Triage and monitoring of COVID-19 patients in intensive care using unsupervised machine learning.

BACKGROUND: We designed an algorithm to assess COVID-19 patients severity and dynamic intubation needs and predict their length of stay using the breathing frequency (BF) and oxygen saturation (SpO2) signals. METHODS: We recorded the BF and SpO2 signals for confirmed COVID-19 patients admitted to the ICU of a teaching hospital during both the first and subsequent outbreaks of the pandemic in France. An unsupervised machine-learning algorithm (the Gaussian mixture model) was applied to the patients' data for clustering. The algorithm's robustness was ensured by comparing its results against actual intubation rates. We predicted intubation rates using the algorithm every hour, thus conducting a severity evaluation. We designed a S24 severity score that represented the patient's severity over the previous 24 h; the validity of MS24, the maximum S24 score, was checked against rates of intubation risk and prolonged ICU stay. RESULTS: Our sample included 279 patients. . The unsupervised clustering had an accuracy rate of 87.8% for intubation recognition (AUC = 0.94, True Positive Rate 86.5%, true Negative Rate 90.9%). The S24 score of intubated patients was significantly higher than that of non-intubated patients at 48 h before intubation. The MS24 score allowed for the distinguishing between three severity levels with an increased risk of intubation: green (3.4%), orange (37%), and red (77%). A MS24 score over 40 was highly predictive of an ICU stay greater than 5 days at an accuracy rate of 81.0% (AUC = 0.87). CONCLUSIONS: Our algorithm uses simple signals and seems to efficiently visualize the patients' respiratory situations, meaning that it has the potential to assist staffs' in decision-making. Additionally, real-time computation is easy to implement.

Prognostic impact of early adjunctive corticosteroid therapy in non-HIV oncology or haematology patients with Pneumocystis jirovecii pneumonia: A propensity score analysis.

PURPOSE: While early adjunctive corticosteroid therapy (EACST) has been proven effective in HIV patients with Pneumocystis Jirovecii Pneumonia (PJP), data remains controversial concerning non-HIV oncology or haematology patients. METHODS: This retrospective study included cancer patients without HIV and with diagnosis of PJP admitted in a cancer referral centre, from January-1-2010 to March-31-2017. We compared 30-day and 1-year mortality rate, change in the respiratory item of the Sequential Organ Failure Assessment score(SOFA-resp worsening), use of tracheal intubation between day-1 and day-5 of anti-pneumocystis therapy and occurrence of coinfections between patients with EACST and those with no or late corticosteroid therapy, using an inverse probability weighting propensity score-based (IPW) analysis. RESULTS: 133 non-HIV oncology or haematology PJP patients were included (EACST n = 58, others n = 75). The main underlying conditions were haematological malignancies (n = 107, 80,5%), solid tumour (n = 27, 20,3%) and allogeneic stem cell transplantation (n = 17, 12,8%). Overall 30-day and 1-year mortality rate was 24,1% and 56,4%, respectively. IPW analysis found no difference on 30-day (HR = 1.45, 95% CI [0.7-3.04], p = 0.321) and 1-year (HR = 1.25, CI 95% [0.75-2.09], p = 0.39) mortality rate between groups. CONCLUSION: No difference in SOFA-resp worsening, tracheal intubation and coinfections was found between groups. Combination of EACST with anti-pneumocystis therapy in non-HIV onco-haematology PJP-patients was not associated with clinical improvement.