To develop an interpretable deep learning model of lupus nephritis (LN) relapse prediction based on dynamic multivariable time-series data.

A single-centre, retrospective cohort study in China.

A Chinese central tertiary hospital.

The cohort study consisted of 1694 LN patients who had been registered in the Nanjing Glomerulonephritis Registry at the National Clinical Research Center of Kidney Diseases, Jinling Hospital from January 1985 to December 2010.

We developed a deep learning algorithm to predict LN relapse that consists of 59 features, including demographic, clinical, immunological, pathological and therapeutic characteristics that were collected for baseline analysis. A total of 32 227 data points were collected by the sliding window method and randomly divided into training (80%), validation (10%) and testing sets (10%). We developed a deep learning algorithm-based interpretable multivariable long short-term memory model for LN relapse risk prediction considering censored time-series data based on a cohort of 1694 LN patients. A mixture attention mechanism was deployed to capture variable interactions at different time points for estimating the temporal importance of the variables. Model performance was assessed according to C-index (concordance index).

The median follow-up time since remission was 4.1 (IQR, 1.7–6.7) years. The interpretable deep learning model based on dynamic multivariable time-series data achieved the best performance, with a C-index of 0.897, among models using only variables at the point of remission or time-variant variables. The importance of urinary protein, serum albumin and serum C3 showed time dependency in the model, that is, their contributions to the risk prediction increased over time.

Deep learning algorithms can effectively learn through time-series data to develop a predictive model for LN relapse. The model provides accurate predictions of LN relapse for different renal disease stages, which could be used in clinical practice to guide physicians on the management of LN patients.

Four years after the devastating Ebola outbreak, governments in West Africa were quick to implement non-pharmaceutical interventions (NPIs) in response to the rapid spread of SARS-CoV-2. The NPIs implemented included physical distancing, closure of schools and businesses, restrictions on public gatherings and mandating the use of face masks among others. In the absence of widely available vaccinations, NPIs were the only known means to try to slow the spread of COVID-19. While numerous studies have assessed the effectiveness of these NPIs in high-income countries, less is known about the processes that lead to the adoption of policies and the factors that influence their implementation and adherence in low-income and middle-income countries. The objective of this scoping review is to understand the extent and type of evidence in relation to the policy formulation, decision-making and implementation stages of NPIs in West Africa.

A scoping review will be undertaken following the guidance developed by Arskey and O’Malley, the Joanna Briggs Institute (JBI) methodology for scoping reviews and the PRISMA guidelines for Scoping Reviews. Both peer-reviewed and grey literature will be searched using Web of Science, Embase, Scopus, APA PsycInfo, WHO Institutional Repository for Information Sharing, JSTOR and Google Advanced Search, and by searching the websites of the WHO, and the West African Health Organisation. Screening will be conducted by two reviewers based on inclusion and exclusion criteria, and data will be extracted, coded and narratively synthesised.

We started this scoping review in May 2023, and anticipate finishing by April 2024. Ethics approval is not required since we are not collecting primary data. This protocol was registered at Open Science Framework (https://osf.io/gvek2/). We plan to disseminate this research through publications, conference presentations and upcoming West African policy dialogues on pandemic preparedness and response.