Exclusive oral antibiotic treatment for hospitalized community-acquired pneumonia: a post-hoc analysis of a randomized clinical trial.

OBJECTIVES: In this study, we aimed to assess the efficacy of different ways of administration and types of beta-lactams for hospitalized community-acquired pneumonia (CAP). METHODS: In this post-hoc analysis of randomized controlled trials (RCT) on patients hospitalized for CAP (pneumonia short treatment trial) comparing 3-day vs. 8-day durations of beta-lactams, which concluded to non-inferiority, we included patients who received either amoxicillin-clavulanate (AMC) or third-generation cephalosporin (3GC) regimens, and exclusively either intravenous or oral treatment for the first 3 days (followed by either 5 days of oral placebo or AMC according to randomization). The choice of route and molecule was left to the physician in charge. The main outcome was a failure at 15 days after the first antibiotic intake, defined as temperature >37.9°C, and/or absence of resolution/improvement of respiratory symptoms, and/or additional antibiotic treatment for any cause. The primary outcome according to the route of administration was evaluated through logistic regression. Inverse probability treatment weighting with a propensity score model was used to adjust for non-randomization of treatment routes and potential confounders. The difference in failure rates was also evaluated among several sub-populations (AMC vs. 3GC treatments, intravenous vs. oral AMC, patients with multi-lobar infection, patients aged ≥65 years old, and patients with CURB65 scores of 3-4). RESULTS: We included 200 patients from the original trial, with 93/200 (46.5%) patients only treated with intravenous treatment and 107/200 (53.5%) patients only treated with oral therapy. The failure rate at Day 15 was not significantly different among patients treated with initial intravenous vs. oral treatment [25/93 (26.9%) vs. 28/107 (26.2%), adjusted odds ratios (aOR) 0.973 (95% CI 0.519-1.823), p 0.932)]. Failure rates at Day 15 were not significantly different among the subgroup populations. DISCUSSION: Among hospitalized patients with CAP, there was no significant difference in efficacy between initial intravenous and exclusive oral treatment. TRIAL REGISTRATION: This trial is registered with ClinicalTrials.gov, NCT01963442.

Validating the accuracy of deep learning for the diagnosis of pneumonia on chest x-ray against a robust multimodal reference diagnosis: a post hoc analysis of two prospective studies.

BACKGROUND: Artificial intelligence (AI) seems promising in diagnosing pneumonia on chest x-rays (CXR), but deep learning (DL) algorithms have primarily been compared with radiologists, whose diagnosis can be not completely accurate. Therefore, we evaluated the accuracy of DL in diagnosing pneumonia on CXR using a more robust reference diagnosis. METHODS: We trained a DL convolutional neural network model to diagnose pneumonia and evaluated its accuracy in two prospective pneumonia cohorts including 430 patients, for whom the reference diagnosis was determined a posteriori by a multidisciplinary expert panel using multimodal data. The performance of the DL model was compared with that of senior radiologists and emergency physicians reviewing CXRs and that of radiologists reviewing computed tomography (CT) performed concomitantly. RESULTS: Radiologists and DL showed a similar accuracy on CXR for both cohorts (p ≥ 0.269): cohort 1, radiologist 1 75.5% (95% confidence interval 69.1-80.9), radiologist 2 71.0% (64.4-76.8), DL 71.0% (64.4-76.8); cohort 2, radiologist 70.9% (64.7-76.4), DL 72.6% (66.5-78.0). The accuracy of radiologists and DL was significantly higher (p ≤ 0.022) than that of emergency physicians (cohort 1 64.0% [57.1-70.3], cohort 2 63.0% [55.6-69.0]). Accuracy was significantly higher for CT (cohort 1 79.0% [72.8-84.1], cohort 2 89.6% [84.9-92.9]) than for CXR readers including radiologists, clinicians, and DL (all p-values < 0.001). CONCLUSIONS: When compared with a robust reference diagnosis, the performance of AI models to identify pneumonia on CXRs was inferior than previously reported but similar to that of radiologists and better than that of emergency physicians. RELEVANCE STATEMENT: The clinical relevance of AI models for pneumonia diagnosis may have been overestimated. AI models should be benchmarked against robust reference multimodal diagnosis to avoid overestimating its performance. TRIAL REGISTRATION: NCT02467192 , and NCT01574066 . KEY POINT: • We evaluated an openly-access convolutional neural network (CNN) model to diagnose pneumonia on CXRs. • CNN was validated against a strong multimodal reference diagnosis. • In our study, the CNN performance (area under the receiver operating characteristics curve 0.74) was lower than that previously reported when validated against radiologists' diagnosis (0.99 in a recent meta-analysis). • The CNN performance was significantly higher than emergency physicians' (p ≤ 0.022) and comparable to that of board-certified radiologists (p ≥ 0.269).