MATERIALS AND METHODS: This was a retrospective study using computed tomography (CT) scans from 3 hospitals. Inclusion criteria were scans with 1-5 nodules of diameter ≥5 mm; exclusion criteria were poor-quality scans or those with nodules measuring <5mm in diameter. In the lesion detection phase, 2,147 nodules from 219 scans were used to develop and train the deep learning 3D-CNN to detect lesions. The 3D-CNN was validated with 235 scans (354 lesions) for sensitivity, specificity, and area under the receiver operating characteristic curve (AUC) analysis. In the path planning phase, Bayesian optimization was used to propose possible needle trajectories for lesion biopsy while avoiding vital structures. Software-proposed needle trajectories were compared with actual biopsy path trajectories from intraprocedural CT scans in 150 patients, with a match defined as an angular deviation of <5° between the 2 trajectories.
RESULTS: The model achieved an overall AUC of 97.4% (95% CI, 96.3%-98.2%) for lesion detection, with mean sensitivity of 93.5% and mean specificity of 93.2%. Among the software-proposed needle trajectories, 85.3% were feasible, with 82% matching actual paths and similar performance between supine and prone/oblique patient orientations (P = .311). The mean angular deviation between matching trajectories was 2.30° (SD ± 1.22); the mean path deviation was 2.94 mm (SD ± 1.60).
CONCLUSIONS: Segmentation, lesion detection, and path planning for CT-guided lung biopsy using an AI-guided software showed promising results. Future integration with automated robotic systems may pave the way toward fully automated biopsy procedures.
METHODS: A user-friendly software was developed to accurately predict the individual size-specific dose estimation of paediatric patients undergoing computed tomography (CT) scans of the head, thorax, and abdomen. The software includes a calculation equation developed based on a novel SSDE prediction equation that used a population's pre-determined percentage difference between volume-weighted computed tomography dose index (CTDIvol) and SSDE with age. American Association of Physicists in Medicine (AAPM RPT 204) method (manual) and segmentation-based SSDE calculators (indoseCT and XXautocalc) were used to assess the proposed software predictions comparatively.
RESULTS: The results of this study show that the automated equation-based calculation of SSDE and the manual and segmentation-based calculation of SSDE are in good agreement for patients. The differences between the automated equation-based calculation of SSDE and the manual and segmentation-based calculation are less than 3%.
CONCLUSION: This study validated an accurate SSDE calculator that allows users to enter key input values and calculate SSDE.
IMPLICATION FOR PRACTICE: The automated equation-based SSDE software (PESSD) seems a promising tool for estimating individualised CT doses during CT scans.
OBJECTIVE: Therefore, this research aims to create a flexible mental health care architecture that leverages data-driven methodologies and ensemble machine learning models. The objective is to proficiently structure, process, and present data for positive computing. The adaptive data-driven architecture facilitates customized interventions for diverse mental disorders, fostering positive computing. Consequently, improved mental health care outcomes and enhanced accessibility for individuals with varied mental health conditions are anticipated.
METHOD: Following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines, the researchers conducted a systematic literature review in databases indexed in Web of Science to identify the existing strengths and limitations of software architecture relevant to our adaptive design. The systematic review was registered in PROSPERO (CRD42023444661). Additionally, a mapping process was employed to derive essential paradigms serving as the foundation for the research architectural design. To validate the architecture based on its features, professional experts utilized a Likert scale.
RESULTS: Through the review, the authors identified six fundamental paradigms crucial for designing architecture. Leveraging these paradigms, the authors crafted an adaptive data-driven architecture, subsequently validated by professional experts. The validation resulted in a mean score exceeding four for each evaluated feature, confirming the architecture's effectiveness. To further assess the architecture's practical application, a prototype architecture for predicting pandemic anxiety was developed.
METHODS: ARCHERY is a non-randomised prospective study to evaluate the quality and economic impact of AI-based automated radiotherapy treatment planning for cervical, head and neck, and prostate cancers, which are endemic in LMICs, and for which radiotherapy is the primary curative treatment modality. The sample size of 990 patients (330 for each cancer type) has been calculated based on an estimated 95% treatment plan acceptability rate. Time and cost savings will be analysed as secondary outcome measures using the time-driven activity-based costing model. The 48-month study will take place in six public sector cancer hospitals in India (n=2), Jordan (n=1), Malaysia (n=1) and South Africa (n=2) to support implementation of the software in LMICs.
ETHICS AND DISSEMINATION: The study has received ethical approval from University College London (UCL) and each of the six study sites. If the study objectives are met, the AI-based software will be offered as a not-for-profit web service to public sector state hospitals in LMICs to support expansion of high quality radiotherapy capacity, improving access to and affordability of this key modality of cancer cure and control. Public and policy engagement plans will involve patients as key partners.
MATERIALS AND METHODS: This is quantitative research with a true experimental approach. Actual bleeding volume was simulated by an acrylic phantom containing Iodine contrast media (5 ml, 10 ml, 15 ml, and 20 ml). The phantom was scanned using routine CT protocol using the helical and sequence technique. Bleeding volume from each technique was measured manually using the Broderick formula and automatic software (ROI based). Accuracy was assessed by comparing the volume measurement result to the actual bleeding volume. Data was analysed using the Friedman test and by Wilcoxon.
RESULTS: The standard deviation of measured bleeding volume from the manual and automatic measurements compared to the actual bleeding volume were (0.220; 0.236; 0.351; 0.057) and (0.139; 0.270; 0.315; 0.329) in helical technique, and (0.333; 0.376; 0.447; 0.476) and (0.139; 0.242; 0.288; 0,376) in sequence technique. There are differences in the measurement results from the helical and sequence techniques (p <0.05) and using manual and automatic methods (p <0.05).
CONCLUSION: The measurement of bleeding volume that has a standard deviation value compared to the actual volume is more accurate in the helical technique using the automatic method, while the sequence technique is the manual method.
METHODS: Ten students who previously underwent the learning module were recruited through purposive sampling. The inclusion criteria were: (a) Fourth-year medical students; and (b) Completed psychiatry posting with the new module. Students who dropped out or were unable to participate in data collection were excluded. Two online focus group discussions (FGDs) with five participants each were conducted by an independent facilitator, guided by a questioning route. The data were transcribed verbatim and coded using the thematic analysis approach to identify themes.
RESULTS: Three main themes of their learning experience were identified: (1) fulfilment of the desired pedagogy (2), realism of the clinical case, and (3) ease of use related to technical settings. The pedagogy theme was further divided into the following subthemes: level of entry for students, flexibility of presentation of content, provision of learning guidance, collaboration with peers, provision of feedback, and assessment of performance. The realism theme had two subthemes: how much the virtual patient experience mimicked an actual patient and how much the case scenario reflected real conditions in the Malaysian context. The technical setting theme entailed two subthemes: access to the software and appearance of the user interface. The study findings are considered in the light of learning formats, pedagogical and learning theories, and technological frameworks.
CONCLUSIONS: The findings shed light on both positive and negative aspects of using virtual patients for medical students' psychiatry posting, which opens room for further improvement of their usage in undergraduate psychiatry education.