Transient diabetes insipidus in critically ill COVID19 patients.

PURPOSE: Vasopressin has become an important vasopressor drug while treating a critically ill patient to maintain adequate mean arterial pressure. Diabetes insipidus (DI) is a rare syndrome characterized by the excretion of a large volume of diluted urine, inappropriate for water homeostasis. We noticed that several COVID19 patients developed excessive polyuria suggestive of DI, with a concomitant plasma sodium-level increase and/or low urine osmolality. We noticed a temporal relationship between vasopressin treatment cessation and polyuria periods. We reviewed those cases to better describe this phenomenon. METHODS: We retrospectively collected COVID19 ECMO patients' (from July 6, 2020, to November 30, 2021) data from the electronic medical records. By examining urine output, urine osmolality (if applicable), plasma sodium level, and plasma osmolality, we set DI diagnosis. We described the clinical course of DI episodes and compared baseline characteristics between patients who developed DI and those who did not. RESULTS: Out of 37 patients, 12 had 18 episodes of DI. These patients were 7 years younger and had lower severity scores (APACHE-II and SOFA). Mortality difference was not seen between groups. 17 episodes occurred after vasopressin discontinuation; 14 episodes were treated with vasopressin reinstitution. DI lasted for a median of 21 h, with a median increase of 14 mEq/L of sodium. CONCLUSIONS: Temporary DI prevalence after vasopressin discontinuation in COVID19 ECMO patients might be higher than previously described for vasopressin-treated patients.

A novel machine learning model to predict respiratory failure and invasive mechanical ventilation in critically ill patients suffering from COVID-19.

In hypoxemic patients at risk for developing respiratory failure, the decision to initiate invasive mechanical ventilation (IMV) may be extremely difficult, even more so among patients suffering from COVID-19. Delayed recognition of respiratory failure may translate into poor outcomes, emphasizing the need for stronger predictive models for IMV necessity. We developed a two-step model; the first step was to train a machine learning predictive model on a large dataset of non-COVID-19 critically ill hypoxemic patients from the United States (MIMIC-III). The second step was to apply transfer learning and adapt the model to a smaller COVID-19 cohort. An XGBoost algorithm was trained on data from the MIMIC-III database to predict if a patient would require IMV within the next 6, 12, 18 or 24 h. Patients' datasets were used to construct the model as time series of dynamic measurements and laboratory results obtained during the previous 6 h with additional static variables, applying a sliding time-window once every hour. We validated the adaptation algorithm on a cohort of 1061 COVID-19 patients from a single center in Israel, of whom 160 later deteriorated and required IMV. The new XGBoost model for the prediction of the IMV onset was trained and tested on MIMIC-III data and proved to be predictive, with an AUC of 0.83 on a shortened set of features, excluding the clinician's settings, and an AUC of 0.91 when the clinician settings were included. Applying these models "as is" (no adaptation applied) on the dataset of COVID-19 patients degraded the prediction results to AUCs of 0.78 and 0.80, without and with the clinician's settings, respectively. Applying the adaptation on the COVID-19 dataset increased the prediction power to an AUC of 0.94 and 0.97, respectively. Good AUC results get worse with low overall precision. We show that precision of the prediction increased as prediction probability was higher. Our model was successfully trained on a specific dataset, and after adaptation it showed promise in predicting outcome on a completely different dataset. This two-step model successfully predicted the need for invasive mechanical ventilation 6, 12, 18 or 24 h in advance in both general ICU population and COVID-19 patients. Using the prediction probability as an indicator of the precision carries the potential to aid the decision-making process in patients with hypoxemic respiratory failure despite the low overall precision.