Pneumocystis jirovecii pneumonia in intensive care units: a multicenter study by ESGCIP and EFISG.

BACKGROUND: Pneumocystis jirovecii pneumonia (PJP) is an opportunistic, life-threatening disease commonly affecting immunocompromised patients. The distribution of predisposing diseases or conditions in critically ill patients admitted to intensive care unit (ICU) and subjected to diagnostic work-up for PJP has seldom been explored. MATERIALS AND METHODS: The primary objective of the study was to describe the characteristics of ICU patients subjected to diagnostic workup for PJP. The secondary objectives were: (i) to assess demographic and clinical variables associated with PJP; (ii) to assess the performance of Pneumocystis PCR on respiratory specimens and serum BDG for the diagnosis of PJP; (iii) to describe 30-day and 90-day mortality in the study population. RESULTS: Overall, 600 patients were included in the study, of whom 115 had presumptive/proven PJP (19.2%). Only 8.8% of ICU patients subjected to diagnostic workup for PJP had HIV infection, whereas hematological malignancy, solid tumor, inflammatory diseases, and solid organ transplants were present in 23.2%, 16.2%, 15.5%, and 10.0% of tested patients, respectively. In multivariable analysis, AIDS (odds ratio [OR] 3.31; 95% confidence interval [CI] 1.13-9.64, p = 0.029), non-Hodgkin lymphoma (OR 3.71; 95% CI 1.23-11.18, p = 0.020), vasculitis (OR 5.95; 95% CI 1.07-33.22, p = 0.042), metastatic solid tumor (OR 4.31; 95% CI 1.76-10.53, p = 0.001), and bilateral ground glass on CT scan (OR 2.19; 95% CI 1.01-4.78, p = 0.048) were associated with PJP, whereas an inverse association was observed for increasing lymphocyte cell count (OR 0.64; 95% CI 0.42-1.00, p = 0.049). For the diagnosis of PJP, higher positive predictive value (PPV) was observed when both respiratory Pneumocystis PCR and serum BDG were positive compared to individual assay positivity (72% for the combination vs. 63% for PCR and 39% for BDG). Cumulative 30-day mortality and 90-day mortality in patients with presumptive/proven PJP were 52% and 67%, respectively. CONCLUSION: PJP in critically ill patients admitted to ICU is nowadays most encountered in non-HIV patients. Serum BDG when used in combination with respiratory Pneumocystis PCR could help improve the certainty of PJP diagnosis.

Search for Screened Interactions Associated with Dark Energy below the 100 µm Length Scale.

We present the results of a search for unknown interactions that couple to mass between an optically levitated microsphere and a gold-coated silicon cantilever. The scale and geometry of the apparatus enable a search for new forces that appear at distances below 100 µm and which would have evaded previous searches due to screening mechanisms. The data are consistent with electrostatic backgrounds and place upper limits on the strength of new interactions at <0.1 fN in the geometry tested. For the specific example of a chameleon interaction with an inverse power law potential, these results exclude matter couplings ß>5.6×10^{4} in the region of parameter space where the self-coupling Λ≳5 meV and the microspheres are not fully screened.

End-to-end offline reinforcement learning for glycemia control.

The development of closed-loop systems for glycemia control in type I diabetes relies heavily on simulated patients. Improving the performances and adaptability of these close-loops raises the risk of over-fitting the simulator. This may have dire consequences, especially in unusual cases which were not faithfully - if at all - captured by the simulator. To address this, we propose to use model-free offline RL agents, trained on real patient data, to perform the glycemia control. To further improve the performances, we propose an end-to-end personalization pipeline, which leverages offline-policy evaluation methods to remove altogether the need of a simulator, while still enabling an estimation of clinically relevant metrics for diabetes.

AD Course Map charts Alzheimer's disease progression.

Alzheimer's disease (AD) is characterized by the progressive alterations seen in brain images which give rise to the onset of various sets of symptoms. The variability in the dynamics of changes in both brain images and cognitive impairments remains poorly understood. This paper introduces AD Course Map a spatiotemporal atlas of Alzheimer's disease progression. It summarizes the variability in the progression of a series of neuropsychological assessments, the propagation of hypometabolism and cortical thinning across brain regions and the deformation of the shape of the hippocampus. The analysis of these variations highlights strong genetic determinants for the progression, like possible compensatory mechanisms at play during disease progression. AD Course Map also predicts the patient's cognitive decline with a better accuracy than the 56 methods benchmarked in the open challenge TADPOLE. Finally, AD Course Map is used to simulate cohorts of virtual patients developing Alzheimer's disease. AD Course Map offers therefore new tools for exploring the progression of AD and personalizing patients care.

Predicting the progression of mild cognitive impairment using machine learning: A systematic, quantitative and critical review.

We performed a systematic review of studies focusing on the automatic prediction of the progression of mild cognitive impairment to Alzheimer's disease (AD) dementia, and a quantitative analysis of the methodological choices impacting performance. This review included 172 articles, from which 234 experiments were extracted. For each of them, we reported the used data set, the feature types, the algorithm type, performance and potential methodological issues. The impact of these characteristics on the performance was evaluated using a multivariate mixed effect linear regressions. We found that using cognitive, fluorodeoxyglucose-positron emission tomography or potentially electroencephalography and magnetoencephalography variables significantly improved predictive performance compared to not including them, whereas including other modalities, in particular T1 magnetic resonance imaging, did not show a significant effect. The good performance of cognitive assessments questions the wide use of imaging for predicting the progression to AD and advocates for exploring further fine domain-specific cognitive assessments. We also identified several methodological issues, including the absence of a test set, or its use for feature selection or parameter tuning in nearly a fourth of the papers. Other issues, found in 15% of the studies, cast doubts on the relevance of the method to clinical practice. We also highlight that short-term predictions are likely not to be better than predicting that subjects stay stable over time. These issues highlight the importance of adhering to good practices for the use of machine learning as a decision support system for the clinical practice.