Bleeding In Head And Neck Malignancy : Institution Based Management And Review (preprint)

Introduction:Squamous cell carcinoma constitutes for >90% of head and neck cancers. Acute rupture of irradiated, large vessels is life-threatening complication. The distribution of bleeding foci is diverse and can range from internal or common carotid arteries to branches of the external carotid artery. We intend to assess the management of patients presented in our institution with such acute bleeding episodes and also review the management of carotid blowout syndrome which is an oncological emergency.Methods:Retrospective observational study of 27 cases presented in our institution with acute bleeding due to head and neck cancer for period of two years. After resuscitation and necessary consents, emergency open tracheostomy was done with universal precautions. ECA/CCA ligation was done. All the patients were started on low molecular weight heparin 8 hours post surgery. Therapeutic outcomes were assessed based on simple frequencies and proportions.Results:Of the 27 cases presented in our institution, 19 of them underwent ECA ligation while 8 of them CCA ligation for the control of active bleeding. 12 of 27 patients were receiving definitive chemoradiation of which 7 of them were ongoing. Remaining 15 patients were receiving adjuvant radiotherapy following surgery.19 patients who underwent ECA ligation, had no further bleeding episodes. 8 patients who underwent CCA ligation, had only wound related complications and none of them had neurological deficits. 11 patients were operated during covid-19 period. 4 patients turned out covid positive. None of the medical personnel contacted the infection.Conclusion:Radiotherapy is one the major contributor for CBS. Endovascular procedures can be used for local tumour bleed, threatened, impending and stable acute CBS. Surgical CCA ligation done in bleeds unsuccessful by endovascular procedure and in acute unstable CBS. ECA ligation is safe and effective method to control local tumor bleed. Surgical finesse, careful planning, adherence to universal precautions and institutional protocol can reduce Covid-19 transmission to medical personnel in this testing times.

Machine Learning Based Predictors for COVID-19 Disease Severity (preprint)

Predictors of the need for intensive care and mechanical ventilation can help healthcare systems in planning for surge capacity for COVID-19. We used socio-demographic data, clinical data, and blood panel profile data at the time of initial presentation to develop machine learning algorithms for predicting the need for intensive care and mechanical ventilation. Among the algorithms considered, the Random Forest classifier performed the best with AUC = 0.80 for predicting ICU need and AUC = 0.82 for predicting the need for mechanical ventilation. We also determined the most influential features in making this prediction, and concluded that all three categories of data are important. Finally, we determined the relative importance of blood panel profile data and noted that the AUC dropped by 0.12 units when this data was not included, thus indicating that it provided valuable data in predicting disease severity.