RESUMO
The main purpose of this study is to evaluate and understand the clinical profile of patients presenting to an Indian tertiary care referral centre with Laryngotracheal Stenosis (LTS) and also to emphasise on the outcomes after treatment in these patients. This is a prospective observational study conducted at a tertiary care referral centre which included 18 patients diagnosed with LTS. All patients were evaluated clinically and radiologically to evaluate the degree of stenosis, site and length of the stenotic segment involved, intervened surgical procedure, intraoperative and postoperative complications following the procedure were all documented and taken into consideration. The data collected was analysed. The most common etiological cause of LTS was post intubation (77.8%). 61.5% among the 13 intubated patients had a history of intubation for more than 10 days. 83.3% of the cases had stenosis at the level of the subglottis and cervical trachea level. Post intubational airway stenosis is the most common cause of LTS. A precise assessment of the laryngotracheal complex is the cornerstone of LTS management. The choice of treatment depends on the location, severity, and length of stenosis, as well as on the patient's comorbidities, history of previous interventions, and on the expertise of the surgical team. Application of topical Mitomycin c during surgery reduces the incidence of granulations. Close postoperative follow up for a long time and the necessity of more than one intervention improves results and can spare patients the morbidity and mortality associated with acute airway obstruction.
RESUMO
INTRODUCTION: India reported a severe public health challenge not only due to the COVID-19 outbreak but also the increasing number of associated mucormycosis cases since 2021.This study aimed at developing artificial intelligence based models to predict the risk of mucormycosis among the patients at the time of discharge from hospital. METHODS: The dataset included of 1229 COVID-19 positive patients, and additional 214 inpatients, COVID-19 positive as well as infected with mucormycosis. We used logistic regression, decision tree and random forest and the extreme gradient boosting algorithm. All our models were evaluated with 5-fold validation to derive a reliable estimate of the model error. RESULTS: The logistic regression, XGBoost and random forest performed equally well with AUROC 95.0, 94.0, and 94.0 respectively. The best accuracy and precision (PPV) were 0.91 ± 0.026 and 0.67 ± 0.0526, respectively achieved by XGBoost, followed by logistic regression. This study also determined top five variables namely obesity, anosmia, de novo diabetes, myalgia, and nasal discharge, which showed positive impact towards the risk of mucormycosis. CONCLUSION: The developed model has the potential to predict the patients at high risk and thus, consequently initiating preventive care or aiding in early detection of mucormycosis infection. Thus, this study, holds potential for early treatment and better management of patients suffering from COVID-19 associated mucormycosis.
