gaps between medical professionals and the public in healthcare environments.

Improving Interdisciplinary Communication and Pathology Reporting for Head and Neck Cancer Resections: 3D Visualizations and Margin Reconciliation

PURPOSE

Surgical pathology reports play an integral role in postoperative management of head and neck cancer patients. Pathology reports of complex head and neck resections must convey critical information to all involved clinicians. Previously, we demonstrated the utility of 3D specimen and defect scanning for communicating margin status and documenting the location of supplemental margins. We introduce a newly designed permanent pathology report which improves documentation of intraoperative margin mapping and extent of corresponding supplemental margins harvested.

METHODS

We test the hypothesis that gaps in understanding exist for head and neck resection pathology reports across providers. A cross-sectional exploratory study using human-centered design was implemented to evaluate the existing permanent pathology report with respect to understanding margin status. Pathologists, surgeons, radiation oncologists, and medical oncologists from United States-based medical institutions were surveyed. The results supported a redesign of our surgical pathology template, incorporating 3D specimen / defect scans and annotated radiographic images indicating the location of inadequate margins requiring supplemental margins, or indicating frankly positive margins discovered on permanent section.

RESULTS

Forty-seven physicians completed our survey. Analyzing surgical pathology reports, 28/47 (60%) respondents reported confusion whether re-excised supplemental margins reflected clear margins, 20/47 (43%) reported uncertainty regarding final margin status, and 20/47 (43%) reported the need for clarity regarding the extent of supplemental margins harvested intraoperatively. From this feedback, we designed a new pathology report template; 61 permanent pathology reports were compiled with this new template over a 12-month period.

CONCLUSION

Feedback from survey respondents led to a redesigned permanent pathology report that offers detailed visual anatomic information regarding intraoperative margin findings and exact location/size of harvested supplemental margins. This newly designed report reconciles frozen and permanent section results and includes annotated radiographic images such that clinicians can discern precise actions taken by surgeons to address inadequate margins, as well as to understand the location of areas of concern that may influence adjuvant radiation planning.

Evaluating Patients' Health Literacy to Improve Thyroid Pathology Reports

INTRODUCTION

As our growing population demonstrates a significant increase in the incidence of thyroid cancer, so does patient access to their medical records. Poor health literacy and understanding of disease severity, underscores the importance of effective and accessible patient-doctor communication. No previous studies on patient understanding of thyroid pathology reports exist; therefore, we sought to characterize health literacy in this population.

METHODS

Using a modified Delphi technique, a 12-question multiple-choice survey regarding common pathology terms with possible definitions for each term was synthesized and administered to patients in a high-volume endocrine surgery clinic. Survey results, patient demographics, history of prior thyroid procedure (biopsy or surgery), and self-reported health literacy were collected. Data analysis included t tests, chi-squared, and multivariable linear regression using R.

RESULTS

The survey was completed by 54 patients (response rate: 69.8%). On univariate analysis, White race, previous thyroid procedure, and at least a high school level education were all more likely to score higher on the survey than their counterparts (P < 0.05). On multivariable logistic regression for predicting a higher survey score, only race (est: 2.48 [95% confidence interval: 1.01-3.96]) and higher educational attainment (est: 3.98 [95% confidence interval: 2.32-5.64]) remained predictive (P < 0.05). The remaining demographic groups (age, health literacy confidence, and previous thyroid procedure) did not show a statistically significant difference.

CONCLUSIONS

Overall, terms on a thyroid pathology report are poorly understood by patients. This is exacerbated by non-White race and low educational attainment. There is a need for patient-facing pathology education.

Forgotten clientele: A systematic review of patient-centered pathology reports

CONTEXT

Patient portals, designed to give ready access to medical records, have led to important improvements in patient care. However, there is a downside: much of the information available on portals is not designed for lay people. Pathology reports are no exception. Access to complex reports often leaves patients confused, concerned and stressed. We conducted a systematic review to explore recommendations and guidelines designed to promote a patient centered approach to pathology reporting.

DESIGN

In consultation with a research librarian, a search strategy was developed to identify literature regarding patient-centered pathology reports (PCPR). Terms such as "pathology reports," "patient-centered," and "lay-terms" were used. The PubMed, Embase and Scopus databases were searched during the first quarter of 2023. Studies were included if they were original research and in English, without date restrictions.

RESULTS

Of 1,053 articles identified, 17 underwent a full-text review. Only 5 studies (≈0.5%) met eligibility criteria: two randomized trials; two qualitative studies; a patient survey of perceived utility of potential interventions. A major theme that emerged from the patient survey/qualitative studies is the need for pathology reports to be in simple, non-medical language. Major themes of the quantitative studies were that patients preferred PCPRs, and patients who received PCPRs knew and recalled their cancer stage/grade better than the control group.

CONCLUSION

Pathology reports play a vital role in the decision-making process for patient care. Yet, they are beyond the comprehension of most patients. No framework or guidelines exist for generating reports that deploy accessible language. PCPRs should be a focus of future interventions to improve patient care.

The impact of curated educational videos on pathology health literacy for patients with a pancreatic, colorectal, or prostate cancer diagnosis

Despite patients having increased access to their own electronic health record (EHR) in recent times, patients are often still not considered a primary audience of pathology reports. An alternative to in-person patient education is the use of multimedia programming to enhance health literacy. Curated video presentations designed to explain diagnosis-specific pathology terms were reviewed by a board-certified pathologist and oncologist team and then shown to patients with a primary diagnosis of either pancreatic, colorectal, or prostate cancer in-clinic; these patients then completed a secure electronic survey immediately afterwards. Seventy patients were surveyed, with 91% agreeing or strongly agreeing that the video they watched increased their understanding of the medical terms used in their pathology reports, with a corresponding average Likert score (ALS) of 4.21 (SD = 0.77, CI = ± 0.18). Furthermore, 95% agreed or strongly agreed that the video they watched both enhanced their understanding of the role of the pathologist in diagnosing cancer (ALS = 4.27; SD = 0.65, CI = ± 0.15) and reported they found the video useful (ALS = 4.27; SD = 0.53, CI = ± 0.13). Curated videos such as those utilized in this study have the potential to increase patient health literacy and inform patients of the multidisciplinary nature of cancer diagnosis.

Addressing the Diagnostic Miscommunication in Pathology

OBJECTIVES

The pathology report serves as a crucial communication tool among a number of stakeholders. It can sometimes be challenging to understand. A communication barrier exists among pathologists, other clinicians, and patients when interpreting the pathology report, leaving both clinicians and patients less empowered when making treatment decisions. Miscommunication can lead to delays in treatment or other costly medical interventions.

METHODS

In this review, we highlight miscommunication in pathology reporting and provide potential solutions to improve communication.

RESULTS

Up to one-third of clinicians do not always understand pathology reports. Several causes of report misinterpretation include the use of pathology-specific jargon, different versions of staging or grading systems, and expressions indicative of uncertainty in the pathologist's report. Active communication has proven to be crucial between the clinician and the pathologist to clarify different aspects of the pathology report. Direct communication between pathologists and patients is evolving, with promising success in proof-of-principle studies. Special attention needs to be paid to avoiding inaccuracy while trying to simplify the pathology report.

CONCLUSIONS

There is a need for active and adequate communication among pathologists, other clinicians, and patients. Clarity and consistency in reporting, quantifying the level of confidence in diagnosis, and avoiding misnomers are key steps toward improving communications.

"Help me figure this out": Qualitative explorations of patient experiences with cancer pathology reports

OBJECTIVE

For patients with a new cancer diagnosis, the pathology report is a critical tool to support diagnosis and decision-making, yet they are designed for providers, not patients. We sought to qualitatively explore patients' experiences receiving and interpreting pathology reports for breast and colorectal cancers.

METHODS

We conducted four focus groups with patients (n = 23) who had received diagnostic or surgical pathology reports for breast cancer, colorectal cancer or polypectomy. Focus groups discussed patients' experiences with pathology reports and recommendations for improving the patient-centeredness of report design. Focus groups were transcribed and thematic analysis was used to explore patient perspectives.

RESULTS

Participants described experiences with pathology reports that were fraught with confusion and variability. Three central themes were identified related to how 1) the experience receiving the pathology report, 2) the pathology report language, and 3) the format of pathology reports all influence patient understanding and ability to engage in treatment decision-making.

CONCLUSION

Due to their complex medical language and challenging framing, traditional pathology reports can contribute to the confusion and uncertainty patients experience as they navigate a new cancer diagnosis.

The development and comparative effectiveness of a patient-centered prostate biopsy report: a prospective, randomized study

PURPOSE

The prostate biopsy pathology report represents a critical document used for decision-making in patients diagnosed with prostate cancer, yet the content exceeds the health literacy of most patients. We sought to create and compare the effectiveness of a patient-centered prostate biopsy report compared with standard reports.

MATERIALS AND METHODS

Using a modified Delphi approach, prostate cancer experts identified critical components of a prostate biopsy report. Patient focus groups provided input for syntax and formatting of patient-centered pathology reports. Ninety-four patients with recent prostate biopsies were block randomized to the standard report with or without the patient-centered report. We evaluated patient activation, self-efficacy, provider communication skills, and prostate cancer knowledge.

RESULTS

Experts selected primary and secondary Gleason score and the number of positive scores as the most important elements of the report. Patients prioritized a narrative design, non-threatening language and information on risk classification. Initial assessments were completed by 87% (40/46) in the standard report group and 81% (39/48) in the patient-centered report group. There were no differences in patient activation, self-efficacy, or provider communication skills between groups. Patients who received the patient-centered report had significantly improved ability to recall their Gleason score (100% vs. 85%, p = 0.026) and number of positive cores (90% vs. 65%, p = 0.014). In total, 86% of patients who received the patient-centered report felt that it helped them better understand their results and should always be provided.

CONCLUSIONS

Patient-centered pathology reports are associated with significantly higher knowledge about a prostate cancer diagnosis. These important health information documents may improve patient-provider communication and help facilitate shared decision-making among patients diagnosed with prostate cancer.

Putting the patient at the centre of pathology: an innovative approach to patient education-MyPathologyReport.ca

In many centres, patients now have access to their electronic medical record (EMR) and laboratory results, including pathology reports, are amongst the most frequently accessed pieces of information. The pathology report is an important but highly technical medical document that can be difficult for patient and clinicians alike to interpret. To improve communication and patient safety, pathologists are being called upon to play a more direct role in patient care. Novel approaches have been undertaken by pathologists to address this need, including the addition of patient-friendly summaries at the beginning of pathology reports and the development of patient education tools. MyPathologyReport.ca is a novel website exclusively providing pathology education to patients. It has been designed to help patients understand the language of pathology and to effectively navigate their pathology report. At present, the website includes over 150 diagnostic articles and over 125 pathology dictionary definitions. The diagnostic articles span all body sites and include a variety of malignant, benign and non-neoplastic conditions. Since its creation, this website has been visited over 14 000 times, with cancer-related diagnoses and definitions representing the most commonly accessed articles. This website has been embedded in patient accessible EMRs and shared through partnerships with patients, caregivers and their respective advocacy groups. Our next steps involve longitudinal assessment of MyPathologyReport.ca from non-medical community members, evaluation of patient satisfaction and understanding and further collaboration with hospitals and care-providers to increase patient access to this resource.

Incorporating Transition-Affirming Language into Anatomical Pathology Reporting for Gender Affirmation Surgery

Background: The use of inclusive terminology in health records continues to be a challenge for transgender, gender-diverse, and nonbinary peoples. When patients access electronic health records, laboratory results, including pathology reports, are among the most frequently viewed items. There has been limited discussion of transgender care within laboratory medicine, despite its role in providing written pathology reports after gender-affirming surgery. Proposal: This group proposes inclusive diagnostic terminology for pathology reporting and puts forward recommendations for procedural descriptions in the pathology report. Finally, we highlight pathological information that should be included in a report that has future cancer screening or diagnostic consequences.

Inferring bladder cancer research prioritization from patient-generated online content

PURPOSE

Patients and their families utilize online resources when dealing with a diagnosis of bladder cancer. Many patients have questions regarding clinical management options. Online research forums may help researchers and providers identify research areas of interest. Our objective was to review online forums and identify research questions that are important to patients and families impacted by bladder cancer diagnosis.

METHODS

We reviewed 1 month of online content from the Bladder Cancer Advocacy Network Inspire online community ( https://www.inspire.com/groups/bladder-cancer-advocacy-network ). Using affinity diagramming, we categorized the submitted content from patient users into themes stratified by the cancer severity of the patient user (non-muscle-invasive bladder cancer, muscle-invasive bladder cancer, metastatic bladder cancer). We categorized the content by the audience of forum posts (i.e., inwardly directed, those seeking support, vs. outwardly directed, those sharing personal experiences) and constructed comparative effectiveness research questions from the submitted content.

RESULTS

From 14 July 2014 to 14 August 2014, a total of 394 forum posts were collected, of which 3 were excluded from analysis due to non-relevant content, leaving 391 comments for final analysis. Almost 38% of posts involved muscle-invasive bladder cancer and 25% of posts were from people other than the patient. Inwardly and outwardly directed posts were commonly related to clinical treatment concerns.

CONCLUSIONS

Review of online patient-generated content may offer insight into comparative effectiveness research topics of importance to bladder cancer patients. A more formalized process may better represent research priorities among bladder cancer patients.

A Natural Language Processing System That Links Medical Terms in Electronic Health Record Notes to Lay Definitions: System Development Using Physician Reviews

Background

Many health care systems now allow patients to access their electronic health record (EHR) notes online through patient portals. Medical jargon in EHR notes can confuse patients, which may interfere with potential benefits of patient access to EHR notes.

Objective

The aim of this study was to develop and evaluate the usability and content quality of NoteAid, a Web-based natural language processing system that links medical terms in EHR notes to lay definitions, that is, definitions easily understood by lay people.

Methods

NoteAid incorporates two core components: CoDeMed, a lexical resource of lay definitions for medical terms, and MedLink, a computational unit that links medical terms to lay definitions. We developed innovative computational methods, including an adapted distant supervision algorithm to prioritize medical terms important for EHR comprehension to facilitate the effort of building CoDeMed. Ten physician domain experts evaluated the user interface and content quality of NoteAid. The evaluation protocol included a cognitive walkthrough session and a postsession questionnaire. Physician feedback sessions were audio-recorded. We used standard content analysis methods to analyze qualitative data from these sessions.

Results

Physician feedback was mixed. Positive feedback on NoteAid included (1) Easy to use, (2) Good visual display, (3) Satisfactory system speed, and (4) Adequate lay definitions. Opportunities for improvement arising from evaluation sessions and feedback included (1) improving the display of definitions for partially matched terms, (2) including more medical terms in CoDeMed, (3) improving the handling of terms whose definitions vary depending on different contexts, and (4) standardizing the scope of definitions for medicines. On the basis of these results, we have improved NoteAid’s user interface and a number of definitions, and added 4502 more definitions in CoDeMed.

Conclusions

Physician evaluation yielded useful feedback for content validation and refinement of this innovative tool that has the potential to improve patient EHR comprehension and experience using patient portals. Future ongoing work will develop algorithms to handle ambiguous medical terms and test and evaluate NoteAid with patients.

The ins and outs of molecular pathology reporting

The raid evolution in molecular pathology resulting in an increasing complexity requires careful reporting. The need for standardisation is clearer than ever. While synoptic reporting was first used for reporting hereditary genetic diseases, it is becoming more frequent in pathology, especially molecular pathology reports too. The narrative approach is no longer feasible with the growing amount of essential data present on the report, although narrative components are still necessary for interpretation in molecular pathology. On the way towards standardisation of reports, guidelines can be a helpful tool. There are several guidelines that focus on reporting in the field of hereditary diseases, but it is not always feasible to extrapolate these to the reporting of somatic variants in molecular pathology. The rise of multi-gene testing causes challenges for the laboratories. In order to provide a continuous optimisation of the laboratory testing process, including reporting, external quality assessment is essential and has already proven to improve the quality of reports. In general, a clear and concise report for molecular pathology can be created by including elements deemed important by different guidelines, adapting the report to the process flows of the laboratory and integrating the report with the laboratory information management system and the patient record.

Readability Formulas and User Perceptions of Electronic Health Records Difficulty: A Corpus Study

Background

Electronic health records (EHRs) are a rich resource for developing applications to engage patients and foster patient activation, thus holding a strong potential to enhance patient-centered care. Studies have shown that providing patients with access to their own EHR notes may improve the understanding of their own clinical conditions and treatments, leading to improved health care outcomes. However, the highly technical language in EHR notes impedes patients’ comprehension. Numerous studies have evaluated the difficulty of health-related text using readability formulas such as Flesch-Kincaid Grade Level (FKGL), Simple Measure of Gobbledygook (SMOG), and Gunning-Fog Index (GFI). They conclude that the materials are often written at a grade level higher than common recommendations.

Objective

The objective of our study was to explore the relationship between the aforementioned readability formulas and the laypeople’s perceived difficulty on 2 genres of text: general health information and EHR notes. We also validated the formulas’ appropriateness and generalizability on predicting difficulty levels of highly complex technical documents.

Methods

We collected 140 Wikipedia articles on diabetes and 242 EHR notes with diabetes International Classification of Diseases, Ninth Revision code. We recruited 15 Amazon Mechanical Turk (AMT) users to rate difficulty levels of the documents. Correlations between laypeople’s perceived difficulty levels and readability formula scores were measured, and their difference was tested. We also compared word usage and the impact of medical concepts of the 2 genres of text.

Results

The distributions of both readability formulas’ scores (P<.001) and laypeople’s perceptions (P=.002) on the 2 genres were different. Correlations of readability predictions and laypeople’s perceptions were weak. Furthermore, despite being graded at similar levels, documents of different genres were still perceived with different difficulty (P<.001). Word usage in the 2 related genres still differed significantly (P<.001).

Conclusions

Our findings suggested that the readability formulas’ predictions did not align with perceived difficulty in either text genre. The widely used readability formulas were highly correlated with each other but did not show adequate correlation with readers’ perceived difficulty. Therefore, they were not appropriate to assess the readability of EHR notes.

Improving the creation and reporting of structured findings during digital pathology review

Background:

Today, pathology reporting consists of many separate tasks, carried out by multiple people. Common tasks include dictation during case review, transcription, verification of the transcription, report distribution, and report the key findings to follow-up registries. Introduction of digital workstations makes it possible to remove some of these tasks and simplify others. This study describes the work presented at the Nordic Symposium on Digital Pathology 2015, in Linköping, Sweden.

Methods:

We explored the possibility to have a digital tool that simplifies image review by assisting note-taking, and with minimal extra effort, populates a structured report. Thus, our prototype sees reporting as an activity interleaved with image review rather than a separate final step. We created an interface to collect, sort, and display findings for the most common reporting needs, such as tumor size, grading, and scoring.

Results:

The interface was designed to reduce the need to retain partial findings in the head or on paper, while at the same time be structured enough to support automatic extraction of key findings for follow-up registry reporting. The final prototype was evaluated with two pathologists, diagnosing complicated partial mastectomy cases. The pathologists experienced that the prototype aided them during the review and that it created a better overall workflow.

Conclusions:

These results show that it is feasible to simplify the reporting tasks in a way that is not distracting, while at the same time being able to automatically extract the key findings. This simplification is possible due to the realization that the structured format needed for automatic extraction of data can be used to offload the pathologists’ working memory during the diagnostic review.

Comparative Effectiveness of a Patient Centered Pathology Report for Bladder Cancer Care

PURPOSE

Patients have unprecedented access to their medical records. However, many documents, such as pathology reports, may be beyond the health literacy of most patients. We compared the effectiveness of bladder biopsy patient centered pathology reports with standard reports.

MATERIALS AND METHODS

Local bladder cancer experts reached consensus on the important elements of a bladder biopsy pathology report to inform prognosis and counseling. Patient focus groups identified the patient centered formats and language to convey these elements and constructed a pilot patient centered pathology report. A total of 40 patients undergoing bladder biopsy were block randomized to receive the standard report with or without the patient centered report. We assessed patient self-efficacy, and provider communication and empathy, and tested bladder cancer knowledge at pathology disclosure and 1 month later. We compared study groups with descriptive statistics.

RESULTS

Experts identified stage, grade and histology as the most important elements of a bladder biopsy pathology report. Patients prioritized 3 themes, including narrative format, tumor stage illustration and risk stratification for recurrence. A total of 39 patients completed initial and followup assessments. Patients with the patient centered pathology report had improved ability to identify cancer stage compared to those with the standard report. Initially 58% of patients with the standard report vs 20% with the patient centered report were unable to describe stage but at followup this incidence was 47% vs 15% (p = 0.02 and 0.03, respectively). Those with the patient centered report also trended toward improved identification of cancer grade. Provider communication trended toward improvement for the patient centered report. Ratings of patient self-efficacy did not differ by report.

CONCLUSIONS

Patient centered pathology reports are associated with greater patient knowledge about the bladder cancer diagnosis. The reports may aid patient-provider communication. This pilot study may serve as a model for the development of patient centered pathology reports for other cancers.

Methods for Linking EHR Notes to Education Materials

It has been shown that providing patients with access to their own electronic health records (EHR) can enhance their medical understanding and provide clinically relevant benefits. However, languages that are difficult for non-medical professionals to comprehend are prevalent in the EHR notes, including medical terms, abbreviations, and domain-specific language patterns. Furthermore, limited average health literacy forms a barrier for patients to understand their health condition, impeding their ability to actively participate in managing their health. Therefore, we are developing a system to retrieve EHR note-tailored online consumer-oriented health education materials to improve patients' health knowledge of their own clinical conditions. Our experiments show that queries combining key concepts and other medical concepts present in the EHR notes significantly outperform (more than doubled) a baseline system of using the phrases from topic models.