Conversational artificial intelligence (chatGPT™) in the management of complex colorectal cancer patients: early experience

INTRODUCTION

In 2022 chatGPT™ (OpenAI, San Francisco) was introduced to the public. The complex reasoning and the natural language processing (NLP) ability of the AI platform has generated much excitement about the potential applications. This study conducted a preliminary analysis of the chatGPT™'s ability to formulate a management plan in accordance with oncological principles for patients with colorectal cancer.

METHODOLOGY

Colorectal cancer cases discussed in the multidisciplinary tumor (MDT) board at a single tertiary institution between September 2022 and January 2023 were prospectively collected. The treatment recommendations made by the chatGPT™ for Stage IV, recurrent, synchronous colorectal cancer were analysed for adherence to oncological principles. The recommendations by chatGPT™ were compared with the decision plans made by the MDT.

RESULTS

In all cases, the chatGPT™ was able to adhere to oncological principles. The recommendations in all 30 cases factored in the patient's overall health and functional status. The oncological management recommendation concordance rate between chatGPT™ and the MDT was 86.7%.

CONCLUSIONS

This study shows a high concordance rate of the chatGPT™'s recommendations with that given by the MDT in the management of complex colorectal patients. This will need to be verified in a larger prospective study.

Management of Progressive Radioiodine-Refractory Thyroid Carcinoma: Current Perspective

Patients with thyroid cancer (TC) usually have an excellent prognosis; however, 5-10% of them develop an advanced disease. The prognosis of this subgroup is still favourable if the lesions respond to radioactive iodine (RAI) treatment. Nearly two-thirds of advanced TC patients become RAI-refractory (RAI-R), and their management is challenging. A multidisciplinary approach in the context of a tumour board is essential to define a personalized strategy. Systemic therapy is not always the best option. In case of slow neoplastic growth and low tumour burden, active surveillance may represent a valuable choice. Local approaches might be considered if the disease progression is limited to a single or few lesions, also in combination and during systemic therapy. Antiresorptive treatment may be started in presence of bone metastases. In case of rapid and/or symptomatic progression involving multiple lesions and/or organs, systemic therapy has to be considered, in absence of contraindications. The multi-kinase inhibitors (MKIs) lenvatinib and sorafenib are currently available as first-line treatment for advanced progressive RAI-R TC. Among second-line options, cabozantinib has been recently approved in RAI-R TC who progressed during MKIs targeting the vascular endothelial growth factor receptor (VEGFR). In the last few years, next-generation sequencing (NGS) assays have been increasingly employed, permitting identification of the genetic alterations harboured by TC, with a significant impact on patients' management. Novel selective targeted therapies have been introduced for the treatment of RAI-R TC in selected cases: REarranged during Transfection (RET) inhibitors (selpercatinib and pralsetinib) and Tropomyosin Receptor Kinase (TRK) inhibitors (larotrectinib and entrectinib) have recently expanded the panorama of the therapeutic options. Moreover, immune checkpoint inhibitors (ICIs) have shown promising results, and they are still under investigation.

Clinician perspectives on clinical decision support systems in lung cancer: Implications for shared decision-making

Background

Lung cancer treatment decisions are typically made among clinical experts in a multidisciplinary tumour board (MTB) based on clinical data and guidelines. The rise of artificial intelligence and cultural shifts towards patient autonomy are changing the nature of clinical decision‐making towards personalized treatments. This can be supported by clinical decision support systems (CDSSs) that generate personalized treatment information as a basis for shared decision‐making (SDM). Little is known about lung cancer patients' treatment decisions and the potential for SDM supported by CDSSs. The aim of this study is to understand to what extent SDM is done in current practice and what clinicians need to improve it.

Objective

To explore (1) the extent to which patient preferences are taken into consideration in non‐small‐cell lung cancer (NSCLC) treatment decisions; (2) clinician perspectives on using CDSSs to support SDM.

Design

Mixed methods study consisting of a retrospective cohort study on patient deviation from MTB advice and reasons for deviation, qualitative interviews with lung cancer specialists and observations of MTB discussions and patient consultations.

Setting and Participants

NSCLC patients (N = 257) treated at a single radiotherapy clinic and nine lung cancer specialists from six Dutch clinics.

Results

We found a 10.9% (n = 28) deviation rate from MTB advice; 50% (n = 14) were due to patient preference, of which 85.7% (n = 12) chose a less intensive treatment than MTB advice. Current MTB recommendations are based on clinician experience, guidelines and patients' performance status. Most specialists (n = 7) were receptive towards CDSSs but cited barriers, such as lack of trust, lack of validation studies and time. CDSSs were considered valuable during MTB discussions rather than in consultations.

Conclusion

Lung cancer decisions are heavily influenced by clinical guidelines and experience, yet many patients prefer less intensive treatments. CDSSs can support SDM by presenting the harms and benefits of different treatment options rather than giving single treatment advice. External validation of CDSSs should be prioritized.

Patient or Public Contribution

This study did not involve patients or the public explicitly; however, the study design was informed by prior interviews with volunteers of a cancer patient advocacy group. The study objectives and data collection were supported by Dutch health care insurer CZ for a project titled ‘My Best Treatment’ that improves patient‐centeredness and the lung cancer patient pathway in the Netherlands.

Exhaustive analysis from the Rhone-Alpes region

OBJECTIVE

Epithelial ovarian cancer (EOC) is a poor prognosis disease partly linked to diagnosis at an advanced stage. The quality of care management is a factor that needs to be explored, more specifically optimal organisation of first-line treatment.

METHODS

A retrospective study, dealing with all patients diagnosed within the Rhone-Alpes region with initial diagnosis EOC in 2012, was performed. The aim was to describe the impact of multidisciplinary tumour boards (MTB) in the organisation of care and the consequence on the patient's outcomes.

RESULTS

271 EOC were analysed. 206 patients had an advanced EOC. Median progression-free survival (PFS) is 17.8 months (CI95%, 14.6-21.2) for AOC. 157 patients (57.9%) had a front-line surgery versus 114 patients (42.1%) interval debulking surgery. PFS for AOC patients with no residual disease is 24.3 months compared with 15.3 months for patients with residual disease (p = .01). No macroscopic residual disease is more frequent in the patients discussed before surgery in MTB compared with patients not submitted before surgery (73% vs. 56.2%, p < .001).

CONCLUSION

These results highlight the heterogeneity of medical practices in terms of front-line surgery versus interval surgery, in the administration of neoadjuvant chemotherapy and in the setting of MTB discussion.

Pilot evaluation of a novel observational tool for collaboration and communication within multidisciplinary team meetings (MDTs)

BACKGROUND

Despite widespread use of multidisciplinary team meetings (MDTs) to facilitate patient care, little evidence exists that MDTs improve patient survival or impact care. Research into MDT function and outcome is limited. This pilot study looks to validate a novel tool developed to assess MDT functioning.

METHODS

A tool was developed with predefined Likert behaviour stems in the areas of structure, communication and collaboration. The tool was evaluated in nine MDTs by three independent observers and included participant evaluation. Inter-rater reliability was calculated with intraclass-correlation coefficients (ICC); Student's t-test was used to calculate significance in participant evaluation and matched observations.

RESULTS

The tool was used to evaluate 9 MDTs, discussing 133 cases. The overall ICC for the three coders was 0.935; for each MDT: 0.776-0.917. The inter-rater reliability for each MDT observation ranged from 0.245-0.923; the majority with an ICC >0.8. No significant difference was noted between participant evaluation and observer response.

DISCUSSION

MDTs provide a means of coordinating complex care for patients. This tool provides a means of evaluating group interaction within MDTs and is designed for use by different medical personnel. The pilot study has shown promising ICC; further evaluation is needed using a broader group of MDTs and including case complexity and outcome.