Search

Simple Summary: This paper presents a cervical cancer detection approach where the KNN Imputer techniques is used to fill the missing values and after that SMOTE upsampled features are utilized to train a multi-model ensemble learning approach. Results demonstrate that use of KNN Imputed SMOTE features yields better results than the original features to classify cancerous and normal patients. Objective: Cervical cancer ranks among the top causes of death among females in developing countries. The most important procedures that should be followed to guarantee the minimizing of cervical cancer's aftereffects are early identification and treatment under the finest medical guidance. One of the best methods to find this sort of malignancy is by looking at a Pap smear image. For automated detection of cervical cancer, the available datasets often have missing values, which can significantly affect the performance of machine learning models. Methods: To address these challenges, this study proposes an automated system for predicting cervical cancer that efficiently handles missing values with SMOTE features to achieve high accuracy. The proposed system employs a stacked ensemble voting classifier model that combines three machine learning models, along with KNN Imputer and SMOTE up-sampled features for handling missing values. Results: The proposed model achieves 99.99% accuracy, 99.99% precision, 99.99% recall, and 99.99% F1 score when using KNN imputed SMOTE features. The study compares the performance of the proposed model with multiple other machine learning algorithms under four scenarios: with missing values removed, with KNN imputation, with SMOTE features, and with KNN imputed SMOTE features. The study validates the efficacy of the proposed model against existing state-of-the-art approaches. Conclusions: This study investigates the issue of missing values and class imbalance in the data collected for cervical cancer detection and might aid medical practitioners in timely detection and providing cervical cancer patients with better care. [ABSTRACT FROM AUTHOR]

Glucose forecasting serves as a backbone for several healthcare applications, including real-time insulin dosing in people with diabetes and physical activity optimization. This paper presents a study on the use of machine learning (ML) and deep learning (DL) methods for predicting glucose variability (GV) in individuals with open-source automated insulin delivery systems (AID). A three-stage experimental framework is employed in this work to systematically implement and evaluate ML/DL methods on a large-scale diabetes dataset collected from individuals with open-source AID. The first stage involves data collection, the second stage involves data preparation and exploratory analysis, and the third stage involves developing, fine-tuning, and evaluating ML/DL models. The performance and resource costs of the models are evaluated alongside relative and proportional errors for 17 GV metrics. Evaluation of fine-tuned ML/DL models shows considerable accuracy in glucose forecasting and variability analysis up to 48 h in advance. The average MAE ranges from 2.50 mg/dL for long short-term memory models (LSTM) to 4.94 mg/dL for autoregressive integrated moving average (ARIMA) models, and the RMSE ranges from 3.7 mg/dL for LSTM to 7.67 mg/dL for ARIMA. Model execution time is proportional to the amount of data used for training, with long short-term memory models having the lowest execution time but the highest memory consumption compared to other models. This work successfully incorporates the use of appropriate programming frameworks, concurrency-enhancing tools, and resource and storage cost estimators to encourage the sustainable use of ML/DL in real-world AID systems. [ABSTRACT FROM AUTHOR]

Chronic wounds are associated with significant clinical, economic and quality‐of‐life burden. Despite the variety of wound imaging systems available in the market for wound assessment and surveillance, few are clinically validated among patients of Asian ethnicity. We aimed to clinically validate the accuracy of a smartphone wound application (Tissue Analytics [TA], Net Health Systems Inc, Florida, USA), versus conventional wound measurements (visual approximation and paper rulers), in patients of Asian ethnicity with venous leg ulcers (VLU). A prospective cohort study of patients presenting with VLU to a specialist wound nurse clinic over a 5‐week duration was conducted. Each patient received seven wound measurements: one by a trained wound nurse clinician, and three separate wound measurements using TA on each of the iOS and Android operating systems. Inter‐rater and intra‐rater reliability between clinical and TA‐based measurements were analysed using intra‐class correlation statistics, with values of <0.5, 0.5 to 0.75, 0.75 to 0.9, and >0.9 indicating poor, moderate, good and excellent reliability, respectively. 82 patients (51% males), with a mean age at 65.8 years, completed the 5‐week study duration. 25 (30%) had underlying diabetes mellitus. Chinese, Malay and Indian ethnicity comprised 68%, 12% and 11%, respectively. The VLU healed in 26 (32%) of patients within the study period. In total, 358 wound episodes with 2334 wound images were analysed. Inter‐rater reliability for length, width and area between wound nurse measurements and TA application measurements was good (range 0.799‐0.919, P < 0.001). Separate measurements of intra‐rater reliability for length, width and area within the iOS or Android systems were excellent (range 0.967‐0.985 and range 0.977‐0.984 respectively, P < 0.001). Inter‐rater reliability between TA used on the iOS and Android systems was also excellent (0.987‐0.989, P < 0.001). Tissue Analytics, a smartphone wound application, is a useful adjunct for wound assessment and surveillance in VLU patients of Asian ethnicity. [ABSTRACT FROM AUTHOR]

Objective. Internet of Things (IoT) integrates several technologies where devices learn from the experience of each other thereby reducing human-intervened likely errors. Modern technologies like IoT and machine learning enable the conventional to patient-specific approach transition in healthcare. In conventional approach, the biggest challenge faced by healthcare professionals is to predict a disease by observing the symptoms, monitoring the remote area patient, and also attending to the patient all the time after being hospitalised. IoT provides real-time data, makes decision-making smarter, and provides far superior analytics, and all these to help improve the quality of healthcare. The main objective of the work was to create an IoT-based automated system using machine learning models for symptom-based COVID-19 prognosis. Methods. Comparative analysis of predictive microbiology of COVID-19 from case symptoms using various machine learning classifiers like logistics regression, k-nearest neighbor, support vector machine, random forest, decision trees, Naïve Bayes, and gradient booster is reported here. For the sake of the validation and verification of the models, performance of each model based on the retrieved cloud-stored data was measured for accuracy. Results. From the accuracy plot, it was concluded that k-NN was more accurate (97.97%) followed by decision tree (97.79), support vector machine (97.42), logistics regression (96.50), random forest (90.66), gradient boosting classifier (87.77), and Naïve Bayes (73.50) in COVID-19 prognosis. Conclusion. The paper presents a health monitoring IoT framework having high clinical significance in real-time and remote healthcare monitoring. The findings reported here and the lessons learnt shall enable the healthcare system worldwide to counter not only this ongoing COVID but many other such global pandemics the humanity may suffer from time to come. [ABSTRACT FROM AUTHOR]

Glaucoma is a serious eye disease characterized by dysfunction and loss of retinal ganglion cells (RGCs) which can eventually lead to loss of vision. Robust mass screening may help to extend the symptom-free life for the affected patients. The retinal optic nerve fiber layer can be assessed using optical coherence tomography, scanning laser polarimetry (SLP), and Heidelberg Retina Tomography (HRT) scanning methods which, unfortunately, are expensive methods and hence, a novel automated glaucoma diagnosis system is needed. This paper proposes a new model for mass screening that aims to decrease the false negative rate (FNR). The model is based on applying nine different machine learning techniques in a majority voting model. The top five techniques that provide the highest accuracy will be used to build a consensus ensemble to make the final decision. The results from applying both models on a dataset with 499 records show a decrease in the accuracy rate from 90% to 83% and a decrease in false negative rate (FNR) from 8% to 0% for majority voting and consensus model, respectively. These results indicate that the proposed model can reduce FNR dramatically while maintaining a reasonable overall accuracy which makes it suitable for mass screening. [ABSTRACT FROM AUTHOR]

Objective: Automated machine learning (autoML) platforms allow health care professionals to play an active role in the development of machine learning (ML) algorithms according to scientific or clinical needs. The aim of this study was to develop and evaluate such a model for automated detection and grading of distal hand osteoarthritis (OA). Methods: A total of 13,690 hand radiographs from 2,863 patients within the Swiss Cohort of Quality Management (SCQM) and an external control data set of 346 non‐SCQM patients were collected and scored for distal interphalangeal OA (DIP‐OA) using the modified Kellgren/Lawrence (K/L) score. Giotto (Learn to Forecast [L2F]) was used as an autoML platform for training two convolutional neural networks for DIP joint extraction and subsequent classification according to the K/L scores. A total of 48,892 DIP joints were extracted and then used to train the classification model. Heatmaps were generated independently of the platform. User experience of a web application as a provisional user interface was investigated by rheumatologists and radiologists. Results: The sensitivity and specificity of this model for detecting DIP‐OA were 79% and 86%, respectively. The accuracy for grading the correct K/L score was 75%, with a κ score of 0.76. The accuracy per DIP‐OA class differed, with 86% for no OA (defined as K/L scores 0 and 1), 71% for a K/L score of 2, 46% for a K/L score of 3, and 67% for a K/L score of 4. Similar values were obtained in an independent external test set. Qualitative and quantitative user experience testing of the web application revealed a moderate to high demand for automated DIP‐OA scoring among rheumatologists. Conversely, radiologists expressed a low demand, except for the use of heatmaps. Conclusion: AutoML platforms are an opportunity to develop clinical end‐to‐end ML algorithms. Here, automated radiographic DIP‐OA detection is both feasible and usable, whereas grading among individual K/L scores (eg, for clinical trials) remains challenging. [ABSTRACT FROM AUTHOR]

Background: The application of data-driven methods is expected to play an increasingly important role in healthcare. However, a lack of personnel with the necessary skills to develop these models and interpret its output is preventing a wider adoption of these methods. To address this gap, we introduce and describe ORIENTATE, a software for automated application of machine learning classification algorithms by clinical practitioners lacking specific technical skills. ORIENTATE allows the selection of features and the target variable, then automatically generates a number of classification models and cross-validates them, finding the best model and evaluating it. It also implements a custom feature selection algorithm for systematic searches of the best combination of predictors for a given target variable. Finally, it outputs a comprehensive report with graphs that facilitates the explanation of the classification model results, using global interpretation methods, and an interface for the prediction of new input samples. Feature relevance and interaction plots provided by ORIENTATE allow to use it for statistical inference, which can replace and/or complement classical statistical studies. Results: Its application to a dataset with healthy and special health care needs (SHCN) children, treated under deep sedation, was discussed as case study. On the example dataset, despite its small size, the feature selection algorithm found a set of features able to predict the need for a second sedation with a f1 score of 0.83 and a ROC (AUC) of 0.92. Eight predictive factors for both populations were found and ordered by the relevance assigned to them by the model. A discussion of how to derive inferences from the relevance and interaction plots and a comparison with a classical study is also provided. Conclusions: ORIENTATE automatically finds suitable features and generates accurate classifiers which can be used in preventive tasks. In addition, researchers without specific skills on data methods can use it for the application of machine learning classification and as a complement to classical studies for inferential analysis of features. In the case study, a high prediction accuracy for a second sedation in SHCN children was achieved. The analysis of the relevance of the features showed that the number of teeth with pulpar treatments at the first sedation is a predictive factor for a second sedation. [ABSTRACT FROM AUTHOR]

Rising incidence and mortality of cancer have led to an incremental amount of research in the field. To learn from preexisting data, it has become important to capture maximum information related to disease type, stage, treatment, and outcomes. Medical imaging reports are rich in this kind of information but are only present as free text. The extraction of information from such unstructured text reports is labor-intensive. The use of Natural Language Processing (NLP) tools to extract information from radiology reports can make it less time-consuming as well as more effective. In this study, we have developed and compared different models for the classification of lung carcinoma reports using clinical concepts. This study was approved by the institutional ethics committee as a retrospective study with a waiver of informed consent. A clinical concept-based classification pipeline for lung carcinoma radiology reports was developed using rule-based as well as machine learning models and compared. The machine learning models used were XGBoost and two more deep learning model architectures with bidirectional long short-term neural networks. A corpus consisting of 1700 radiology reports including computed tomography (CT) and positron emission tomography/computed tomography (PET/CT) reports were used for development and testing. Five hundred one radiology reports from MIMIC-III Clinical Database version 1.4 was used for external validation. The pipeline achieved an overall F1 score of 0.94 on the internal set and 0.74 on external validation with the rule-based algorithm using expert input giving the best performance. Among the machine learning models, the Bi-LSTM_dropout model performed better than the ML model using XGBoost and the Bi-LSTM_simple model on internal set, whereas on external validation, the Bi-LSTM_simple model performed relatively better than other 2. This pipeline can be used for clinical concept-based classification of radiology reports related to lung carcinoma from a huge corpus and also for automated annotation of these reports. [ABSTRACT FROM AUTHOR]

A correct protocol assignment is critical to high-quality imaging examinations, and its automation can be amenable to natural language processing (NLP). Assigning protocols for abdominal imaging CT scans is particularly challenging given the multiple organ specific indications and parameters. We compared conventional machine learning, deep learning, and automated machine learning builder workflows for this multiclass text classification task. A total of 94,501 CT studies performed over 4 years and their assigned protocols were obtained. Text data associated with each study including the ordering provider generated free text study indication and ICD codes were used for NLP analysis and protocol class prediction. The data was classified into one of 11 abdominal CT protocol classes before and after augmentations used to account for imbalances in the class sample sizes. Four machine learning (ML) algorithms, one deep learning algorithm, and an automated machine learning (AutoML) builder were used for the multilabel classification task: Random Forest (RF), Tree Ensemble (TE), Gradient Boosted Tree (GBT), multi-layer perceptron (MLP), Universal Language Model Fine-tuning (ULMFiT), and Google's AutoML builder (Alphabet, Inc., Mountain View, CA), respectively. On the unbalanced dataset, the manually coded algorithms all performed similarly with F1 scores of 0.811 for RF, 0.813 for TE, 0.813 for GBT, 0.828 for MLP, and 0.847 for ULMFiT. The AutoML builder performed better with a F1 score of 0.854. On the balanced dataset, the tree ensemble machine learning algorithm performed the best with an F1 score of 0.803 and a Cohen's kappa of 0.612. AutoML methods took a longer time for completion of NLP model training and evaluation, 4 h and 45 min compared to an average of 51 min for manual methods. Machine learning and natural language processing can be used for the complex multiclass classification task of abdominal imaging CT scan protocol assignment. [ABSTRACT FROM AUTHOR]