Split-Dose Cisplatin in Patients With Locally Advanced or Metastatic Urothelial Carcinoma: A Systematic Literature Review and Network Meta-Analysis.

BACKGROUND: Gemcitabine plus cisplatin (GC) is a highly active and commonly used regimen in locally advanced/metastatic urothelial carcinoma (la/mUC). With GC, cisplatin is dosed at 70 mg/m2 on day 1 of a 3-week cycle; however, for many patients, impaired renal or cardiac function, neuropathy, or poor performance status (PS) can preclude the use of cisplatin. A promising alternative is split-dose GC, in which the cisplatin dose is divided over 2 days. METHODS: We conducted a systematic literature review (SLR) and network meta-analysis (NMA) to better understand treatment patterns and comparative effectiveness and safety of split-dose GC vs gemcitabine plus carboplatin (GCa), GC, and methotrexate, vinblastine, doxorubicin, and cisplatin (MVAC). RESULTS: Among 120 identified studies, 16 studies representing 1,767 patients included split-dose GC. Common reasons for choosing split-dose GC were impaired renal function, age > 70 years, comorbidities, and physician preference. Split-dose GC had objective response rates (ORRs) of 39%-80%, median progression-free survival (PFS) of 3.5-9.9 months, and median overall survival (OS) of 8.5-18.1 months. Discontinuation rates due to adverse events were 5%-38%. In the NMA, ORR with split-dose GC was significantly higher than with GCa. PFS and OS for split-dose GC were similar to that observed with the other regimens (GCa, GC, and MVAC). CONCLUSIONS: This is the first SLR and NMA of split-dose GC in la/mUC. Despite heterogeneity in the limited studies included, split-dose GC demonstrated comparable effectiveness and safety profile to those seen with other regimens. Split-dose GC thus has the potential to extend the la/mUC population eligible to receive cisplatin-based regimens and warrants further prospective study.

Identifying suicide ideation in mental health application posts: A random forest algorithm.

The growing use of digitized mental health applications requires new reliable early screening tools to identify user suicide risk. We used a lexicon-based random forest machine learning algorithm to predict suicide ideation scores from 714 online community text posts from December 2019 to April 2020. We validated predicted scores against expert-rated suicide ideation scores. The algorithm-predicted scores offered high validity and a low error rate and correctly identified 95% of expert-rated high-risk suicide ideation posts. Our findings highlight a potential new method to detect suicidal ideation of digital mental health application users.

An Open Trial of the Effectiveness, Program Usage, and User Experience of Internet-based Cognitive Behavioural Therapy for Mixed Anxiety and Depression for Healthcare Workers on Disability Leave.

OBJECTIVE: An open trial of an internet-based Cognitive Behavioural Therapy (iCBT) program for healthcare workers was conducted. METHODS: Healthcare workers on disability leave who used the iCBT program were assessed on: self-reported depression and anxiety symptoms using the Depression Anxiety Stress Scales-21; and, program usage. Healthcare workers' experience of using iCBT was evaluated in a separate survey. RESULTS: Of the 497 healthcare workers referred to the iCBT program, 51% logged in, 25% logged in more than once, and 12% logged in more than once and completed at least two assessments. For the latter group, self-reported depression and anxiety symptoms significantly decreased from the first assessment. CONCLUSIONS: This iCBT program was perceived to be of benefit to healthcare workers, with program usage and effectiveness that was similar to what has been previously reported for unguided iCBT.

Survival forests for data with dependent censoring.

Tree-based methods are very powerful and popular tools for analysing survival data with right-censoring. The existing methods assume that the true time-to-event and the censoring times are independent given the covariates. We propose different ways to build survival forests when dependent censoring is suspected, by using an appropriate estimator of the survival function when aggregating the individual trees and/or by modifying the splitting rule. The appropriate estimator used in this paper is the copula-graphic estimator. We also propose a new method for building survival forests, called p-forest, that may be used not only when dependent censoring is suspected, but also as a new survival forest method in general. The results from a simulation study indicate that these modifications improve greatly the estimation of the survival function in situations of dependent censoring. A real data example illustrates how the proposed methods can be used to perform a sensitivity analysis.

L1 splitting rules in survival forests.

The log-rank test is used as the split function in many commonly used survival trees and forests algorithms. However, the log-rank test may have a significant loss of power in some circumstances, especially when the hazard functions or when the survival functions cross each other in the two compared groups. We investigate the use of the integrated absolute difference between the two children nodes survival functions as the splitting rule. Simulations studies and applications to real data sets show that forests built with this rule produce very good results in general, and that they are often better compared to forests built with the log-rank splitting rule.