A5037129424- Antibiotic Use and Resistance
- Bacterial Identification and Susceptibility Testing
- Sepsis Diagnosis and Treatment
- Mosquito-borne diseases and control
- Patient Satisfaction in Healthcare
- Streptococcal Infections and Treatments
- Patient-Provider Communication in Healthcare
- Heart Rate Variability and Autonomic Control
- Viral Infections and Vectors
- Diabetes Management and Research
- Electronic Health Records Systems
- Diabetes and associated disorders
- Clinical Laboratory Practices and Quality Control
- Viral Infections and Outbreaks Research
- Non-Invasive Vital Sign Monitoring
- Pancreatic function and diabetes
- Machine Learning in Healthcare
- Hemodynamic Monitoring and Therapy
- Artificial Intelligence in Healthcare
- COVID-19 Clinical Research Studies
- COVID-19 and healthcare impacts
- Cell Image Analysis Techniques
- Telemedicine and Telehealth Implementation
- SARS-CoV-2 and COVID-19 Research
- Cardiac, Anesthesia and Surgical Outcomes
Imperial College London
2016-2025
Madigan Army Medical Center
2023
International Centre for Diarrhoeal Disease Research
2023
National Institute for Health Research
2021
The inappropriate use of antimicrobials drives antimicrobial resistance. We conducted a study to map physician decision-making processes for acute infection management in secondary care identify potential targets quality improvement interventions. Physicians newly qualified consultant level participated semi-structured interviews. Interviews were audio recorded and transcribed verbatim analysis using NVIVO11.0 software. Grounded theory methodology was applied. Analytical categories created...
A locally developed case-based reasoning (CBR) algorithm, designed to augment antimicrobial prescribing in secondary care was evaluated.Prescribing recommendations made by a CBR algorithm were compared decisions physicians clinical practice. Comparisons examined 2 patient populations: first, patients with confirmed Escherichia coli blood stream infections ("E. patients"), and second ward-based presenting range of potential ("ward patients"). Prescribing against the Antimicrobial Spectrum...
Infection diagnosis can be challenging, relying on clinical judgement and non-specific markers of infection. We evaluated a supervised machine learning (SML) algorithm for diagnosing bacterial infection using routinely available blood parameters presentation to hospital.An SML was developed classify cases into versus no microbiology records six (C-reactive protein, white cell count, bilirubin, creatinine, ALT alkaline phosphatase) from 160203 individuals. A cohort patients admitted hospital...
In type 1 diabetes management, maintaining nocturnal blood glucose within target range can be challenging. Although semi-automatic systems to modulate insulin pump delivery, such as low-glucose suspension and the artificial pancreas, are starting become a reality, their elevated cost performance below user expectations is hindering adoption. Hence, decision support system that helps people with diabetes, on multiple daily injections or therapy, avoid undesirable overnight fluctuations...
Antimicrobial Resistance is threatening our ability to treat common infectious diseases and overuse of antimicrobials human infections in hospitals accelerating this process. Clinical Decision Support Systems (CDSSs) have been proven enhance quality care by promoting change prescription practices through antimicrobial selection advice. However, bypassing an initial assessment determine the existence underlying disease that justifies need therapy might lead indiscriminate often unnecessary...
Abstract Background To characterise the longitudinal dynamics of C-reactive protein (CRP) and Procalcitonin (PCT) in a cohort hospitalised patients with COVID-19 support antimicrobial decision-making. Methods Longitudinal CRP PCT concentrations trajectories 237 were modelled. The dataset comprised 2,021 data points for 284 PCT. Pairwise comparisons performed between: (i) those or without significant bacterial growth from cultures, (ii) who survived died hospital. Results higher over time...
Identifying patients at risk of dengue shock syndrome (DSS) is vital for effective healthcare delivery. This can be challenging in endemic settings because high caseloads and limited resources. Machine learning models trained using clinical data could support decision-making this context.
Abstract Background Bacterial infection has been challenging to diagnose in patients with COVID-19. We developed and evaluated supervised machine learning algorithms support the diagnosis of secondary bacterial hospitalized during COVID-19 pandemic. Methods Inpatient data at three London hospitals for first COVD-19 wave March April 2020 were extracted. Demographic, blood test microbiology individuals without SARS-CoV-2-positive PCR obtained. A Gaussian Naive Bayes, Support Vector Machine...
Symptomatic dengue infection can result in a life-threatening shock syndrome and timely diagnosis is essential. Point-of-care tests for non-structural protein 1 IgM are used widely but performance be limited. We developed supervised machine learning model to predict whether patients with acute febrile illnesses had of or other (OFI). The impact seasonality on over time was examined.We analysed data from prospective observational clinical study Vietnam. Enrolled presented an illness <72 h...
Abstract Background We developed a personalised antimicrobial information module co-designed with patients. This study aimed to evaluate the potential impact of this patient-centred intervention on short-term knowledge and understanding therapy in secondary care. Methods Thirty previous patients who had received antibiotics hospital within 12 months were recruited co-design an promote patient engagement infection management. Two workshops, containing five focus-groups held. These...
Objective To understand patient engagement with decision-making for infection management in secondary care and the consequences associated current practices. Design A qualitative investigation using in-depth focus groups. Participants Fourteen members of public who had received antimicrobials from preceding 12 months UK were identified recruitment. Ten agreed to participate. All participants experience pathways across a variety South-East England healthcare institutes. Study findings...
The decision on when it is appropriate to stop antimicrobial treatment in an individual patient complex and under-researched. Ceasing too early can drive failure, while excessive risks adverse events. Under- over-treatment promote the development of resistance (AMR). We extracted routinely collected electronic health record data from MIMIC-IV database for 18,988 patients (22,845 unique stays) who received intravenous antibiotic during intensive care unit (ICU) admission. A model was...
Close vital signs monitoring is crucial for the clinical management of patients with dengue. We investigated performance a non-invasive wearable utilising photoplethysmography (PPG), to provide real-time risk prediction in hospitalised individuals. performed prospective observational study Vietnam between January 2020 and October 2022: 153 were included analyses, providing 1353 h PPG data. Using multi-modal transformer approach, 10-min waveform segments basic data (age, sex, features on...
Electrocardiogram (ECG) and photoplethysmogram (PPG) are commonly used to determine the vital signs of heart rate, respiratory oxygen saturation in patient monitoring. In addition simple observation those summarized indexes, waveform signals can be analyzed provide deeper insights into disease pathophysiology support clinical decisions. Such data, generated from continuous monitoring both conventional bedside low-cost wearable monitors, increasingly accessible. However, recorded waveforms...
In the last years, there has been an increase of antimicrobial resistance rates around world with misuse and overuse antimicrobials as one main leading drivers. response to this threat, a variety initiatives have arisen promote efficient use antimicrobials. These rely on surveillance systems appropriate prescription practices are provided by national or global health care institutions limited consideration variations within hospitals. As consequence, physicians' adherence these generic...
Abstract Background Dengue is a common viral illness and severe disease results in life-threatening complications. Healthcare services low- middle-income countries treat the majority of dengue cases worldwide. However, clinical decision-making processes which result effective treatment are poorly characterised within this setting. In order to improve care through interventions relating digital decision-support systems (CDSS), we set out establish framework for management inform...
Background Increased data availability has prompted the creation of clinical decision support systems. These systems utilise information to enhance health care provision, both predict likelihood specific outcomes or evaluate risk further complications. However, their adoption remains low due concerns regarding quality recommendations, and a lack clarity on how results are best obtained presented. Methods We used autoencoders capable reducing dimensionality complex datasets in order produce...