During prosthetic joint infection (PJI), optimal surgical management with exchange of the device is sometimes impossible, especially in the elderly population. Thus, prolonged suppressive antibiotic therapy (PSAT) is the only option to prevent acute sepsis, but little is known about this strategy. We aimed to describe the characteristics, outcome and tolerance of PSAT in elderly patients with PJI. We performed a national cross-sectional cohort study of patients >75 years old and treated with PSAT for PJI. We evaluated the occurrence of events, which were defined as: (i) local or systemic progression of the infection (failure), (ii) death and (iii) discontinuation or switch of PSAT. A total of 136 patients were included, with a median age of 83 years [interquartile range (IQR) 81-88]. The predominant pathogen involved was Staphylococcus (62.1%) (Staphylococcus aureus in 41.7%). A single antimicrobial drug was prescribed in 96 cases (70.6%). There were 46 (33.8%) patients with an event: 25 (18%) with an adverse drug reaction leading to definitive discontinuation or switch of PSAT, 8 (5.9%) with progression of sepsis and 13 died (9.6%). Among patients under follow-up, the survival rate without an event at 2 years was 61% [95% confidence interval (CI): 51;74]. In the multivariate Cox analysis, patients with higher World Health Organization (WHO) score had an increased risk of an event [hazard ratio (HR) = 1.5, p = 0.014], whereas patients treated with beta-lactams are associated with less risk of events occurring (HR = 0.5, p = 0.048). In our cohort, PSAT could be an effective and safe option for PJI in the elderly.

PURPOSE Drug development in oncology currently is facing a conjunction of an increasing number of antineoplastic agents (ANAs) candidate for phase I clinical trials (P1CTs) and an important attrition rate for final approval. We aimed to develop a machine learning algorithm (RESOLVED2) to predict drug development outcome, which could support early go/no-go decisions after P1CTs by better selection of drugs suitable for further development. METHODS PubMed abstracts of P1CTs reporting on ANAs were used together with pharmacologic data from the DrugBank5.0 database to model time to US Food and Drug Administration (FDA) approval (FDA approval-free survival) since the first P1CT publication. The RESOLVED2 model was trained with machine learning methods. Its performance was evaluated on an independent test set with weighted concordance index (IPCW). RESULTS We identified 462 ANAs from PubMed that matched with DrugBank5.0 (P1CT publication dates 1972 to 2017). Among 1,411 variables, 28 were used by RESOLVED2 to model the FDA approval-free survival, with an IPCW of 0.89 on the independent test set. RESOLVED2 outperformed a model that was based on efficacy/toxicity (IPCW, 0.69). In the test set at 6 years of follow-up, 73% (95% CI, 49% to 86%) of drugs predicted to be approved were approved, whereas 92% (95% CI, 87% to 98%) of drugs predicted to be nonapproved were still not approved (log-rank P < .001). A predicted approved drug was 16 times more likely to be approved than a predicted nonapproved drug (hazard ratio, 16.4; 95% CI, 8.40 to 32.2). CONCLUSION As soon as P1CT completion, RESOLVED2 can predict accurately the time to FDA approval. We provide the proof of concept that drug development outcome can be predicted by machine learning strategies.

PURPOSE Early discontinuation affects more than one third of patients enrolled in early-phase oncology clinical trials. Early discontinuation is deleterious both for the patient and for the study, by inflating its duration and associated costs. We aimed at predicting the successful screening and dose-limiting toxicity period completion (SSD) from automatic analysis of consultation reports. MATERIALS AND METHODS We retrieved the consultation reports of patients included in phase I and/or phase II oncology trials for any tumor type at Gustave Roussy, France. We designed a preprocessing pipeline that transformed free text into numerical vectors and gathered them into semantic clusters. These document-based semantic vectors were then fed into a machine learning model that we trained to output a binary prediction of SSD status. RESULTS Between September 2012 and July 2020, 56,924 consultation reports were used to build the dictionary and 1,858 phase I or II inclusion reports were used to train (72%), validate (14%), and test (14%) a random forest model. Preprocessing could efficiently cluster words with semantic proximity. On the unseen test cohort of 264 consultation reports, the performances of the model reached: F1 score 0.80, recall 0.81, and area under the curve 0.88. Using this model, we could have reduced the screen fail rate (including dose-limiting toxicity period) from 39.8% to 12.8% (relative risk, 0.322; 95% CI, 0.209 to 0.498; P < .0001) within the test cohort. Most important semantic clusters for predictions comprised words related to hematologic malignancies, anatomopathologic features, and laboratory and imaging interpretation. CONCLUSION Machine learning with semantic conservation is a promising tool to assist physicians in selecting patients prone to achieve SSD in early-phase oncology clinical trials.

Model-based Reinforcement Learning estimates the true environment through a world model in order to approximate the optimal policy. This family of algorithms usually benefits from better sample efficiency than their model-free counterparts. We investigate whether controllers learned in such a way are robust and able to generalize under small perturbations of the environment. Our work is inspired by the PILCO algorithm, a method for probabilistic policy search. We show that enforcing a lower bound to the likelihood noise in the Gaussian Process dynamics model regularizes the policy updates and yields more robust controllers. We demonstrate the empirical benefits of our method in a simulation benchmark.