Expert System for Diagnosing Early Symptoms of Stroke Using the Fuzzy Mamdani Method

One of the dangerous diseases is stroke because it can disrupt the nervous system system in humans so that sufferers of this disease often experience paralysis in their body parts. Therefore, an application is needed to assist medical personnel when doctors are not available or are not on duty. Expert system applications are needed in early diagnosing the characteristics of the disease suffered by a patient. Expert systems are computer-based systems that use knowledge, facts and reasoning techniques to solve problems. The purpose of this study is to make it easier for researchers to identify problems with stroke based on the symptoms experienced by the patient or a person. The research method used is the fuzzy mamdani method. Data collection techniques are quantitative data techniques. The results that have been achieved from this study are that it can prevent and reduce the risk of stroke that can occur as early as possible in sufferers or the community and reduce the death rate in stroke patients.

Artificial Intelligence-Based Recognition of Different Types of Shoulder Implants in X-ray Scans Based on Dense Residual Ensemble-Network for Personalized Medicine

Re-operations and revisions are often performed in patients who have undergone total shoulder arthroplasty (TSA) and reverse total shoulder arthroplasty (RTSA). This necessitates an accurate recognition of the implant model and manufacturer to set the correct apparatus and procedure according to the patient’s anatomy as personalized medicine. Owing to unavailability and ambiguity in the medical data of a patient, expert surgeons identify the implants through a visual comparison of X-ray images. False steps cause heedlessness, morbidity, extra monetary weight, and a waste of time. Despite significant advancements in pattern recognition and deep learning in the medical field, extremely limited research has been conducted on classifying shoulder implants. To overcome these problems, we propose a robust deep learning-based framework comprised of an ensemble of convolutional neural networks (CNNs) to classify shoulder implants in X-ray images of different patients. Through our rotational invariant augmentation, the size of the training dataset is increased 36-fold. The modified ResNet and DenseNet are then combined deeply to form a dense residual ensemble-network (DRE-Net). To evaluate DRE-Net, experiments were executed on a 10-fold cross-validation on the openly available shoulder implant X-ray dataset. The experimental results showed that DRE-Net achieved an accuracy, F1-score, precision, and recall of 85.92%, 84.69%, 85.33%, and 84.11%, respectively, which were higher than those of the state-of-the-art methods. Moreover, we confirmed the generalization capability of our network by testing it in an open-world configuration, and the effectiveness of rotational invariant augmentation.

Do you hear us? Elevating the voice of patients from Asia Pacific (AP) and Middle East (ME) in pharmaceutical research.

e18519 Background: Incorporating patient (pt) perspectives in the development of new therapies (from trial design to regulatory & reimbursement decisions) and providing pts with plain language summaries (PLS) of clinical trial results is increasingly important to minimise knowledge and experience disparities. One model to facilitate this in pharmaceutical research is via Patient Expert Panels (PEPs). Aim: To assess the feasibility & impact of PEPs consisting of members from AP&ME on the development of 1. PLS of data presented at ESMO and ASH 2020 for selected Novartis-sponsored clinical trials 2. Disease education material for sickle cell disease (SCD). Methods: Thematic analysis of meeting minutes from PEPs conducted between Sep – Dec 2020 was performed. Data relating to meeting duration were extracted. The responses from an 8-item survey of PEP members were analysed descriptively for 6 items, thematically for 2. Results: Five virtual PEPs were conducted, with a median duration of 60 mins [range 60-120]. In total, 9 PLS were reviewed (8 breast cancer, 1 CML) & 1 SCD education booklet. Five common themes emerged regarding the input & impact of the PEP [Table]. 88% panelists responded they “Definitely will” participate in future PEPs, thereby confirming their feasibility, with the following quote being representative of the panelists’ experience & impact “I appreciated how our input as patients was valued and highly taken into consideration. It felt like our time and feedback was important to everyone.” Conclusions: PEP constituted of pts from countries in AP&ME are feasible and lead to impactful improvements in the development of PLS and disease education information. Given pt advocates in these countries are volunteers from organisations with limited resources, have diverse backgrounds in terms of culture, language & disease awareness, their input is more representative of a broader pt population. As a result, the final versions of the reviewed documents were more inclusive & accessible. [Table: see text]