Development and pilot testing of a conversation aid to support the evaluation of patients with thyroid nodules

Clinician feedback using a shared decision-making tool for the evaluation of patients with thyroid nodules-an observational study

BACKGROUND

We pilot-tested an encounter conversation aid to support shared decision making (SDM) between patients with thyroid nodules and their clinicians.

OBJECTIVE

Characterize the clinician feedback after providing care to patients with thyroid nodules using a tool to promote SDM conversations during the clinical encounter, and evaluate how clinicians used the tool during the visit.

METHODS

Mixed method study in two academic centers in the U.S., including adult patients presenting for evaluation of thyroid nodules and their clinicians. We thematically analyzed interviews with clinicians after they used the SDM tool in at least three visits to characterize their feedback. Additionally, investigators evaluated visits recordings to determine the extent to which clinicians engaged patients in the decision-making process (OPTION score, scale 0 to 100, higher levels indicating higher involvement), the tool's components used (fidelity), and encounter duration. Using a post-visit survey, we evaluated the extent to which clinicians felt the tool was easy to use, helpful, and supportive of the patient-clinician collaboration.

RESULTS

Thirteen clinicians participated in the study and used the SDM tool in the care of 53 patients. Clinicians thought the tool was well-organized and beneficial to patients and clinicians. Clinicians noticed a change in their routine with the use of the conversation aid and suggested it needed to be more flexible to better support varying conversations. The median OPTION score was 34, the fidelity of use 75%, and the median visit duration 17 min. In most encounters, clinicians agreed or strongly agreed the tool was easy to use (86%), helpful (65%), and supported collaboration (62%).

CONCLUSION

Clinicians were able to use a SDM tool in the care of patients with thyroid nodules. Although they wished it were more flexible, they found on the whole that its use in the clinical encounter was beneficial to patients and clinicians.

Stratifying High-Risk Thyroid Nodules Using a Novel Deep Learning System

INTRODUCTION

The current ultrasound scan classification system for thyroid nodules is time-consuming, labor-intensive, and subjective. Artificial intelligence (AI) has been shown to increase the accuracy of predicting the malignancy rate of thyroid nodules. This study aims to demonstrate the state-of-the-art Swin Transformer to classify thyroid nodules.

MATERIALS AND METHODS

Ultrasound images were collected prospectively from patients who received fine needle aspiration biopsy for thyroid nodules from January 2016 to June 2021. One hundred thirty-nine patients with malignant thyroid nodules were enrolled, while 235 patients with benign nodules served as controls. Images were fed to Swin-T and ResNeSt50 models to classify the thyroid nodules.

RESULTS

Patients with malignant nodules were younger and more likely male compared to those with benign nodules. The average sensitivity and specificity of Swin-T were 82.46% and 84.29%, respectively. The average sensitivity and specificity of ResNeSt50 were 72.51% and 77.14%, respectively. Receiver operating characteristics analysis revealed that the area under the curve of Swin-T was higher (AUC=0.91) than that of ResNeSt50 (AUC=0.82). The McNemar test evaluating the performance of these models showed that Swin-T had significantly better performance than ResNeSt50.Swin-T classifier can be a useful tool in helping shared decision-making between physicians and patients with thyroid nodules, particularly in those with high-risk characteristics of sonographic patterns.

Thyroid Cancer Risk Communication in Patients with Thyroid Nodules

The objective of this study is to evaluate thyroid cancer risk clinician-patient communication among patients receiving usual counseling and counseling enhanced by a conversation aid. A secondary analysis of clinical visit recordings and post-visit surveys obtained during a trial assessing the impact of a conversation aid for patients with thyroid nodules was conducted. We assessed how thyroid cancer risk was communicated, different risk communication strategies between groups, and predictors of accurate cancer risk perception. Fifty-nine patients were analyzed. Most were women (90%) and middle-aged (median 57 years). A verbal description of thyroid cancer risk was present most frequently (83%) and was more frequent in the conversation aid than the usual care group (100% vs. 63%, p < 0.001). A numerical description using percentages was present in 41% of visits and was more frequent in the conversation aid group (59% vs. 19%, p = 0.012). Natural frequencies (7%) and positive/negative framing (10%) were utilized less commonly. Uncertainty about risks was not discussed. No predictors of accurate risk perception were identified. Clinicians most commonly present a verbal description of thyroid cancer risk. Less commonly, natural frequencies, negative/positive framing, or uncertainty is discussed. Clinicians caring for patients with thyroid nodules should be aware of different strategies for communicating thyroid cancer risk.

Patient feedback receiving care using a shared decision making tool for thyroid nodule evaluation-an observational study

PURPOSE

To characterize the feedback of patients with thyroid nodules receiving care using a shared decision making (SDM) tool designed to improve conversations with their clinicians related to diagnostic options (e.g. thyroid biopsy, ultrasound surveillance).

METHODS

Investigators qualitatively analyzed post-encounter interviews with patients to characterize their feedback of a SDM tool used during their clinical visits. Additionally, investigators counted instances of diagnostic choice awareness and of patients' expression of a diagnostic management preference in recordings of clinical encounters of adult patients presenting for evaluation of thyroid nodules in which the SDM tool was used.

RESULTS

In total, 53 patients (42 (79%) women); median age 62 years were enrolled and had consultations supported by the SDM tool. Patients were favorable about the design of the SDM tool and its ability to convey information about options and support patient-clinician interactions. Patients identified opportunities to improve the tool through adding more content and improve its use in practice through training of clinicians in its use. There was evidence of diagnostic choice awareness in 52 (98%) of these visits and patients expressed a diagnostic management preference in 40 (76%).

CONCLUSION

User centered design including feedback from patients and real life observation supports the use of the SDM tool to facilitate collaboration between patients and clinicians.

What do patients want to know about surgery for low-risk thyroid cancer? A qualitative study

BACKGROUND

Shared decision-making about treatment for low-risk thyroid cancer requires patients and surgeons to work together to select treatment that best balances risks and expected outcomes with patient preferences and values. To participate, patients must be activated and ask questions. We aimed to characterize what topics patients prioritize during treatment decision-making.

METHODS

We identified substantive questions by patients with low-risk (cT1-2, N0) thyroid cancer during audio-recorded consultations with 9 surgeons at 2 unique health care systems. Logistics questions were excluded. Qualitative content analysis was used to identify major themes among patients' questions and surgeon responses.

RESULTS

Overall, 28 of 30 patients asked 253 substantive questions, with 2 patients not asking any substantive questions (median 8, range 0-25). Patients were 20 to 71 years old, mostly White (86.7%) and female (80.0%). The questions addressed extent of surgery, hormone supplementation, risk of cancer progression, radioactive iodine, and etiology of thyroid cancer. When patients probed for a recommendation regarding extent of surgery, surgeons often responded indirectly. When patients asked how surgery could impact quality of life, surgeons focused on oncologic benefits and surgical risk. Patients commonly asked about hormone supplementation and radioactive iodine.

CONCLUSION

Patient questions focused on the decision regarding extent of surgery, quality of life, and nonsurgical aspects of thyroid cancer care. Surgeon responses do not consistently directly answer patients' questions but focus on the risks, benefits, and conduct of surgery itself. These findings suggest an opportunity to help surgeons with resources to improve shared decision-making by providing information that patients prioritize.

Design and Virtual Workflow of a Patient Database for Clinical and Pharmaceutical Trials Part II: A Prototype for Endocrinology

Background In previous work, we have reported that patient recruitment is closely related to electronic health records (EHR). As a result, the next step of investigation would lead to the implementation of research practices for using EHR in selecting patients for clinical trials. Towards that end, open-source software offers several integrated solutions that can meet the needs of an EHR and patient recruitment.  Aim In the present work, we have designed a prototype of a patient recruitment system using open-source tools. The proposed prototype can draw data from a patient management system and present selected patients based on specific criteria.  Methods For the objective of the present study, we have used the methodology described previously. In particular, we recorded numerous integrated solutions for EHR from the area of free and open-source software. Open Electronic Medical Records (OpenEMR) ranked first for functionality and second for usability efficiency. Hence, we relied on OpenEMR to design a prototype patient recruitment system. After the installation and commissioning of OpenEMR, we created appropriate test scenarios. Therefore, populated appropriate patient data in OpenEMR. PhpMyAdmin was installed and commissioned along with the OpenEMR installation. This tool is used to manage MySQL database systems. MySQL is the database system that programmers rely on to develop OpenEMR.  Results A prototype patient recruitment system was designed, which draws data from a view of the OpenEMR database to present results based on criteria.  Conclusions After the adaptation of the database and the design of the proposed solution, we concluded, based on the prototype results, that there is potential for developing an integrated patient recruitment management system. This management system can be based on the implementation of complex criteria and present results according to the needs of the end-user.