Convolutional Neural Network to Classify Infrared Thermal Images of Fractured Wrists in Pediatrics

Healthcare, Год журнала: 2024, Номер 12(10), С. 994 - 994

Опубликована: Май 11, 2024

Convolutional neural network (CNN) models were devised and evaluated to classify infrared thermal (IRT) images of pediatric wrist fractures. The recorded from 19 participants with a fracture 21 without (sprain). injury diagnosis was by X-ray radiography. For each participant, 299 IRT their wrists recorded. These generated 11,960 (40 × images). image, the region interest (ROI) selected fast Fourier transformed (FFT) obtain magnitude frequency spectrum. spectrum resized 100 pixels its center as this represented main components. Image augmentations rotation, translation shearing applied spectra assist CNN generalization during training. had 34 layers associated convolution, batch normalization, rectified linear unit, maximum pooling SoftMax classification. ratio for training test 70:30, respectively. effects augmentation dropout on performance explored. Wrist identification sensitivity accuracy 88% 76%, respectively, achieved. model able identify fractures; however, larger sample size would improve accuracy.

Язык: Английский

---

The Use of COVID-19 Mobile Apps in Connecting Patients with Primary Healthcare in 30 Countries: Eurodata Study

Healthcare, Год журнала: 2024, Номер 12(14), С. 1420 - 1420

Опубликована: Июль 16, 2024

The COVID-19 pandemic has necessitated changes in European healthcare systems, with a significant proportion of cases being managed on an outpatient basis primary (PHC). To alleviate the burden facilities, many countries developed contact-tracing apps and symptom checkers to identify potential cases. As evolved, Union introduced Digital Certificate for travel, which relies vaccination, recent recovery, or negative test results. However, integration between these PHC not been thoroughly explored Europe.

Язык: Английский

---

The impact of artificial intelligence in the diagnosis and management of acoustic neuroma: A systematic review

Technology and Health Care, Год журнала: 2024, Номер 32(6), С. 3801 - 3813

Опубликована: Авг. 2, 2024

Schwann cell sheaths are the source of benign, slowly expanding tumours known as acoustic neuromas (AN). The diagnostic and treatment approaches for AN must be patient-centered, taking into account unique factors preferences.

Язык: Английский

---

SMOTE-Based Automated PCOS Prediction Using Lightweight Deep Learning Models

Diagnostics, Год журнала: 2024, Номер 14(19), С. 2225 - 2225

Опубликована: Окт. 5, 2024

The reproductive age of women is particularly vulnerable to the effects polycystic ovarian syndrome (PCOS). High levels testosterone and other male hormones are frequent contributors PCOS. It believed that miscarriages ovulation problems majorly caused by A recent study found 31.3% Asian have been afflicted with Healing life-threatening disorders associated PCOS requires more research. In prior research, methods involved autonomously classified using a number different machine learning techniques. ML-based approaches involve hand-crafted feature extraction suffer from low performance issues, which cannot be ignored for accurate prediction identification

Язык: Английский

---

Role of mobile health applications in prevention and detection of pandemic disease: A population perspective

Digital Health, Год журнала: 2024, Номер 10

Опубликована: Янв. 1, 2024

Background The Saudi government and the MOH launched six mobile application help in tracking positive cases, get medical consultation from home, vaccination for coronavirus disease 2019 (COVID-19). Our study was conducted to evaluate role of health applications prevention detection pandemic population perspectives. Methods A cross-sectional descriptive exploratory research design utilized this study. Based on sample size calculation (described below), we recruited a convenience 462 participants Northern Border Region according set inclusion exclusion criteria: Anyone over 12 years age, including both genders citizens non-Saudi citizens, were eligible participate during period March 2022 end July. Results In total participated, 79.2% them females. There statistically significant difference between educational level overall score public satisfaction with ease use as well services provided by apps COVID-19 pandemic. Additionally, there gender ( p = 0.028). Conclusion found that most agree Ministry Health have been successful aiding anticipation early facilitating access healthcare services. Over half strongly these very effective beneficial their helped save time.

Язык: Английский

---

Implementing Explainable Machine Learning Models for Practical Prediction of Early Neonatal Hypoglycemia

Diagnostics, Год журнала: 2024, Номер 14(14), С. 1571 - 1571

Опубликована: Июль 19, 2024

Hypoglycemia is a common metabolic disorder that occurs in the neonatal period. Early identification of neonates at risk developing hypoglycemia can optimize therapeutic strategies care. This study aims to develop machine learning model and implement predictive application assist clinicians accurately predicting within four hours after birth. Our retrospective analyzed data from born ≥35 weeks gestational age admitted well-baby nursery between 1 January 2011 31 August 2021. We collected electronic medical records 2687 tertiary center Southern Taiwan. Using 12 clinically relevant features, we evaluated nine approaches build models. selected models with highest area under receiver operating characteristic curve (AUC) for integration into our hospital information system (HIS). The top three AUC values early prediction were 0.739 Stacking, 0.732 Random Forest Voting. considered best because it has relatively high shows no significant overfitting (accuracy 0.658, sensitivity 0.682, specificity 0.649, F1 score 0.517 precision 0.417). was incorporated web-based integrated system. Shapley Additive Explanation (SHAP) indicated mode delivery, age, multiparity, respiratory distress, birth weight < 2500 gm as five predictors hypoglycemia. implementation provides an effective tool assists identifying at-risk hypoglycemia, thereby allowing timely interventions treatments.

Язык: Английский

---

Enhancing Diagnostic Accuracy for Skin Cancer and COVID-19 Detection: A Comparative Study Using a Stacked Ensemble Method

Technologies, Год журнала: 2024, Номер 12(9), С. 142 - 142

Опубликована: Авг. 27, 2024

In recent years, COVID-19 and skin cancer have become two prevalent illnesses with severe consequences if untreated. This research represents a significant step toward leveraging machine learning (ML) ensemble techniques to improve the accuracy efficiency of medical image diagnosis for critical diseases such as (grayscale images) (RGB images). this paper, stacked approach is proposed enhance precision effectiveness both cancer. The method combines pretrained models convolutional neural networks (CNNs) including ResNet101, DenseNet121, VGG16 feature extraction grayscale (COVID-19) RGB (skin cancer) images. performance model evaluated using individual CNNs combination vectors generated from architectures. obtained through transfer are then fed into base-learner consisting five different ML algorithms. final step, predictions models, validation dataset, extracted assembled applied input meta-learner obtain predictions. metrics show high intermediate

Язык: Английский

---

TRENDS IN THE ADVANCEMENT OF MOBILE APPLICATIONS FOR THE DIAGNOSIS AND TREATMENT OF TINNITUS: A COMPREHENSIVE REVIEW OF SCIENTIFIC LITERATURE

Journal of Hearing Science, Год журнала: 2024, Номер 14(2), С. 9 - 21

Опубликована: Авг. 1, 2024

Introduction Tinnitus is a condition that requires multidisciplinary care and monitoring. Widespread use of mobile devices ready access to the internet offers possible solution since smartphones can run apps programmed for particular health problem. The aim article assess scale direction how are being created used diagnose treat tinnitus. Material methods Publications in Google Scholar, PubMed, ResearchGate were searched years 2010–2023. results review organized by themes. Results Hits into following themes: (1) existing tinnitus, (2) supporting diagnosis (3) tinnitus therapy, (4) look future – sensors built-in or connected devices, wearables, artificial intelligence (AI), big data systems. Conclusions Smartphone-based with ecological momentary assessment possibilities using wearable diagnostic might be useful better understanding variability perhaps its causes. Mobile crowdsensing central databases support appear valuable resource new scientific research. There now providing variety therapies sound self-help psychology, educational training. Equally important therapy smart managed hearing aids, cochlear implants, other hearables. In future, development technologies will help create platforms

Язык: Английский

---

AI-based Medical Imagery Diagnosis for COVID-19 Disease Examination and Remedy

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Ноя. 21, 2024

COVID-19, caused by the SARS-CoV-2 coronavirus, has spread to more than 200 countries, affecting millions, costing billions, and claiming nearly 2 million lives since late 2019. This highly contagious disease can easily overwhelm healthcare systems if not managed promptly. The current diagnostic method, Molecular diagnosis, is slow low sensitivity. CXR, an initial imaging tool, provides rapid results, but less sensitive compared CT scans. article focuses on using AI for two main objectives: classifying severity of COVID-19 determining appropriate treatment. Highlights key factors in diagnosis treatment addressing questions such as: 1. For innate immunity important or acquired immunity? 2. Is disorder Acute Respiratory Distress Syndrome(ARDS)? 3. cross mortality due aging dangerous COVID-19? 4. a seasonal deficiency vitamin D winter? 5. it better treat as epidemic pandemic?

Язык: Английский

---

Deep-Learning Model for Mortality Prediction of ICU Patients with Paralytic Ileus

Bioengineering, Год журнала: 2024, Номер 11(12), С. 1214 - 1214

Опубликована: Ноя. 30, 2024

Paralytic Ileus (PI) patients in the Intensive Care Unit (ICU) face a significant risk of death. Current predictive models for PI are often complex and rely on many variables, resulting unreliable outcomes such serious health condition. Predicting mortality ICU with is particularly challenging due to vast amount data numerous features involved. To address this issue, deep-learning framework was developed using Medical Information Mart IV (MIMIC-IV) dataset, which includes from 1017 PI. By employing SHAP (SHapley Additive exPlanations) analysis, we were able narrow down six distinct clinical lab items. The proposed framework, called DLMP (Deep Learning Model Mortality Prediction Patients PI), utilizes these unique items: Anion gap, Platelet, PTT, BUN, Total Bilirubin, Bicarbonate, along one demographic variable as inputs neural network consisting only two neuron layers. achieved an outstanding prediction performance AUC score 0.887, outperforming existing significantly enhances compared traditional process mining machine learning models. This model holds considerable potential prognosis, enabling families be better informed about severity patient’s condition prepare accordingly. Furthermore, valuable research purposes trials.

Язык: Английский

---