Research articles

Andrade, Cashman et al. evaluate varying immunization regimens of INO-4500, a DNA-based vaccine for Lassa fever, in non-human primates. INO-4500 induces humoral and cellular immune responses, conferring short- and long-term protection from lethal Lassa Virus challenge.

Su et al. dissect SARS-CoV-2 variant patterns in Cambodia. They uncover divergent evolutionary trajectories and population dynamics, along with contrasting migration patterns, between Alpha and Delta variants in 2021.

Giesa et al. train and evaluate multiple deep learning architectures on multivariable clinical time series for the prediction of postoperative delirium (POD). An adapted transformer model named as TRAPOD performs best, making use of temporal intraoperative dynamics.

Dhakal, Yin, Escarra-Senmarti et al. investigate the associations of antibody biomarkers with recovery or death from COVID-19 using machine learning algorithms. They demonstrate the serological antibody measures, among COVID-19 patients, that predict intubation or death.

Huang et al. train and optimize a machine learning model using patient characteristics and NMR biomarkers to predict Myalgic Encephalomyelitis/Chronic Fatigue Syndrome cases in the UK Biobank. This works explores the heterogenous symptoms and comorbidities of this condition.

Fazli Besheli et al. identify intraoperative high frequency oscillations (HFOs) using noise-resilient computational intelligence to effectively localize seizure-generating brain regions. Epileptogenic zones are identified from brief intraoperative neural recordings.

Jo, Inoue et al. use a machine-learning Bayesian causal forest algorithm to evaluate the effect of intensified myeloablative conditioning (MAC) on mortality following haematopoietic stem cell transplantation (HSCT). Intensified myeloablative conditioning (MAC) has heterogeneous effects on reducing mortality.

Steinberg et al. explore the associations between the nasal microbiota, respiratory tract infections (RTIs) and antibiotics in infants with cystic fibrosis (CF) and controls during the first year of life. Infants with CF have a different microbiota before their first RTI or antibiotic treatment, with lower diversity linked to higher number of RTIs.

Choi et al. develop and validate a sepsis treatment model based on deep reinforcement learning using patients’ treatment records. The model increases patients’ estimated survival rate and analysis of the treatment model’s strategies also suggests potential future sepsis research directions.

Bartha et al. investigate the evolution of SARS-CoV-2 towards an endemic state. Real world data on over 600,000 individuals and from wastewater surveillance show loss of SARS-CoV-2 virulence and patterns of morbidity similar to influenza.

Ding et al. propose a deep learning-based model for fast and accurate 3D CT reconstruction given 2D kV (X-Ray) images as the solo inputs. The experimental results and analysis indicate that the proposed framework can be used for accurate and robust patient alignment with minimum imaging dose.

Lukas et al. investigate the co-development of tinnitus-related distress and depressiveness throughout treatment. The strong bidirectional relationship indicates a combined treatment of tinnitus and depression, suggesting enhanced treatment success in tinnitus-related distress when depression is addressed and vice versa.

Schiabor Barrett et al evaluate variants in GCK, a gene associated with Monogenic Diabetes of the Young (MODY), in two population cohorts with healthcare records. They find that participants with pathogenic MODY and other glucose-elevating variants are at risk for Type 2 Diabetes (T2D) and those with T2D show secondary complications of T2D.

Nightingale et al. compare block-homogeneity and statistical disaggregation approaches to analyse visceral leishmaniasis incidence across 45,000 villages in Bihar state. Village-level incidence is not measured more accurately by the disaggregation approach and spatial auto-correlation is evident on a block-level but weak between neighbouring villages within the same block.

Starck and Sideri-Lampretsa et al. propose a pipeline for generating whole-body atlases from a heterogeneous population by dividing it into anatomically meaningful subgroups. They demonstrate the use of these atlases for studying differences between healthy individuals and those with conditions such as diabetes or cardiovascular disease.

Costello et al. assess the impact of ursodeoxycholic acid (UDCA) treatment on COVID-19-related outcomes among people with chronic primary biliary cirrhosis and primary sclerosing cholangitis. Using a population-based cohort, they show that treatment with UDCA was associated with a reduced risk of COVID-19-related hospitalisation or death.

Wei and colleagues use electronic health records to predict individual hospital discharge events and hospital-wide discharge numbers. Detailed data and an extreme gradient boosting model predict hospital discharge better than simple logistic regression models, highlighting the potential of machine learning approaches to help optimise patient flow.

Bassi et al investigate the impact of phrenic nerve stimulation on deeply sedated, mechanically ventilated patients with acute respiratory distress syndrome. Cortical activity, connectivity, and synchronization are increased when phrenic stimulation is included in addition to invasive mechanical ventilation.

Smelik et al. investigate the effectiveness of using multi-omics biomarkers in blood for cancer screening. The results indicate that while these biomarkers show promise for diagnosing individual cancers in close proximity to the blood stream, they do not surpass clinical variables for diagnosing multiple cancers.

Andelman-Gur et al. use a nasal airflow monitoring device to detect alterations of respiratory dynamics in patients with Parkinson’s Disease. They reveal longer, but less variable, inhalations and show that changes in airflow dynamics are correlated with disease severity, plus 30 min of data is adequate to discriminate patients from controls.