A5071835845- Ovarian cancer diagnosis and treatment
- Spectroscopy Techniques in Biomedical and Chemical Research
- Radiomics and Machine Learning in Medical Imaging
- Endometrial and Cervical Cancer Treatments
- COVID-19 and healthcare impacts
- Spectroscopy and Chemometric Analyses
- Cardiac, Anesthesia and Surgical Outcomes
- Trauma and Emergency Care Studies
- Meta-analysis and systematic reviews
- Machine Learning in Healthcare
- Artificial Intelligence in Healthcare and Education
- Uterine Myomas and Treatments
- Intraperitoneal and Appendiceal Malignancies
- Endometriosis Research and Treatment
- Bee Products Chemical Analysis
- Topic Modeling
- Cervical Cancer and HPV Research
- Advances in Oncology and Radiotherapy
- Near-Field Optical Microscopy
- Pregnancy and preeclampsia studies
- Ovarian function and disorders
- BRCA gene mutations in cancer
- Cancer Immunotherapy and Biomarkers
- Appendicitis Diagnosis and Management
- Radiation Dose and Imaging
St James's University Hospital
2016-2025
Laboratoire des Sciences de l'Ingénieur, de l'Informatique et de l'Imagerie
2020-2022
Leeds Teaching Hospitals NHS Trust
2018-2022
NIHR Birmingham Biomedical Research Centre
2021
University of Birmingham
2020-2021
Yorkshire Cancer Research
2021
Urology Foundation
2021
Association for Cancer Surgery
2021
AstraZeneca (Brazil)
2020
Stryker (United Kingdom)
2020
Surgical management of ovarian tumours largely depends on their histo-pathological diagnosis. Currently, screening for malignancy with tumour markers in conjunction radiological investigations has a low specificity discriminating benign from malignant tumours. Also, pre-operative biopsy masses increases the risk intra-peritoneal dissemination malignancy. Intra-operative frozen section, although sufficiently accurate differentiating according to histological type, operation times. This...
Abstract Background The foundation of modern ovarian cancer care is cytoreductive surgery to remove all macroscopic disease (R0). Identification R0 resection patients may help individualise treatment. Machine learning and AI have been shown be effective systems for classification prediction. For a as heterogenous cancer, they could potentially outperform conventional predictive algorithms routine clinical use. We investigated the performance an system, k -nearest neighbor ( -NN) classifier,...
(1) Background: Surgical cytoreduction for epithelial ovarian cancer (EOC) is a complex procedure. Encompassed within the performance skills to achieve surgical precision, intra-operative decision-making remains core feature. The use of eXplainable Artificial Intelligence (XAI) could potentially interpret influence human factors on effort cytoreductive outcome in question; (2) Methods: retrospective cohort study evaluated 560 consecutive EOC patients who underwent surgery between January...
The advancement of natural language processing (NLP) technologies has transformed various sectors. However, their application in the healthcare domain, particularly for analysing clinical notes, remains underdeveloped. We investigated use deep neural networks, specifically transformer-based models, to predict intraoperative and postoperative outcomes related advanced-stage epithelial ovarian cancer cytoreduction (aEOC) using unstructured surgical notes. evaluated performance RoBERTa, a...
Background/Objectives: The advancement of natural language processing (NLP) technologies has transformed various sectors. However, their application in the healthcare domain, particularly for analysing clinical notes, remains underdeveloped. We investigated use deep neural networks, specifically transformer-based models, to predict intraoperative and post-operative outcomes related advanced-stage epithelial ovarian cancer cytoreduction (aEOC) using unstructured surgical notes. Methods:...
Accurate prediction of patient prognosis can be especially useful for the selection best treatment protocols. Machine Learning serve this purpose by making predictions based upon generalizable clinical patterns embedded within learning datasets. We designed a study to support feature 2-year prognostic period and compared performance several algorithms accurate estimation in advanced-stage high grade serous ovarian cancer (HGSOC) patients.The was formulated as binary classification problem....
Background: The Peritoneal Carcinomatosis Index (PCI) and the Intra-operative Mapping for Ovarian Cancer (IMO), to a lesser extent, have been universally validated in advanced-stage epithelial ovarian cancer (EOC) describe extent of peritoneal dissemination are proven be powerful predictors surgical outcome with an added sensitivity assessment at laparotomy around 70%. This leaves room improvement because two-dimensional anatomic scoring model fails reflect patient’s real anatomy, as seen by...
The cyclical process of regeneration the endometrium suggests that it may contain a cell population can provide daughter cells with high proliferative potential. These lineages are clinically significant as they represent clonogenic also be involved in tumourigenesis well endometriotic lesion development. To determine whether putative stem location within human uterine tissue derived using vibrational spectroscopy techniques, normal endometrial was interrogated by two spectroscopic...
Abstract Prostate cancer is the most commonly-diagnosed malignancy in males worldwide; however, there marked geographic variation incidence that may be associated with a Westernised lifestyle. We set out to determine whether attenuated total reflection Fourier-transform infrared (ATR-FTIR) or Raman spectroscopy combined principal component analysis-linear discriminant analysis variable selection techniques employing genetic algorithm successive projection could utilised explore differences...
Cervical cancer remains a major cause of morbidity and mortality among women, especially in the developing world. Increased synthesis proteins, lipids nucleic acids is pre-condition for rapid proliferation cells. We show that scanning near-field optical microscopy, combination with an infrared free electron laser (SNOM-IR-FEL), able to distinguish between normal squamous low-grade high-grade dyskaryosis, mixed squamous/glandular pre-invasive adenocarcinoma cervical lesions, at designated...
Achieving complete surgical cytoreduction in advanced stage high grade serous ovarian cancer (HGSOC) patients warrants an availability of Critical Care Unit (CCU) beds. Machine Learning (ML) could be helpful monitoring CCU admissions to improve standards care. We aimed the accuracy predicting admission HGSOC by ML algorithms and developed ML-based predictive score. A cohort 291 with fully curated data was selected. Several linear non-linear distances, quadratic discriminant methods, were...
Contemporary efforts to predict surgical outcomes focus on the associations between traditional discrete risk factors. We aimed determine whether natural language processing (NLP) of unstructured operative notes improves prediction residual disease in women with advanced epithelial ovarian cancer (EOC) following cytoreductive surgery.Electronic Health Records were queried identify EOC including their notes. The Term Frequency - Inverse Document (TF-IDF) score was used quantify discrimination...
In our center, adjuvant chemotherapy is routinely offered in high-grade serous ovarian cancer (HGSOC) patients but less commonly as a standard treatment low-grade (LGSOC) patients. This study evaluates the efficacy of this paradigm by analysing survival outcomes and comparing influence different clinical surgical characteristics between women with advanced LGSOC (n = 37) HGSOC 300). Multivariate analysis was used to identify independent prognostic features for HGSOC. Adjuvant given 99.7%...
Background and Objectives: Approximately 10−15% of high-grade serous ovarian cancer (HGSOC) cases are related to BRCA germline mutations. Better survival rates increased chemosensitivity reported in patients with a 1/2 mutation. However, the FIGO stage histopathological entity may have been confounding factors. This study aimed compare chemotherapy response between without mutation advanced HGSOC receiving neoadjuvant (NACT). Materials Methods: A cohort BRCA-tested undergoing cytoreductive...
(1) Background: Length of stay (LOS) has been suggested as a marker the effectiveness short-term care. Artificial Intelligence (AI) technologies could help monitor hospital stays. We developed an AI-based novel predictive LOS score for advanced-stage high-grade serous ovarian cancer (HGSOC) patients following cytoreductive surgery and refined factors significantly affecting LOS. (2) Methods: Machine learning deep methods using artificial neural networks (ANN) were used together with...
Ultrasound imaging of the placenta and its relationship to poor perinatal outcome has been studied since 1973. Studies have predominantly focussed on placental morphology in third trimester or high-risk pregnancies. We aimed correlate abnormal appearances identified second with histological appearances. present four cases detected at 20 week routine ultrasound scan low-risk women relate them origins, which often involved areas villous infarction. Abnormal anomaly scans might identify...