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

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.

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.

Patient-centred pathology reporting improves patient experience and understanding of disease in prostate cancer care

Introduction and Objectives

Patient-centred (PC) and holistic care improves patient satisfaction and health outcomes. We sought to investigate the benefit of utilising a PC pathology report in patients undergoing radical prostatectomy (RP) for prostate cancer (PCa). Our study aimed to evaluate and compare patient understanding of their PCa diagnosis after RP, upon receiving either a standard histopathology report or a personalised and PC report (PCR). Moreover, we evaluated knowledge retention at 4 weeks after the initial consultation.

Methods

We invited patients undergoing RP at three metropolitan Urology clinics to participate in our randomised controlled study. Patients were randomised to receive either a PCR or standard pathology report. Patient satisfaction questionnaires (Perceived Efficacy in Patient-Physician Interactions [PEPPI], Consultation and Relational Empathy [CARE] and Communication Assessment Tool [CAT]) and a knowledge test were conducted within 72 h of the initial appointment and again at 4 weeks. Accurate recollection of Gleason grade group (GGG) and extracapsular extension (ECE) were classified as 'correct'. Baseline demographic data included age, education, marital and employment status, pre-op prostate specific antigen (PSA) and clinical stage. Baseline data were tested for differences between groups using the Student's t test, chi-squared test or Fisher's exact test depending on whether data were continuous, categorical or sparse. Comparison of correctly answered 'knowledge' questions was analysed using chi-squared test. A significance level of p ≤ 0.05 was used.

Results

Data from 62 patients were analysed (30 standard vs. 32 PCR). No significant differences in baseline demographics were found between groups. Both groups reported high levels of satisfaction with their healthcare experiences in all domains of patient-physician rapport, empathy and communication. There were no significant differences between groups in PEPPI (p = 0.68), CAT (p = 0.39) and CARE (p = 0.66) scores, at baseline and 4 weeks. Ninety-three per cent of patients who received the PCR understood the report while 90% felt the report added to their understanding of their PCa. Regarding patient knowledge, the PCR group had significantly more correct answers on GGG and ECE as compared with the standard report group at baseline and 4 weeks (p < 0.001 and 0.001, respectively).

Conclusions

Our findings demonstrate that PC pathology reports improve patient knowledge and understanding of their PCa that is retained for at least 4 weeks after initial receipt of results.

One procedure-one report: the Re-Imagine Cytopathology Task Force position paper on small tissue biopsy triage in anatomic pathology

INTRODUCTION

Endoscopic biopsy procedures increasingly generate multiple tissue samples from multiple sites, and frequently retrieve concurrent cytologic specimens and small core needle biopsies. There is currently lack of consensus in subspecialized practices as to whether cytopathologists or surgical pathologists should review such samples, and whether the pathology findings should be reported together or separately.

MATERIALS AND METHODS

In December 2021, the American Society of Cytopathology convened the Re-Imagine Cytopathology Task Force to examine various workflows that would facilitate unified pathology reporting of concurrently obtained biopsies and improve clinical care.

RESULTS AND CONCLUSIONS

This position paper summarizes the key points and highlights the advantages, challenges, and resources available to support the implementation of such workflows that result in "one procedure-one report".

Multi-pilot implementation experiences of patient-centered pathology reports: lessons learned for the advancement of patient-centered tools for cancer decision-making

PURPOSE

New federal legislation in the United States grants patients expanded access to their medical records, making it critical that medical records information is understandable to patients. Provision of informational summaries significantly increase patient perceptions of patient-centered care and reduce feelings of uncertainty, yet their use for cancer pathology is limited.

METHODS

Our team developed and piloted patient-centered versions of pathology reports (PCPRs) for four cancer organ sites: prostate, bladder, breast, and colorectal polyp. The objective of this analysis was to identify common barriers and facilitators to support dissemination of PCPRs in care delivery settings. We analyzed quantitative and qualitative data from pilot PCPR implementations, guided by the RE-AIM framework to explore constructs of reach, effectiveness, adoption, implementation, and maintenance.

RESULTS

We present two case studies of PCPR implementation - breast cancer and colorectal polyps-that showcase diverse workflows for pathology reporting. Cross-pilot learnings emphasize the potential for PCPRs to improve patient satisfaction, knowledge, quality of shared decision-making activities, yet several barriers to dissemination exist.

CONCLUSION

While there is promise in expanding patient-centered cancer communication tools, more work is needed to expand the technological capacity for PCPRs and connect PCPRs to opportunities to reduce costs, improve quality, and reduce waste in care delivery systems.

Exploring the value of using patient-oriented MRI reports in clinical practice - a pilot study

PURPOSE

Standard radiology reports (SRR) are designed to communicate information between doctors. With many patients having instantaneous access to SRRs on patient portals, interpretation without guidance from doctors can cause anxiety and panic. In this pilot study, we designed a patient-centred prostate MRI template report (PACERR) to address some of these challenges and tested whether PACERRs improve patient knowledge and experience.

MATERIALS AND METHODS

Patients booked for clinical prostate MRI were randomly assigned to SRR or SRR + PACERR. Questionnaires included multiple-choice that targeted 4 domains (understanding, usefulness, next steps, emotional experience) hypothesized to improve with patient-centred reports and short answer questions, testing knowledge regarding MRI results. Clinical encounters were observed and recorded to explore whether adding PACERR improved communication. Likert scaled-responses and short-answer questions were compared using Mann-Whitney U test and Kruskal-Wallis test.

RESULTS

Of the 40 participants, the majority were MRI naïve (70%). Patients receiving a PACERR had higher scores in the categories of patient understanding (mean: 4.17 vs. 3.39, p=0.006), usefulness (mean: 4.58 vs. 3.07, p<0.001), and identifying next steps (mean: 1.89 vs. 3.03, p=0.003) but not emotional experience (mean: 4.18 vs. 3.79, p=0.22). PACERR participants found the layout and design more patient friendly (mean: 4.47 vs. 2.61, p<0.001) and easier to understand (mean: 4.37 vs. 2.38, p<0.001). In the knowledge section, overall, the PACERR arm scored better (87% vs. 56%, p=0.004).

CONCLUSION

With the addition of prostate MRI PACERR, participants had better understanding of their results and felt more prepared to involve themselves in discussions with their doctor.

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.