Predicting the microbial cause of community-acquired pneumonia: can physicians or a data-driven method differentiate viral from bacterial pneumonia at patient presentation?

BACKGROUND: Community-acquired pneumonia (CAP) requires urgent and specific antimicrobial therapy. However, the causal pathogen is typically unknown at the point when anti-infective therapeutics must be initiated. Physicians synthesize information from diverse data streams to make appropriate decisions. Artificial intelligence (AI) excels at finding complex relationships in large volumes of data. We aimed to evaluate the abilities of experienced physicians and AI to answer this question at patient admission: is it a viral or a bacterial pneumonia? METHODS: We included patients hospitalized for CAP and recorded all data available in the first 3-h period of care (clinical, biological and radiological information). For this proof-of-concept investigation, we decided to study only CAP caused by a singular and identified pathogen. We built a machine learning model prediction using all collected data. Finally, an independent validation set of samples was used to test the pathogen prediction performance of: (i) a panel of three experts and (ii) the AI algorithm. Both were blinded regarding the final microbial diagnosis. Positive likelihood ratio (LR) values > 10 and negative LR values < 0.1 were considered clinically relevant. RESULTS: We included 153 patients with CAP (70.6% men; 62 [51-73] years old; mean SAPSII, 37 [27-47]), 37% had viral pneumonia, 24% had bacterial pneumonia, 20% had a co-infection and 19% had no identified respiratory pathogen. We performed the analysis on 93 patients as co-pathogen and no-pathogen cases were excluded. The discriminant abilities of the AI approach were low to moderate (LR+ = 2.12 for viral and 6.29 for bacterial pneumonia), and the discriminant abilities of the experts were very low to low (LR+ = 3.81 for viral and 1.89 for bacterial pneumonia). CONCLUSION: Neither experts nor an AI algorithm can predict the microbial etiology of CAP within the first hours of hospitalization when there is an urgent need to define the anti-infective therapeutic strategy.

Monitoring Transcutaneously Measured Partial Pressure of CO2 During Intubation in Critically Ill Subjects.

BACKGROUND: The risk for severe hypoxemia during endotracheal intubation is a major concern in the ICU, but little attention has been paid to CO2 variability. The objective of this study was to assess transcutaneously measured partial pressure of CO2 ([Formula: see text]) throughout intubation in subjects in the ICU who received standard oxygen therapy, high-flow nasal cannula oxygen therapy, or noninvasive ventilation for preoxygenation. We hypothesized that the 3 methods differ in terms of ventilation and CO2 removal. METHODS: In this single-center, prospective, observational study, we recorded [Formula: see text] from preoxygenation to 3 h after the initiation of mechanical ventilation among subjects requiring endotracheal intubation. Subjects were sorted into 3 groups according to the preoxygenation method. We then assessed the link between [Formula: see text] variability and the development of postintubation hypotension. RESULTS: A total of 202 subjects were included in the study. The [Formula: see text] values recorded at endotracheal intubation, at the initiation of mechanical ventilation, and after 30 min and 1 h of mechanical ventilation were significantly higher than those recorded during preoxygenation (P < .05). [Formula: see text] variability differed significantly according to the preoxygenation method (P < .001, linear mixed model). A decrease in [Formula: see text] by > 5 mm Hg within 30 min after the start of mechanical ventilation was independently associated with postintubation hypotension (odds ratio = 2.14 [95% CI 1.03-4.44], P = .039) after adjustments for age, Simplified Acute Physiology Score II, COPD, cardiac comorbidity, the use of propofol for anesthetic induction, and minute ventilation at the start of mechanical ventilation. CONCLUSIONS: [Formula: see text] variability during intubation is significant and differs with the method of preoxygenation. A decrease in [Formula: see text] after the beginning of mechanical ventilation was associated with postintubation hypotension. (ClinicalTrials.gov registration NCT0388430.).

Severe leptospirosis in non-tropical areas: a nationwide, multicentre, retrospective study in French ICUs.

PURPOSE: To report the incidence, risk factors, clinical presentation, and outcome predictors of severe leptospirosis requiring intensive care unit (ICU) admission in a temperate zone. METHODS: LEPTOREA was a retrospective multicentre study conducted in 79 ICUs in metropolitan France. Consecutive adults admitted to the ICU for proven severe leptospirosis from January 2012 to September 2016 were included. Multiple correspondence analysis (MCA) and hierarchical classification on principal components (HCPC) were performed to distinguish different clinical phenotypes. RESULTS: The 160 included patients (0.04% of all ICU admissions) had median values of 54 years [38-65] for age, 40 [28-58] for the SAPSII, and 11 [8-14] for the SOFA score. Hospital mortality was 9% and was associated with older age; worse SOFA score and early need for endotracheal ventilation and/or renal replacement therapy; chronic alcohol abuse and worse hepatic dysfunction; confusion; and higher leucocyte count. Four phenotypes were identified: moderately severe leptospirosis (n = 34, 21%) with less organ failure and better outcomes; hepato-renal leptospirosis (n = 101, 63%) with prominent liver and kidney dysfunction; neurological leptospirosis (n = 8, 5%) with the most severe organ failures and highest mortality; and respiratory leptospirosis (n = 17, 11%) with pulmonary haemorrhage. The main risk factors for leptospirosis contamination were contact with animals, contact with river or lake water, and specific occupations. CONCLUSIONS: Severe leptospirosis was an uncommon reason for ICU admission in metropolitan France and carried a lower mortality rate than expected based on the high severity and organ-failure scores. The identification in our population of several clinical presentations may help clinicians establish an appropriate index of suspicion for severe leptospirosis.

Diagnostic performance of multiplex PCR on pulmonary samples versus nasopharyngeal aspirates in community-acquired severe lower respiratory tract infections.

BACKGROUND: PCR-based techniques for the diagnosis of community- acquired severe lower respiratory tract infections are becoming the standard of care. However, their relative ability to identify either atypical bacteria or viruses that cause LRTI from clinical samples from various sources is yet to be determined. OBJECTIVES AND STUDY DESIGN: The aim of our study was to compare the diagnostic yield of nasopharyngeal aspirates with that of pulmonary samples for the etiological diagnosis of severe acute lower respiratory tract infections by multiplex PCR. Patients were adults with community-acquired pneumonia or acute exacerbation of chronic obstructive pulmonary disease. RESULTS: We obtained concordant results for 81 (79%) of the 103 pairs of samples. In 14 of the 22 discordant results, more pathogens were evidenced in the lower respiratory tract samples. CONCLUSIONS: Pulmonary samples had a similar diagnostic sensitivity for virus detection by multiplex PCR as nasopharyngeal aspirates. In contrast, in our study, the diagnostic efficacy of pulmonary samples for Legionella pneumophila over simple aspirates was clearly superior.

Parathyroid hormone decline 4 hours after total thyroidectomy accurately predicts hypocalcemia.

BACKGROUND: The level of parathyroid hormone (iPTH) serum has been controversial in the prediction of postthyroidectomy hypocalcemia. Analysis of the decrease between preoperative and postoperative iPTH levels should be more accurate. Therefore, the aim of our study was to prospectively establish the reliability of the iPTH decrease for early diagnosis of postoperative hypocalcemia and to identify the patients who are not at risk for hypocalcemia. METHODS: A prospective study of 137 consecutive patients who underwent total thyroidectomy was performed. Serum iPTH level was measured preoperatively and 4 hours postoperatively (iPTH(H4)). The sensitivity, specificity, and positive and negative predictive values for the iPTH(H4) and for the iPTH decline were estimated by confidence interval from thresholds determined by ROC curve analysis. RESULTS: Thirty-nine patients developed hypocalcemia (28.5%). Patients who developed hypocalcemia had a significantly lower iPTH(H4) and a significantly greater iPTH decrease (P < .001). The thresholds enabling prediction of hypocalcemia were 19.4 ng/L for iPTH(H4) and 68.5% for iPTH decline. Sensitivity, specificity, and positive and negative predictive values for iPTH(H4) were 84.6%, 92.9%, 82.5%, and 93.8% (overall accuracy, 90.5%). iPTH decline was more accurate to predict hypocalcemia (sensitivity, 97.4%; specificity, 95.9%; positive predictive values 90.5%; negative predictive values, 98.6%; and overall accuracy, 96.4%). CONCLUSION: The decrease in iPTH is more precise than the iPTH(H4) alone and can accurately predict hypocalcemia after total thyroidectomy. Patients with a decrease in iPTH less than 68.5% can be discharged at postoperative day one without any supplementation. Patients with iPTH decline more than 68.5% should be administered calcium and vitamin D supplementation before symptoms appear.

Reproducibility and validity of the French version of the long international physical activity questionnaire in patients with type 2 diabetes.

BACKGROUND: Increasing physical activity and decreasing sedentary time are cornerstones in the management of type 2 diabetes (T2DM). However, there are few instruments available to measure physical activity in this population. We translated the long version of the International Physical Activity Questionnaire (IPAQ-L) into French and studied its reproducibility and validity in patients with T2DM. METHODS: Reproducibility was studied by 2 telephone administrations, 8 days apart. Concurrent validity was tested against pedometry for 7 days during habitual life. RESULTS: One-hundred forty-three patients with T2DM were recruited (59% males; age: 60.9 ± 10.5 years; BMI: 31.2 ± 5.2 kg/m2; HbA1c: 7.4 ± 1.2%). Intraclass correlation coefficients (95% CI) for repeated administration (n = 126) were 0.74 (0.61-0.83) for total physical activity, 0.72 (0.57-0.82) for walking, and 0.65 (0.51-0.78) for sitting time. Total physical activity and walking (MET-min·week-1) correlated with daily steps (Spearman r = .24 and r = .23, respectively, P < .05). Sitting time (min·week-1) correlated negatively with daily steps in women (r = -0.33; P < .05). CONCLUSION: Our French version of the IPAQ-L appears reliable to assess habitual physical activity and sedentary time in patients with T2DM, confirming previous data in nonclinical populations.