Leveraging Large Language Models for Precision Monitoring of Chemotherapy-Induced Toxicities: A Pilot Study with Expert Comparisons and Future Directions.

INTRODUCTION: Large Language Models (LLMs), such as the GPT model family from OpenAI, have demonstrated transformative potential across various fields, especially in medicine. These models can understand and generate contextual text, adapting to new tasks without specific training. This versatility can revolutionize clinical practices by enhancing documentation, patient interaction, and decision-making processes. In oncology, LLMs offer the potential to significantly improve patient care through the continuous monitoring of chemotherapy-induced toxicities, which is a task that is often unmanageable for human resources alone. However, existing research has not sufficiently explored the accuracy of LLMs in identifying and assessing subjective toxicities based on patient descriptions. This study aims to fill this gap by evaluating the ability of LLMs to accurately classify these toxicities, facilitating personalized and continuous patient care. METHODS: This comparative pilot study assessed the ability of an LLM to classify subjective toxicities from chemotherapy. Thirteen oncologists evaluated 30 fictitious cases created using expert knowledge and OpenAI's GPT-4. These evaluations, based on the CTCAE v.5 criteria, were compared to those of a contextualized LLM model. Metrics such as mode and mean of responses were used to gauge consensus. The accuracy of the LLM was analyzed in both general and specific toxicity categories, considering types of errors and false alarms. The study's results are intended to justify further research involving real patients. RESULTS: The study revealed significant variability in oncologists' evaluations due to the lack of interaction with fictitious patients. The LLM model achieved an accuracy of 85.7% in general categories and 64.6% in specific categories using mean evaluations with mild errors at 96.4% and severe errors at 3.6%. False alarms occurred in 3% of cases. When comparing the LLM's performance to that of expert oncologists, individual accuracy ranged from 66.7% to 89.2% for general categories and 57.0% to 76.0% for specific categories. The 95% confidence intervals for the median accuracy of oncologists were 81.9% to 86.9% for general categories and 67.6% to 75.6% for specific categories. These benchmarks highlight the LLM's potential to achieve expert-level performance in classifying chemotherapy-induced toxicities. DISCUSSION: The findings demonstrate that LLMs can classify subjective toxicities from chemotherapy with accuracy comparable to expert oncologists. The LLM achieved 85.7% accuracy in general categories and 64.6% in specific categories. While the model's general category performance falls within expert ranges, specific category accuracy requires improvement. The study's limitations include the use of fictitious cases, lack of patient interaction, and reliance on audio transcriptions. Nevertheless, LLMs show significant potential for enhancing patient monitoring and reducing oncologists' workload. Future research should focus on the specific training of LLMs for medical tasks, conducting studies with real patients, implementing interactive evaluations, expanding sample sizes, and ensuring robustness and generalization in diverse clinical settings. CONCLUSIONS: This study concludes that LLMs can classify subjective toxicities from chemotherapy with accuracy comparable to expert oncologists. The LLM's performance in general toxicity categories is within the expert range, but there is room for improvement in specific categories. LLMs have the potential to enhance patient monitoring, enable early interventions, and reduce severe complications, improving care quality and efficiency. Future research should involve specific training of LLMs, validation with real patients, and the incorporation of interactive capabilities for real-time patient interactions. Ethical considerations, including data accuracy, transparency, and privacy, are crucial for the safe integration of LLMs into clinical practice.

BRAF mutational status is associated with survival outcomes in locally advanced resectable and metastatic NSCLC.

BACKGROUND: Immunotherapy-based treatments have demonstrated high efficacy in patients with advanced and locally advanced non-small-cell lung cancer (NSCLC). BRAF mutations affect a small but significant fraction of NSCLC. The efficacy of these therapies in this subgroup of patients is unknown. MATERIALS AND METHODS: Plasma and tissue samples from 116 resectable stage IIIA/B NSCLC patients, included in NADIM and NADIM II clinical trials (NADIM cohort), and from a prospective academic cohort with 84 stage IV NSCLC patients (BLI-O cohort), were analyzed by next-generation sequencing. RESULTS: The p.G464E, p.G466R, p.G466V, p.G469V, p.L597Q, p.T599I, p.V600E (n = 2) BRAF mutations, were identified in four (3.45 %) samples from the NADIM cohort, all of which were cases treated with neoadjuvant chemoimmunotherapy (CH-IO), and four (4.76 %) samples from the BLI-O cohort, corresponding to cases treated with first-line immunotherapy (n = 2) or CH-IO (n = 2). All these patients were alive and had no evidence of disease at data cut-off. Conversely, patients with BRAF wild-type (wt) tumors in the BLI-O cohort had a median progression-free survival (PFS) of 5.49 months and a median overall survival (OS) of 12.00 months (P-LogRank = 0.013 and 0.046, respectively). Likewise, PFS and OS probabilities at 36 months were 60.5 % and 76.1 % for patients with BRAF-wt tumors in the NADIM cohort. The pathological complete response (pCR) rate after neoadjuvant CH-IO in patients with BRAF-positive tumors (n = 4) was 100 %, whereas the pCR rate in the BRAF-wt population was 44.3 % (RR: 2.26; 95 % CI: 1.78-2.85; P < 0.001). CONCLUSION: BRAF mutations may be a good prognostic factor for advanced and locally advanced NSCLC patients undergoing immunotherapy-based treatments.

The S-REAL study: Spanish real-world data on unresectable stage III NSCLC patients treated with durvalumab after chemoradiotherapy.

OBJECTIVES: The S-REAL study aimed to assess the effectiveness of durvalumab as consolidation therapy after definitive chemoradiotherapy (CRT) in a real-world cohort of patients with locally advanced, unresectable stage III non-small cell lung cancer (LA-NSCLC) included in a Spanish early access program (EAP). METHODS: In this multicentre, observational, retrospective study we analysed data from patients treated in 39 Spanish hospitals, who started intravenous durvalumab (10 mg/kg every 2 weeks) between September 2017 and December 2018. The primary endpoint was progression-free survival (PFS). Secondary endpoints included patient characterization and adverse events of special interest (AESI). RESULTS: A total of 244 patients were followed up for a median of 21.9 months [range 1.2-34.7]. Median duration of durvalumab was 45.5 weeks (11.4 months) [0-145]. Median PFS was 16.7 months (95% CI 12.2-25). No remarkable differences in PFS were observed between patients with programmed cell death-ligand 1 (PD-L1) expression ≥ 1% or < 1% (16.7 versus 15.6 months, respectively). However, PFS was higher in patients who had received prior concurrent CRT (cCRT) versus sequential CRT (sCRT) (20.6 versus 9.4 months). AESIs leading to durvalumab discontinuation were registered in 11.1% of patients. CONCLUSIONS: These results are in line with prior published evidence and confirm the benefits of durvalumab in the treatment of LA-NSCLC patients in a real-world setting. We also observed a lower incidence of important treatment-associated toxicities, such as pneumonitis, compared with the pivotal phase III PACIFIC clinical study.

Addressing lung cancer screening eligibility in Spain using 2013 and 2021 US Preventive Service Task Force criteria: cross-sectional study.

Objectives: The aim of the study was to ascertain the percentage of Spanish lung cancer cases that would fulfil the lung cancer screening inclusion criteria recommended by the United States Preventive Service Task Force (USPSTF) in 2013 and 2021. Methods: A cross-sectional study was carried out. All lung cancer cases registered in the Thoracic Tumor Registry with data on date of birth, date of diagnosis, smoking habit, number of pack-years and time elapsed since smoking cessation were included. Results: The study included 15 006 patients diagnosed with lung cancer in Spain between 2016 and 2022. Eligibility to participate in screening increased from 53.7% to 63.5% (an increase of 9.8%) according to the 2013 and 2021 recommendations, respectively. The percentage of eligible men rose by 9.2 percentage points with the 2021 versus 2013 recommendations, whereas this rise was 11.5 percentage points in women. Under the 2021 recommendations, 36.6% of women and 5.3% of men would not have fulfilled the screening inclusion criteria due to being never-smokers; 14.9% of women and 11.0% of men would not have fulfilled the age criterion; and 27.0% of ex-smokers among women compared to 35.6% among men would not have been eligible due to >15 years having elapsed since smoking cessation. Conclusions: In Spain, over one-third of lung cancer cases could not be detected through screening, by virtue of not meeting the most recent inclusion criteria stated by the USPSTF. The degree of fulfilment in a potential nationwide screening programme should be analysed, with the aim of establishing inclusion criteria in line with each country's context.

Changes in lung cancer survival by TNM stage in the Basque country from 2003 to 2014 according to period of diagnosis.

INTRODUCTION: The objective of this study was to analyze the survival of patients with lung cancer by TNM stage in the 4-year periods 2003-2006, 2007-2010 and 2011-2014, treated in the Basque Health Service, and to compare this with survival in an equivalent sample of the general population. METHODS: A retrospective observational design was applied to cases from the Hospital Cancer Registry of Euskadi. A cohort of 11,635 patients had complete data for the following variables: TNM stage, age, sex, histology, date of diagnosis, vital status and date of death. Relative survival and Cox and parametric regression models were used to assess changes in survival. RESULTS: The lung cancer 5-year survival probability decreased with increasing stage, from 50-65% in patients with stage I disease to 2-3% in those with stage IV disease. Comparing patients diagnosed from 2011-2014 and 2003-2006, we found that survival improved: (a) the risk of death (hazard ratio) in 2003-2006 was 1.66 for stage I, 1.51 for stage II, 1.21 for stage III, and 1.10 for stage IV; (b) the 5-year relative survival increased from 11.0% to 17.8% in the period 2011-2014; and (c) the years of life lost decreased significantly from 2003-2006 to 2011-2014, varying between 6.16 (stage I) and 16.21 (stage IV). CONCLUSIONS: Survival from lung cancer by stage in the Basque Country has lengthened significantly across all disease stages. Nonetheless, since we estimated that lung cancer patients still have significantly lower mean survival times than the general population, there is a need for more research to improve these outcomes.

Prolonged survival with erlotinib followed by afatinib in a caucasian smoker with metastatic, poorly differentiated large cell carcinoma of the lung: a case report.

Activating mutations in the tyrosine kinase domain of the epidermal growth factor receptor (EGFR; ErbB1) - either exon 19 deletions or exon 21 point mutations - are associated with hypersensitivity to EGFR tyrosine kinase inhibitors (TKIs). EGFR mutations are more frequently found in females, non-smokers, Asians, and patients with adenocarcinoma. We report the case of a 51-year-old Caucasian woman with metastatic NSCLC harboring an EGFR exon 19 deletion although she was a smoker and had a poorly differentiated large cell carcinoma. Following a partial response on 4 months of chemotherapy, the patient progressed and was treated with the reversible EGFR TKI erlotinib for 3 y. The patient then developed resistance to erlotinib and went on to receive the irreversible ErbB Family Blocker afatinib for 1 year, attaining a partial response at 4 months. The impressive survival time attained by our patient highlights the clinical benefit of targeting one or more members of the ErbB Family in patients with disseminated NSCLC and EGFR activating mutations.