Adapting multilingual vision language transformers for low-resource Urdu optical character recognition (OCR).

In the realm of digitizing written content, the challenges posed by low-resource languages are noteworthy. These languages, often lacking in comprehensive linguistic resources, require specialized attention to develop robust systems for accurate optical character recognition (OCR). This article addresses the significance of focusing on such languages and introduces ViLanOCR, an innovative bilingual OCR system tailored for Urdu and English. Unlike existing systems, which struggle with the intricacies of low-resource languages, ViLanOCR leverages advanced multilingual transformer-based language models to achieve superior performances. The proposed approach is evaluated using the character error rate (CER) metric and achieves state-of-the-art results on the Urdu UHWR dataset, with a CER of 1.1%. The experimental results demonstrate the effectiveness of the proposed approach, surpassing state of the-art baselines in Urdu handwriting digitization.

DIGIPREDICT: physiological, behavioural and environmental predictors of asthma attacks-a prospective observational study using digital markers and artificial intelligence-study protocol.

INTRODUCTION: Asthma attacks are a leading cause of morbidity and mortality but are preventable in most if detected and treated promptly. However, the changes that occur physiologically and behaviourally in the days and weeks preceding an attack are not always recognised, highlighting a potential role for technology. The aim of this study 'DIGIPREDICT' is to identify early digital markers of asthma attacks using sensors embedded in smart devices including watches and inhalers, and leverage health and environmental datasets and artificial intelligence, to develop a risk prediction model to provide an early, personalised warning of asthma attacks. METHODS AND ANALYSIS: A prospective sample of 300 people, 12 years or older, with a history of a moderate or severe asthma attack in the last 12 months will be recruited in New Zealand. Each participant will be given a smart watch (to assess physiological measures such as heart and respiratory rate), peak flow meter, smart inhaler (to assess adherence and inhalation) and a cough monitoring application to use regularly over 6 months with fortnightly questionnaires on asthma control and well-being. Data on sociodemographics, asthma control, lung function, dietary intake, medical history and technology acceptance will be collected at baseline and at 6 months. Asthma attacks will be measured by self-report and confirmed with clinical records. The collected data, along with environmental data on weather and air quality, will be analysed using machine learning to develop a risk prediction model for asthma attacks. ETHICS AND DISSEMINATION: Ethical approval has been obtained from the New Zealand Health and Disability Ethics Committee (2023 FULL 13541). Enrolment began in August 2023. Results will be presented at local, national and international meetings, including dissemination via community groups, and submission for publication to peer-reviewed journals. TRIAL REGISTRATION NUMBER: Australian New Zealand Clinical Trials Registry ACTRN12623000764639; Australian New Zealand Clinical Trials Registry.

Investigating Machine Learning Techniques for Predicting Risk of Asthma Exacerbations: A Systematic Review.

Asthma, a common chronic respiratory disease among children and adults, affects more than 200 million people worldwide and causes about 450,000 deaths each year. Machine learning is increasingly applied in healthcare to assist health practitioners in decision-making. In asthma management, machine learning excels in performing well-defined tasks, such as diagnosis, prediction, medication, and management. However, there remain uncertainties about how machine learning can be applied to predict asthma exacerbation. This study aimed to systematically review recent applications of machine learning techniques in predicting the risk of asthma attacks to assist asthma control and management. A total of 860 studies were initially identified from five databases. After the screening and full-text review, 20 studies were selected for inclusion in this review. The review considered recent studies published from January 2010 to February 2023. The 20 studies used machine learning techniques to support future asthma risk prediction by using various data sources such as clinical, medical, biological, and socio-demographic data sources, as well as environmental and meteorological data. While some studies considered prediction as a category, other studies predicted the probability of exacerbation. Only a group of studies applied prediction windows. The paper proposes a conceptual model to summarise how machine learning and available data sources can be leveraged to produce effective models for the early detection of asthma attacks. The review also generated a list of data sources that other researchers may use in similar work. Furthermore, we present opportunities for further research and the limitations of the preceding studies.

Multi-Class Skin Lesions Classification Using Deep Features.

Skin cancer classification is a complex and time-consuming task. Existing approaches use segmentation to improve accuracy and efficiency, but due to different sizes and shapes of lesions, segmentation is not a suitable approach. In this research study, we proposed an improved automated system based on hybrid and optimal feature selections. Firstly, we balanced our dataset by applying three different transformation techniques, which include brightness, sharpening, and contrast enhancement. Secondly, we retrained two CNNs, Darknet53 and Inception V3, using transfer learning. Thirdly, the retrained models were used to extract deep features from the dataset. Lastly, optimal features were selected using moth flame optimization (MFO) to overcome the curse of dimensionality. This helped us in improving accuracy and efficiency of our model. We achieved 95.9%, 95.0%, and 95.8% on cubic SVM, quadratic SVM, and ensemble subspace discriminants, respectively. We compared our technique with state-of-the-art approach.

Impact of socio-economic status and race on emergency hospital admission outcomes: Analysis from hospital admissions between 2001 and 2012.

Socio-economic and racial/ethnic disparities in healthcare quality have been the point of huge discussion and debate. There is currently a public debate over healthcare legislation in the United States to eliminate the disparities in healthcare. We reviewed the literature and critically examined standard socio-economic and racial/ethnic measurement approaches. As a result of the literature review, we identified and discussed the limitations in existing quality assessment for identifying and addressing these disparities. The aim of this research was to investigate the difference between health outcomes based on patients' ability to pay and ethnic status during a single emergency admission. We conducted a multifactorial analysis using the 11-year admissions data from a single hospital to test the bias in short-term health outcomes for length of stay and death rate, based on 'payment type' and 'race', for emergency hospital admissions. Inconclusive findings for racial bias in outcomes may be influenced by different insurance and demographic profiles by race. As a result, we found that the Self-Pay (no insurance) category has the shortest statistically significant length of stay. While the differences between Medicare, Private and Government are not significant, Self-Pay was significantly shorter. That 'Whites' have more Medicare (older) patients than 'Blacks' might possibly lead to a longer length of stay and higher death rate for the group.

Sentiment Analysis on USA vs. New Zealand on Health and Safety Mandates During Early Stages of COVID-19 Pandemic.

The Coronavirus pandemic has surprised the world and social media was extremely used to express frustrations and development of the cases found. Social media tools, such as Twitter, show a comparable impact with the number of tweets related to COVID-19 indicating remarkable development in a limited ability to focus time. The purpose of this paper is to investigate the impact of Coronavirus on the United States of America (USA) and New Zealand (NZ), and how that is reflected in a sentiment analysis through the examination of American and New Zealand tweets. We have gathered tweets from a March 2020 - August 2020 and used sentiment extraction on the tweets. The major finding of this sentiment extraction is the fact that the overall average sentiment over the 5-month period stayed in a negative range in the USA and NZ. This paper aims to analyze these trends, identify patterns, and determine whether these trends were caused by the COVID-19 pandemic or outside sources. One trend that was analyzed was the spike of COVID-19 results in relation to the number of protests occurring in the USA.

Internet of things (IoT) applications for elderly care: a reflective review.

Increasing in elderly population put extra pressure on healthcare systems globally in terms of operational costs and resources. To minimize this pressure and provide efficient healthcare services, the application of the Internet of Things (IoT) and wearable technology could be promising. These technologies have the potential to improve the quality of life of the elderly population while reducing strain on healthcare systems and minimizing their operational cost. Although IoT and wearable applications for elderly healthcare purposes were reviewed previously, there is a further need to summarize their current applications in this fast-developing area. This paper provides a comprehensive overview of IoT and wearable technologies' applications including the types of data collected and the types of devices for elderly healthcare. This paper provides insights into existing areas of IoT/wearable applications while presenting new research opportunities in emerging areas of applications, such as robotic technology and integrated applications. The analysis in this paper could be useful to healthcare solution designers and developers in defining technology supported futuristic healthcare strategies to serve elderly people and increasing their quality of life.

Predicting Patients at Risk of 30-Day Unplanned Hospital Readmission.

We developed a machine learning model to predict 30-day readmissions using the model types; XGBoost, Random Forests and Adaboost with decision stumps as a base learner with different feature combinations and preprocessing procedures. The proposed model achieved the F1-score (0.386 ± 0.006), sensitivity (0.598 ± 0.013), positive predictive value (PPV) (0.285 ± 0.004) and negative predictive value (NPV) (0.932 ± 0.002). When compared with LACE and PARR (NZ) models, the proposed model achieved better F1-score by 12.5% compared to LACE and 22.9% compared to PARR (NZ). The mean sensitivity of the proposed model was 6.0% higher than LACE and 42.4% higher than PARR (NZ). The mean PPV was 15.9% and 13.5% higher than LACE and PARR (NZ) respectively.

Obesity Risk Assessment Model Using Wearable Technology with Personalized Activity, Calorie Expenditure and Health Profile.

There is a worldwide increase in the rate of obesity and its related long-term conditions, emphasizing an immediate need to address this modern-age global epidemic of healthy living. Moreover, healthcare spending on long-term or chronic care conditions such as obesity is increasing to the point that requires effective interventions and advancements to reduce the burden of the healthcare. This research focuses on the early risk assessment of overweight/obesity using wearable technology. We establish an individualised health profile that identifies the level of activity and current health status of an individual using real-time activity and vital signs. We developed an algorithm to assess the risk of obesity using the individual's current activity and calorie expenditure. The algorithm was deployed on a smartphone application to collect wearable device data, and user reported data. Based on the collected data, the proposed application assesses the risk of obesity/overweight, measures the current activity level and recommends an optimized calorie plan.

A Systematic Review of Wearable Sensors and IoT-Based Monitoring Applications for Older Adults - a Focus on Ageing Population and Independent Living.

This review aims to present current advancements in wearable technologies and IoT-based applications to support independent living. The secondary aim was to investigate the barriers and challenges of wearable sensors and Internet-of-Things (IoT) monitoring solutions for older adults. For this work, we considered falls and activity of daily life (ADLs) for the ageing population (older adults). A total of 327 articles were screened, and 14 articles were selected for this review. This review considered recent studies published between 2015 and 2019. The research articles were selected based on the inclusion and exclusion criteria, and studies that support or present a vision to provide advancement to the current space of ADLs, independent living and supporting the ageing population. Most studies focused on the system aspects of wearable sensors and IoT monitoring solutions including advanced sensors, wireless data collection, communication platform and usability. Moderate to low usability/ user-friendly approach is reported in most of the studies. Other issues found were inaccurate sensors, battery/ power issues, restricting the users within the monitoring area/ space and lack of interoperability. The advancement of wearable technology and the possibilities of using advanced IoT technology to assist older adults with their ADLs and independent living is the subject of many recent research and investigation.

A Cox-Based Risk Prediction Model for Early Detection of Cardiovascular Disease: Identification of Key Risk Factors for the Development of a 10-Year CVD Risk Prediction.

BACKGROUND AND OBJECTIVE: Current cardiovascular disease (CVD) risk models are typically based on traditional laboratory-based predictors. The objective of this research was to identify key risk factors that affect the CVD risk prediction and to develop a 10-year CVD risk prediction model using the identified risk factors. METHODS: A Cox proportional hazard regression method was applied to generate the proposed risk model. We used the dataset from Framingham Original Cohort of 5079 men and women aged 30-62 years, who had no overt symptoms of CVD at the baseline; among the selected cohort 3189 had a CVD event. RESULTS: A 10-year CVD risk model based on multiple risk factors (such as age, sex, body mass index (BMI), hypertension, systolic blood pressure (SBP), cigarettes per day, pulse rate, and diabetes) was developed in which heart rate was identified as one of the novel risk factors. The proposed model achieved a good discrimination and calibration ability with C-index (receiver operating characteristic (ROC)) being 0.71 in the validation dataset. We validated the model via statistical and empirical validation. CONCLUSION: The proposed CVD risk prediction model is based on standard risk factors, which could help reduce the cost and time required for conducting the clinical/laboratory tests. Healthcare providers, clinicians, and patients can use this tool to see the 10-year risk of CVD for an individual. Heart rate was incorporated as a novel predictor, which extends the predictive ability of the past existing risk equations.

Machine Learning-based Risk of Hospital Readmissions: Predicting Acute Readmissions within 30 Days of Discharge.

The objective of this study was to design and develop a 30-day risk of hospital readmission predictive model using machine learning techniques. The proposed risk of readmission predictive model was then validated with the two most commonly used risk of readmission models - LACE index and patient at-risk of hospital readmission (PARR). The study cohort consisted of 180,118 admissions with 22565 (12.5%) of actual readmissions within 30-day of hospital discharge, from 01 Jan 2015 to 31 Dec 2016 from two Auckland-region hospitals. We developed a machine learning model to predict 30-day readmissions using the model types: XGBoost, Random Forests and Adaboost with decision stumps as a base learner with different feature combinations and preprocessing procedures. The proposed model achieved the F1-score (0.386 ± 0.006), sensitivity (0.598 ± 0.013), positive predictive value (PPV) (0.285 ± 0.004) and negative predictive value (NPV) (0.932 ± 0.002). When compared with LACE and PARR (NZ) models, the proposed model achieved better F1-score by 12.5% compared to LACE and 22.9% compared to PARR (NZ). The mean sensitivity of the proposed model was 6.0% higher than LACE and 42.4% higher than PARR (NZ). The mean PPV was 15.9% and 13.5% higher than LACE and PARR (NZ) respectively.

Clinical decision support systems in hospital care using ubiquitous devices: Current issues and challenges.

Supporting clinicians in decision making using advanced technologies has been an active research area in biomedical engineering during the past years. Among a wide range of ubiquitous systems, smartphone applications have been increasingly developed in healthcare settings to help clinicians as well as patients. Today, many smartphone applications, from basic data analysis to advanced patient monitoring, are available to clinicians and patients. Such applications are now increasingly integrating into healthcare for clinical decision support, and therefore, concerns around accuracy, stability, and dependency of these applications are rising. In addition, lack of attention to the clinicians' acceptability, as well as the low impact on the medical professionals' decision making, are posing more serious issues on the acceptability of smartphone applications. This article reviews smartphone-based decision support applications, focusing on hospital care settings and their overall impact of these applications on the wider clinical workflow. Additionally, key challenges and barriers of the current ubiquitous device-based healthcare applications are identified. Finally, this article addresses current challenges, future directions, and the adoption of mobile healthcare applications.

Clinical Decision Support for Early Detection of Prediabetes and Type 2 Diabetes Mellitus Using Wearable Technology.

Worldwide spending on long-term and chronic care conditions is increasing to a point that requires immediate interventions and advancements to reduce the burden of the healthcare cost. This research is focused on early detection of prediabetes and type 2 diabetes mellitus (T2DM) using wearable technology. An artificial intelligence model was developed based on adaptive-neuro fuzzy interference to detect prediabetes and T2DM via individualized monitoring. The key contributing factors to the proposed model include heart rate, heart rate variability, breathing rate, breathing volume, and activity data (steps, cadence and calories). The data was collected using an advanced wearable body vest. The real-time data was combined with manual recordings of blood glucose, height, weight, age and sex. The model analyzed the data alongside a clinical knowledge-base. Fuzzy rules were used to establish baseline values via existing interventions, clinical guidelines and protocols. The proposed model was tested and validated using Kappa analysis and achieved an overall agreement of 91%.

Falls management framework for supporting an independent lifestyle for older adults: a systematic review.

Falls are one of the common health and well-being issues among the older adults. Internet of things (IoT)-based health monitoring systems have been developed over the past two decades for improving healthcare services for older adults to support an independent lifestyle. This research systematically reviews technological applications related to falls detection and falls management. The systematic review was conducted in accordance to the preferred reporting items for systematic reviews and meta-analysis statement (PRISMA). Twenty-four studies out of 806 articles published between 2015 and 2017 were identified and included in this review. Selected studies were related to pre-fall and post-fall applications using motion sensors (10; 41.67%), environment sensors (10; 41.67%) and few studies used the combination of these types of sensors (4; 16.67%). As an outcome of this review, we postulated a falls management framework (FMF). FMF considered pre- and post-fall strategies to support older adults live independently. A part of this approach involved active analysis of sensor data with the aim of helping the older adults manage their risk of fall and stay safe in their home. FMF aimed to serve the researchers, developers, clinicians and policy makers with pre- and post-falls management strategies to enhance the older adults' independent living and well-being.

Medical Device Integrated Vital Signs Monitoring Application with Real-Time Clinical Decision Support.

This research involves the design and development of a novel Android smartphone application for real-time vital signs monitoring and decision support. The proposed application integrates market available, wireless and Bluetooth connected medical devices for collecting vital signs. The medical device data collected by the app includes heart rate, oxygen saturation and electrocardiograph (ECG). The collated data is streamed/displayed on the smartphone in real-time. This application was designed by adopting six screens approach (6S) mobile development framework and focused on user-centered approach and considered clinicians-as-a-user. The clinical engagement, consultations, feedback and usability of the application in the everyday practices were considered critical from the initial phase of the design and development. Furthermore, the proposed application is capable to deliver rich clinical decision support in real-time using the integrated medical device data.

A Systematic Review of Wearable Patient Monitoring Systems - Current Challenges and Opportunities for Clinical Adoption.

The aim of this review is to investigate barriers and challenges of wearable patient monitoring (WPM) solutions adopted by clinicians in acute, as well as in community, care settings. Currently, healthcare providers are coping with ever-growing healthcare challenges including an ageing population, chronic diseases, the cost of hospitalization, and the risk of medical errors. WPM systems are a potential solution for addressing some of these challenges by enabling advanced sensors, wearable technology, and secure and effective communication platforms between the clinicians and patients. A total of 791 articles were screened and 20 were selected for this review. The most common publication venue was conference proceedings (13, 54%). This review only considered recent studies published between 2015 and 2017. The identified studies involved chronic conditions (6, 30%), rehabilitation (7, 35%), cardiovascular diseases (4, 20%), falls (2, 10%) and mental health (1, 5%). Most studies focussed on the system aspects of WPM solutions including advanced sensors, wireless data collection, communication platform and clinical usability based on a specific area or disease. The current studies are progressing with localized sensor-software integration to solve a specific use-case/health area using non-scalable and 'silo' solutions. There is further work required regarding interoperability and clinical acceptance challenges. The advancement of wearable technology and possibilities of using machine learning and artificial intelligence in healthcare is a concept that has been investigated by many studies. We believe future patient monitoring and medical treatments will build upon efficient and affordable solutions of wearable technology.

Mobile technologies and the holistic management of chronic diseases.

Ageing populations and unhealthy lifestyles have led to some chronic conditions such as diabetes and heart disease reaching epidemic proportions in many developed nations. This paper explores the potential of mobile technologies to improve this situation. The pervasive nature of these technologies can contribute holistically across the whole spectrum of chronic care ranging from public information access and awareness, through monitoring and treatment of chronic disease, to support for patient carers. A related study to determine the perceptions of healthcare providers to m-health confirmed the view that attitudes were likely to be more important barriers to progress than technology. A key finding concerned the importance of seamless and integrated m-health processes across the spectrum of chronic disease management.

Opportunities and barriers for mobile health in New Zealand.

Ownership and the use of mobile technologies greatly exceed those of personal desktop computer systems and countries throughout the world are beginning to understand how these technologies can enhance the delivery of healthcare (m-health). This paper reviews the opportunities and barriers for m-health and describes a study to understand its potential in New Zealand. A survey consisting of a questionnaire and in-depth interviews was used to reveal clinician and service provider attitudes to m-health. The general perception is that m-health will be an increasing component of future healthcare with many opportunities for empowering patients, delivering convenience care, and supporting carers as well as offering the potential for more effective public health and lifestyle broadcasting. Participants recognised several barriers to the acceptance and sustainability of m-health, identifying privacy of information and device form factor as major concerns.