Diabetes is a chronic disease that continues to be a significant and global concern since it affects the entire population’s health. It is a metabolic disorder that leads to high blood sugar levels and many other problems such as stroke, kidney failure, and heart and nerve problems. Several researchers have attempted to construct an accurate diabetes prediction model over the years. However, this subject still faces significant open research issues due to a lack of appropriate data sets and prediction approaches, which pushes researchers to use big data analytics and machine learning (ML)-based methods. Applying four different machine learning methods, the research tries to overcome the problems and investigate healthcare predictive analytics. The study’s primary goal was to see how big data analytics and machine learning-based techniques may be used in diabetes. The examination of the results shows that the suggested ML-based framework may achieve a score of 86. Health experts and other stakeholders are working to develop categorization models that will aid in the prediction of diabetes and the formulation of preventative initiatives. The authors perform a review of the literature on machine models and suggest an intelligent framework for diabetes prediction based on their findings. Machine learning models are critically examined, and an intelligent machine learning-based architecture for diabetes prediction is proposed and evaluated by the authors. In this study, the authors utilize our framework to develop and assess decision tree (DT)-based random forest (RF) and support vector machine (SVM) learning models for diabetes prediction, which are the most widely used techniques in the literature at the time of writing. It is proposed in this study that a unique intelligent diabetes mellitus prediction framework (IDMPF) is developed using machine learning. According to the framework, it was developed after conducting a rigorous review of existing prediction models in the literature and examining their applicability to diabetes. Using the framework, the authors describe the training procedures, model assessment strategies, and issues associated with diabetes prediction, as well as solutions they provide. The findings of this study may be utilized by health professionals, stakeholders, students, and researchers who are involved in diabetes prediction research and development. The proposed work gives 83% accuracy with the minimum error rate.
In recent years, neurological diseases have become a standout amongst all the other diseases and are the most important reasons for mortality and morbidity all over the world. The current study’s aim is to conduct a pilot study for testing the prototype of the designed glove-wearable technology that could detect and analyze the heart rate and EEG for better management and avoiding stroke consequences. The qualitative, clinical experimental method of assessment was explored by incorporating use of an IoT-based real-time assessing medical glove that was designed using heart rate-based and EEG-based sensors. We conducted structured interviews with 90 patients, and the results of the interviews were analyzed by using the Barthel index and were grouped accordingly. Overall, the proportion of patients who followed proper daily heart rate recording behavior went from 46.9% in the first month of the trial to 78.2% after 3–10 months of the interventions. Meanwhile, the percentage of individuals having an irregular heart rate fell from 19.5% in the first month of the trial to 9.1% after 3–10 months of intervention research. In T5, we found that delta relative power decreased by 12.1% and 5.8% compared with baseline at 3 and at 6 months and an average increase was 24.3 ± 0.08. Beta-1 remained relatively steady, while theta relative power grew by 7% and alpha relative power increased by 31%. The T1 hemisphere had greater mean values of delta and theta relative power than the T5 hemisphere. For alpha ( p < 0.05) and beta relative power, the opposite pattern was seen. The distinction was statistically significant for delta ( p < 0.001), alpha ( p < 0.01), and beta-1 ( p < 0.05) among T1 and T5 patient groups. In conclusion, our single center-based study found that such IoT-based real-time medical monitoring devices significantly reduce the complexity of real-time monitoring and data acquisition processes for a healthcare provider and thus provide better healthcare management. The emergence of significant risks and controlling mechanisms can be improved by boosting the awareness. Furthermore, it identifies the high-risk factors besides facilitating the prevention of strokes. The EEG-based brain-computer interface has a promising future in upcoming years to avert DALY.
The quantity of data required to give a valid analysis grows exponentially as machine learning dimensionality increases. In a single experiment, microarrays or gene expression profiling assesses and determines gene expression levels and patterns in various cell types or tissues. The advent of DNA microarray technology has enabled simultaneous intensive care of hundreds of gene expressions on a single chip, advancing cancer categorization. The most challenging aspect of categorization is working out many information points from many sources. The proposed approach uses microarray data to train deep learning algorithms on extracted features and then uses the Latent Feature Selection Technique to reduce classification time and increase accuracy. The feature-selection-based techniques will pick the important genes before classifying microarray data for cancer prediction and diagnosis. These methods improve classification accuracy by removing duplicate and superfluous information. The Artificial Bee Colony (ABC) technique of feature selection was proposed in this research using bone marrow PC gene expression data. The ABC algorithm, based on swarm intelligence, has been proposed for gene identification. The ABC has been used here for feature selection that generates a subset of features and every feature produced by the spectators, making this a wrapper-based feature selection system. This method’s main goal is to choose the fewest genes that are critical to PC performance while also increasing prediction accuracy. Convolutional Neural Networks were used to classify tumors without labelling them. Lung, kidney, and brain cancer datasets were used in the procedure’s training and testing stages. Using the cross-validation technique of k-fold methodology, the Convolutional Neural Network has an accuracy rate of 96.43%. The suggested research includes techniques for preprocessing and modifying gene expression data to enhance future cancer detection accuracy.
Purpose: Our purpose was to evaluate whether omitting high-dose clinical target volume radiation (CTV-HD) around the gross tumor volume (GTV) in patients with oropharyngeal squamous cell carcinoma (OSCC) treated with intensity-modulated radiotherapy (IMRT) was associated with increased local failure.Methods and materials: Patients diagnosed with stage I to stage IV OSCC between December 2004 and April 2017 were retrospectively reviewed. All patients were treated with radical radiotherapy using IMRT, with or without neoadjuvant or concurrent chemotherapy. In accordance with institution guidelines, CTV-HD was not used. Local failure was defined as disease persistence or reappearance at the primary tumor site. When primary failure was documented, the computed tomography/positron emission tomography (CT/PET) scan that showed primary failure was fused with the original treatment scan. Each recurrent tumor was contoured to evaluate the pattern of recurrence. Recurrences were categorized as in-field, marginal, or out-of-field if >95%, 20%-95%, or <20% of the recurrent tumor volume, respectively, was encompassed by the 95% high-dose prescription isodose line of the original treatment plan. We then determined whether omitting CTV-HD was associated with increased locoregional failure.Results: A total of 272 patients with OSCC were assessed. The median follow-up from initial treatment was 43 months (range: 3-194 months). Seven patients were lost to follow-up. The overall five-year survival rate was 87%. The three- and five-year disease-free survival rates were 86% and 83%, respectively. Forty-one patients had 53 treatment failures (16 were local, eight were regional, and 29 were distant; some patients had treatment failures in multiple locations). Fourteen (87.5%) of the local recurrences were in-field, one (6.25%) was marginal, and one (6.25%) was out-of-field.Conclusion: Our analysis of patients with oropharyngeal cancer suggests that local failure is mostly in-field and potentially due to radioresistance, rather than a marginal miss of the tumor. It suggests that omitting CTV-HD is feasible and safe.
Hypopharyngeal carcinoma is usually present at late stages, necessitating an aggressive line of management consisting of surgical procedures, chemotherapy, and radiation therapy, depending on the case. Practitioners tend to support total laryngectomies or total esophagostomies for most cases of hypopharyngeal carcinoma. The extensive procedures needed will most probably require, depending on the residual defect, a follow-up reconstructive procedure that might require utilizing flaps. Types of reconstructive methods and types of grafts or flaps used could be divided into a multitude of categories depending on the magnitude, shape, extension, and whether the underlying defect that is being reconstructed is circumferential or not. These reconstructive procedures are aimed at improving the quality of life, improving the aesthetic outcome, and restoring the functionality of the pharyngoesophageal segment. When it comes to hypopharyngeal cancer, the most common kind is squamous cell carcinoma (SCC), which has the worst prognosis of all the head and neck malignancies. Overall, the 5-year survival rate remains low, despite recent advancements in diagnostic imaging, radiation, and chemotherapy, as well as enhanced surgical methods and techniques. Hypopharyngeal malignancies are more probable than other tumors to present with advanced primary illness, with nodal metastasis a distinct possibility. The size and amount of local dissemination of the original carcinoma, as well as the extent of involvement of regional lymph nodes, are the most critical factors in predicting prognosis. Hypopharyngeal cancers are more likely than other head and neck cancers to manifest with distant metastases at the time of diagnosis. The appearance of second primary tumors, as well as the development of distant metastases, is a contributing factor to poor survival rate. Imaging techniques such as computed tomography (CT) and magnetic resonance imaging (MRI) with contrast remain the gold standard for evaluating hypopharyngeal carcinoma in the early stages. In most cases, imaging leads to an increase in the tumor stage at the time of presentation. Objectives. The main objectives are to review the research published about flaps, outline the optimum situations that will dictate the usage of a few of the most often used flaps for the rebuilding of the hypopharyngeal segment defects, and outline some of the complications associated with reconstruction. Methods. The processing was carried out with the title-specific search of the PubMed database using the query terms “hypopharyngeal carcinoma” and “reconstruction” to identify the most relevant articles without restricting publication dates. Information about the types of defects and methods of reconstruction was extracted from the reviewed articles. Two books were also reviewed, which were Regional and Free Flaps for Head and Neck Reconstruction (second edition) and Head and Neck Reconstruction: A Defect-Oriented Approach. Conclusion. Deciding the appropriate approach to a case should be individualized and should depend on the capabilities of the center, the defect’s size and status, and lastly, the surgeon’s training. The use of interpretation in the diagnosis of flaps can offer the best results in restoring functionality and vascularity and might also offer improved cosmesis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.