RESUMEN
BACKGROUND: Laryngeal carcinoma (LC) remains a significant economic and emotional problem to the healthcare system and severe social morbidity. New tools as Machine Learning could allow clinicians to develop accurate and reproducible treatments. METHODS: This study aims to evaluate the performance of a ML-algorithm in predicting 1- and 3-year overall survival (OS) in a cohort of patients surgical treated for LC. Moreover, the impact of different adverse features on prognosis will be investigated. Data was collected on oncological FU of 132 patients. A retrospective review was performed to create a dataset of 23 variables for each patient. RESULTS: The decision-tree algorithm is highly effective in predicting the prognosis, with a 95% accuracy in predicting the 1-year survival and 82.5% in 3-year survival; The measured AUC area is 0.886 at 1-year Test and 0.871 at 3-years Test. The measured AUC area is 0.917 at 1-year Training set and 0.964 at 3-years Training set. Factors that affected 1yOS are: LNR, type of surgery, and subsite. The most significant variables at 3yOS are: number of metastasis, perineural invasion and Grading. CONCLUSIONS: The integration of ML in medical practices could revolutionize our approach on cancer pathology.
Asunto(s)
Neoplasias Laríngeas , Humanos , Proyectos Piloto , Neoplasias Laríngeas/cirugía , Aprendizaje Automático , Algoritmos , Pronóstico , Estudios RetrospectivosRESUMEN
BACKGROUND: We prospectively evaluated the efficacy of hyaluronic acid (HA) as an adjuvant treatment to hasten the improvement of nasal respiration and to minimize patients' discomfort in the postoperative radiofrequency volumetric tissue reduction (RFVTR) of inferior turbinates. METHODS: We enrolled 57 patients randomly assigned into two groups, HA (22 patients) and saline group (35 patients), which received isotonic saline nasal irrigation. We used the monopolar device somnoplasty for all patients. Visual analogic scale (VAS) and nasal endoscopy were used to assess the outcomes of the treatments during the 1st month of follow-up. RESULTS: The mean VAS score of the HA group at the 1st week was significantly lower than the control group (3.36 ± 1.89 versus 6.95 ± 1.52; p < 0.05). The VAS score remained significantly lower in the HA group also at the 2nd week (3.43 ± 1.27 versus 5.75±1.39; p < 0.05), becoming similar to the control group at the 4th week (p = ns). Since the first visit the HA group also showed significantly lower crust score than the saline group (p < 0.05), and there was no crust found in either group at the last visit. The compliance to treatment was similar in both groups. CONCLUSION: The results of this prospective study suggest a role of HA as a supportive treatment for faster improvement of nasal respiration, also minimizing patients' discomfort in postoperative nasal surgery, promoting nasal mucosa healing in postoperative RFVTR for inferior turbinate hypertrophy.