Predicting Severe Haematological Toxicity in Gastrointestinal Cancer Patients Undergoing 5-FU-Based Chemotherapy: A Bayesian Network Approach.

PURPOSE: Severe toxicity is reported in about 30% of gastrointestinal cancer patients receiving 5-Fluorouracil (5-FU)-based chemotherapy. To date, limited tools exist to identify at risk patients in this setting. The objective of this study was to address this need by designing a predictive model using a Bayesian network, a probabilistic graphical model offering robust, explainable predictions. METHODS: We utilized a dataset of 267 gastrointestinal cancer patients, conducting preprocessing, and splitting it into TRAIN and TEST sets (80%:20% ratio). The RandomForest algorithm assessed variable importance based on MeanDecreaseGini coefficient. The bnlearn R library helped design a Bayesian network model using a 10-fold cross-validation on the TRAIN set and the aic-cg method for network structure optimization. The model's performance was gauged based on accuracy, sensitivity, and specificity, using cross-validation on the TRAIN set and independent validation on the TEST set. RESULTS: The model demonstrated satisfactory performance with an average accuracy of 0.85 (±0.05) and 0.80 on TRAIN and TEST datasets, respectively. The sensitivity and specificity were 0.82 (±0.14) and 0.87 (±0.07) for the TRAIN dataset, and 0.71 and 0.83 for the TEST dataset, respectively. A user-friendly tool was developed for clinical implementation. CONCLUSIONS: Despite several limitations, our Bayesian network model demonstrated a high level of accuracy in predicting the risk of developing severe haematological toxicity in gastrointestinal cancer patients receiving 5-FU-based chemotherapy. Future research should aim at model validation in larger cohorts of patients and different clinical settings.

Identification of HLA class I-restricted immunogenic neoantigens in triple negative breast cancer.

Immune checkpoint inhibitor (ICI)-based immunotherapy in triple negative breast cancer (TNBC) is achieving limited therapeutic results, requiring the development of more potent strategies. Combination of ICI with vaccination strategies would enhance antitumor immunity and response rates to ICI in patients having poorly infiltrated tumors. In heavily mutated tumors, neoantigens (neoAgs) resulting from tumor mutations have induced potent responses when used as vaccines. Thus, our aim was the identification of immunogenic neoAgs suitable as vaccines in TNBC patients. By using whole exome sequencing, RNAseq and HLA binding algorithms of tumor samples from a cohort of eight TNBC patients, we identified a median of 60 mutations/patient, which originated a putative median number of 98 HLA class I-restricted neoAgs. Considering a group of 27 predicted neoAgs presented by HLA-A*02:01 allele in two patients, peptide binding to HLA was experimentally confirmed in 63% of them, whereas 55% were immunogenic in vivo in HLA-A*02:01+ transgenic mice, inducing T-cells against the mutated but not the wild-type peptide sequence. Vaccination with peptide pools or DNA plasmids expressing these neoAgs induced polyepitopic T-cell responses, which recognized neoAg-expressing tumor cells. These results suggest that TNBC tumors harbor neoAgs potentially useful in therapeutic vaccines, opening the way for new combined immunotherapies.

Los tics y su relación con las dificultades de aprendizaje: estudio longitudinal de la prevalencia de los tics primarios y comorbilidad asociada en población escolar / Tics and its relationship with academic difficulties: Prevalence of tics and comorbid behavioral disorders in schoolchildren

Con el objetivo de estudiar la prevalencia de los trastornos con tics y la asociación con las dificultades de aprendizaje, se realizó un estudio epidemiológico en una muestra de 1.139 escolares. Los resultados señalaron una prevalencia del 16.86% (IC 95% del 14.10 - 19.63). Además se encontraron dificultades académicas en el 11.9% de los escolares, y la presencia de tics en el 8.6%. La presencia de trastornos de tics no se asoció con el bajo rendimiento académico en la cohorte. Los resultados obtenidos fueron contradictorios con relación a otros estudios publicados anteriormente. Como consecuencia de la divergencia en los resultados, se diseña un segundo estudio, que toma como punto de partida el seguimiento longitudinal de la cohorte de los escolares estudiados. En el análisis de regresión de Cox, durante el periodo de seguimiento de 4 años, la repetición de curso se asoció con una menor frecuencia de apoyo psicológico en el centro escolar (HR = 17.5; IC del 95% 5.7 a 53.9) y menor practica de deporte (HR = 4.02, 95% CI 01/03 a 11/08). No se encontró una asociación entre los tics y mayor riesgo de repetir curso.

In order to study the prevalence of tic disorders and their association with learning difficulties, we conducted an epidemiological study based on a sample of 1,139 schoolchildren. The results showed a prevalence of 16.86% (95% CI 14.10 to 19.63). Besides we found academic difficulties at 11.9% of schoolchildren, and the presence of tics at 8.6%. The presence of tic disorders was not associated with a poor school performance in the cohort. The results were contradictory in relation to other previously published studies. As a consequence of the divergence in the results, we designed a second study, which takes as its starting point the longitudinal follow-up of the cohort studied. In the Cox regression analysis, during the follow-up period of 4 years, the repetition of an academic year was associated with a lower frequency of psychological support at school (HR = 17.5; 95% CI 5.7 to 53 9) and a lower sports practice (HR = 4.02, 95% CI 01/03 to 11/08). We don't found an association between tics and a higher frequency of repeat an academic year.