Maria Angeles Sala

Dr. Maria Angeles Sala

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 August 2024 in Cancers
Verified
Journal Article
Open access
PDF file
OSOskitz Ruiz Sarrias
Oskitz Ruiz Sarrias
MPMaría Purificación Martínez del Prado
María Purificación Martínez del Prado
MSMaria Angeles Sala
Maria Angeles Sala
JSJosune Azcuna Sagarduy
Josune Azcuna Sagarduy
PCPablo Casado Cuesta
Pablo Casado Cuesta
OBOnintza Sayar Beristain
Onintza Sayar Beristain
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.

12 August 2025 in The Lancet Regional Health - Europe
Verified
Journal Article
Open access
Mariano ProvencioMariano Provencio
Mariano Provencio
MCManuel Cobo
Manuel Cobo
DRDelvys Rodriguez-Abreu
Delvys Rodriguez-Abreu
ECEnric Carcereny
Enric Carcereny
RCRafael López Castro
Rafael López Castro
SVSergio Vázquez
Sergio Vázquez
Among patients with lung cancer, treatment with novel oncological agents may influence the risk of developing Second Primary Cancers (SPCs). We aimed to evaluate the incidence of SPCs in patients with lung cancer according to the type of oncological treatment received. We conducted an observational, prospective, nationwide study based on the Spanish Thoracic Tumour Registry (TTR), between August 2016 and March 2023. Eligible patients aged over 18 years, diagnosed with lung cancer, and who achieved tumour remission were included. A total of 20,574 patients were included. After a median follow-up of 41.2 months (95% CI 40.2–42.2), 480 patients developed a SPC (2.3%). The overall incidence was higher among those treated with chemotherapy (2.9%) compared with those receiving immunotherapy (2.1%) or targeted therapy (1.5%) (p < 0.001). The cumulative incidence of SPCs at 12 months for patients that received chemotherapy was 1.22% (95% CI 0.99–1.45), 0.85% (95% CI 0.62–1.08) for immunotherapy and 0.67% (95% CI 0.34–0.99) for targeted therapy (p < 0.001). In the adjusted multivariate model, both immunotherapy and targeted therapy were associated with a reduced risk of SPCs: HR = 0.470 (95% CI 0.338–0.654) and HR = 0.701 (95% CI 0.574–0.855), respectively. Additional associated factors with SPCs included metastatic disease, HR = 0.456 (95% CI 0.377–0.552); history of tobacco use, HR = 1.599 (95% CI 1.127–2.269); and current smoking, HR = 1.319 (95% CI 0.923–1.884) p < 0.001. Patients treated with immunotherapy and targeted therapy exhibited a significantly lower incidence of SPCs. Tobacco use was a key associated factor. Strengthening oncological follow-up and promoting interventions to address modifiable risk factors are essential for optimising long-term outcomes in lung cancer survivors. This study was supported by the Spanish Lung Cancer Group (Fundación GECP).

9 September 2024 in Clinical Cancer Research
Verified
Journal Article
Closed access
PDF file
RSRoss A Soo
Ross A Soo
UDUrania Dafni
Urania Dafni
JHJi-Youn Han
Ji-Youn Han
BCByoung Chul Cho
Byoung Chul Cho
Ernest NadalErnest Nadal
Ernest Nadal
RSRolf A. Stahel
Rolf A. Stahel
Purpose: The ETOP 10-16 BOOSTER study was a randomized phase II trial of osimertinib and bevacizumab therapy versus osimertinib therapy in patients with an acquired EGFR T790M mutation. The mechanisms of acquired resistance to osimertinib and bevacizumab have not been described previously. Experimental Design: Next-generation sequencing (Guardant360) was conducted in serial plasma samples. The association between ctDNA and efficacy outcomes was explored, and molecular alterations at progression were described. Results: A total of 136 patients (88% of 155 randomized) had plasma samples at baseline (68 per arm), 110 (71%) at week 9, and 65 (42%) at progression. In a multivariable model for progression-free survival (PFS), the treatment effect was found to differ by smoking status (interaction P = 0.046), with the effect of smoking also differing by baseline EGFR T790M (interaction P = 0.033), whereas both TP53 at baseline and the tissue EGFR exon 21 L858R mutation were significantly associated with worse PFS outcome. Smokers (current/former) without baseline EGFR T790M showed a significant improvement in PFS under combination treatment, albeit with small numbers (P = 0.015). Week-9 EGFR T790M clearance was associated with improved PFS in the osimertinib arm (P = 0.0097). Acquired EGFR C797S mutations were detected in 22% and 13% of patients in the combination and osimertinib arms, respectively. Conclusions: The differential effect of treatment by smoking was not explained by TP53 mutations or other molecular alterations examined. Molecular mechanisms of acquired resistance were detected, but no novel molecular alterations were identified in the combination arm.

15 November 2024
Verified
Other
Open access
PDF file
RSRoss A Soo
Ross A Soo
UDUrania Dafni
Urania Dafni
JHJi-Youn Han
Ji-Youn Han
BCByoung Chul Cho
Byoung Chul Cho
Ernest NadalErnest Nadal
Ernest Nadal
RSRolf A. Stahel
Rolf A. Stahel
Supplementary Figure S3. EGFR T790M mutational status (MD/MND) by treatment arm at baseline (N=136), week 9 (N=110) and progression (N=65).

15 November 2024
Verified
Other
Open access
PDF file
RSRoss A Soo
Ross A Soo
UDUrania Dafni
Urania Dafni
JHJi-Youn Han
Ji-Youn Han
BCByoung Chul Cho
Byoung Chul Cho
Ernest NadalErnest Nadal
Ernest Nadal
RSRolf A. Stahel
Rolf A. Stahel
Supplementary Figure S9. Overall survival for the N=136 patients constituting the biomarker analysis cohort, by baseline mutational status of (A) EGFR T790M (B) TP53.