Machine learning methods for detecting urinary tract infection and analysing daily living activities in people with dementia

A dual-sensing strategy for the early diagnosis of urinary tract infections via detecting biofilm cellulose using aromatic amino acid-capped Au and Ag nanoparticles

Currently, urinary tract infection (UTI) diagnosis focuses on planktonic cell detection rather than biofilm detection, but the facile identification of UPEC bacterial biofilms is crucial in UTI diagnosis as the biofilm formed by bacteria is the causative agent of recurrent and chronic UTIs. Therefore, in this work, we developed a simple, cost-effective, colorimetric, and electrochemical-based strategy for the detection of cellulose in urine. Cellulose, a biofilm matrix component, was detected using tyrosine-capped gold and silver nanoparticles through a visible colorimetric change with a decrease in the absorbance intensity and a decrease in current response in the case of cyclic voltammetry. The sensor displayed a linear detection range of 10-70 mg mL-1 for colorimetry and 10-300 μg mL-1 for cyclic voltammetry with a good selectivity of <2.8% and a recovery rate of 95-100% in real-time sample analysis. Moreover, the binding affinity of cellulose with tyrosine was investigated using molecular docking studies to validate the sensing mechanism. We anticipate that our work will aid clinicians in the implementation of rapid, cost-effective, and definitive diagnosis of UTIs.

Digital remote monitoring for screening and early detection of urinary tract infections

Urinary Tract Infections (UTIs) are one of the most prevalent bacterial infections in older adults and a significant contributor to unplanned hospital admissions in People Living with Dementia (PLWD), with early detection being crucial due to the predicament of reporting symptoms and limited help-seeking behaviour. The most common diagnostic tool is urine sample analysis, which can be time-consuming and is only employed where UTI clinical suspicion exists. In this method development and proof-of-concept study, participants living with dementia were monitored via low-cost devices in the home that passively measure activity, sleep, and nocturnal physiology. Using 27828 person-days of remote monitoring data (from 117 participants), we engineered features representing symptoms used for diagnosing a UTI. We then evaluate explainable machine learning techniques in passively calculating UTI risk and perform stratification on scores to support clinical translation and allow control over the balance between alert rate and sensitivity and specificity. The proposed UTI algorithm achieves a sensitivity of 65.3% (95% Confidence Interval (CI) = 64.3-66.2) and specificity of 70.9% (68.6-73.1) when predicting UTIs on unseen participants and after risk stratification, a sensitivity of 74.7% (67.9-81.5) and specificity of 87.9% (85.0-90.9). In addition, feature importance methods reveal that the largest contributions to the predictions were bathroom visit statistics, night-time respiratory rate, and the number of previous UTI events, aligning with the literature. Our machine learning method alerts clinicians of UTI risk in subjects, enabling earlier detection and enhanced screening when considering treatment.

TIHM: An open dataset for remote healthcare monitoring in dementia

Dementia is a progressive condition that affects cognitive and functional abilities. There is a need for reliable and continuous health monitoring of People Living with Dementia (PLWD) to improve their quality of life and support their independent living. Healthcare services often focus on addressing and treating already established health conditions that affect PLWD. Managing these conditions continuously can inform better decision-making earlier for higher-quality care management for PLWD. The Technology Integrated Health Management (TIHM) project developed a new digital platform to routinely collect longitudinal, observational, and measurement data, within the home and apply machine learning and analytical models for the detection and prediction of adverse health events affecting the well-being of PLWD. This work describes the TIHM dataset collected during the second phase (i.e., feasibility study) of the TIHM project. The data was collected from homes of 56 PLWD and associated with events and clinical observations (daily activity, physiological monitoring, and labels for health-related conditions). The study recorded an average of 50 days of data per participant, totalling 2803 days.

Using home monitoring technology to study the effects of traumatic brain injury in older multimorbid adults

Internet of things (IOT) based in-home monitoring systems can passively collect high temporal resolution data in the community, offering valuable insight into the impact of health conditions on patients' day-to-day lives. We used this technology to monitor activity and sleep patterns in older adults recently discharged after traumatic brain injury (TBI). The demographics of TBI are changing, and it is now a leading cause of hospitalisation in older adults. However, research in this population is minimal. We present three cases, showcasing the potential of in-home monitoring systems in understanding and managing early recovery in older adults following TBI.

Multicohort cross-sectional study of cognitive and behavioural digital biomarkers in neurodegeneration: the Living Lab Study protocol

INTRODUCTION AND AIMS

Digital biomarkers can provide a cost-effective, objective and robust measure for neurological disease progression, changes in care needs and the effect of interventions. Motor function, physiology and behaviour can provide informative measures of neurological conditions and neurodegenerative decline. New digital technologies present an opportunity to provide remote, high-frequency monitoring of patients from within their homes. The purpose of the living lab study is to develop novel digital biomarkers of functional impairment in those living with neurodegenerative disease (NDD) and neurological conditions.

METHODS AND ANALYSIS

The Living Lab study is a cross-sectional observational study of cognition and behaviour in people living with NDDs and other, non-degenerative neurological conditions. Patients (n≥25 for each patient group) with dementia, Parkinson's disease, amyotrophic lateral sclerosis, mild cognitive impairment, traumatic brain injury and stroke along with controls (n≥60) will be pragmatically recruited. Patients will carry out activities of daily living and functional assessments within the Living Lab. The Living Lab is an apartment-laboratory containing a functional kitchen, bathroom, bed and living area to provide a controlled environment to develop novel digital biomarkers. The Living Lab provides an important intermediary stage between the conventional laboratory and the home. Multiple passive environmental sensors, internet-enabled medical devices, wearables and electroencephalography (EEG) will be used to characterise functional impairments of NDDs and non-NDD conditions. We will also relate these digital technology measures to clinical and cognitive outcomes.

ETHICS AND DISSEMINATION

Ethical approvals have been granted by the Imperial College Research Ethics Committee (reference number: 21IC6992). Results from the study will be disseminated at conferences and within peer-reviewed journals.

Digital Endpoints for Assessing Instrumental Activities of Daily Living in Mild Cognitive Impairment: Systematic Review

BACKGROUND

Subtle impairments in instrumental activities of daily living (IADLs) can be a key predictor of disease progression and are considered central to functional independence. Mild cognitive impairment (MCI) is a syndrome associated with significant changes in cognitive function and mild impairment in complex functional abilities. The early detection of functional decline through the identification of IADL impairments can aid early intervention strategies. Digital health technology is an objective method of capturing IADL-related behaviors. However, it is unclear how these IADL-related behaviors have been digitally assessed in the literature and what differences can be observed between MCI and normal aging.

OBJECTIVE

This review aimed to identify the digital methods and metrics used to assess IADL-related behaviors in people with MCI and report any statistically significant differences in digital endpoints between MCI and normal aging and how these digital endpoints change over time.

METHODS

A total of 16,099 articles were identified from 8 databases (CINAHL, Embase, MEDLINE, ProQuest, PsycINFO, PubMed, Web of Science, and Scopus), out of which 15 were included in this review. The included studies must have used continuous remote digital measures to assess IADL-related behaviors in adults characterized as having MCI by clinical diagnosis or assessment. This review was conducted in accordance with the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines.

RESULTS

Ambient technology was the most commonly used digital method to assess IADL-related behaviors in the included studies (14/15, 93%), with passive infrared motion sensors (5/15, 33%) and contact sensors (5/15, 33%) being the most prevalent types of methods. Digital technologies were used to assess IADL-related behaviors across 5 domains: activities outside of the home, everyday technology use, household and personal management, medication management, and orientation. Other recognized domains-culturally specific tasks and socialization and communication-were not assessed. Of the 79 metrics recorded among 11 types of technologies, 65 (82%) were used only once. There were inconsistent findings around differences in digital IADL endpoints across the cognitive spectrum, with limited longitudinal assessment of how they changed over time.

CONCLUSIONS

Despite the broad range of metrics and methods used to digitally assess IADL-related behaviors in people with MCI, several IADLs relevant to functional decline were not studied. Measuring multiple IADL-related digital endpoints could offer more value than the measurement of discrete IADL outcomes alone to observe functional decline. Key recommendations include the development of suitable core metrics relevant to IADL-related behaviors that are based on clinically meaningful outcomes to aid the standardization and further validation of digital technologies against existing IADL measures. Increased longitudinal monitoring is necessary to capture changes in digital IADL endpoints over time in people with MCI.

TRIAL REGISTRATION

PROSPERO International Prospective Register of Systematic Reviews CRD42022326861; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=326861.

Using home monitoring technology to study the effects of traumatic brain injury on older multimorbid adults: protocol for a feasibility study

INTRODUCTION

The prevalence of traumatic brain injury (TBI) among older adults is increasing exponentially. The sequelae can be severe in older adults and interact with age-related conditions such as multimorbidity. Despite this, TBI research in older adults is sparse. Minder, an in-home monitoring system developed by the UK Dementia Research Institute Centre for Care Research and Technology, uses infrared sensors and a bed mat to passively collect sleep and activity data. Similar systems have been used to monitor the health of older adults living with dementia. We will assess the feasibility of using this system to study changes in the health status of older adults in the early period post-TBI.

METHODS AND ANALYSIS

The study will recruit 15 inpatients (>60 years) with a moderate-severe TBI, who will have their daily activity and sleep patterns monitored using passive and wearable sensors over 6 months. Participants will report on their health during weekly calls, which will be used to validate sensor data. Physical, functional and cognitive assessments will be conducted across the duration of the study. Activity levels and sleep patterns derived from sensor data will be calculated and visualised using activity maps. Within-participant analysis will be performed to determine if participants are deviating from their own routines. We will apply machine learning approaches to activity and sleep data to assess whether the changes in these data can predict clinical events. Qualitative analysis of interviews conducted with participants, carers and clinical staff will assess acceptability and utility of the system.

ETHICS AND DISSEMINATION

Ethical approval for this study has been granted by the London-Camberwell St Giles Research Ethics Committee (REC) (REC number: 17/LO/2066). Results will be submitted for publication in peer-reviewed journals, presented at conferences and inform the design of a larger trial assessing recovery after TBI.

Developing Acute Event Risk Profiles for Older Adults with Dementia in Long-Term Care Using Motor Behavior Clusters Derived from Deep Learning

OBJECTIVES

This paper uses deep (machine) learning techniques to develop and test how motor behaviors, derived from location and movement sensor tracking data, may be associated with falls, delirium, and urinary tract infections (UTIs) in long-term care (LTC) residents.

DESIGN

Longitudinal observational study.

SETTING AND PARTICIPANTS

A total of 23 LTC residents (81,323 observations) with cognitive impairment or dementia in 2 northeast Department of Veterans Affairs LTC facilities.

METHODS

More than 18 months of continuous (24/7) monitoring of motor behavior and activity levels used objective radiofrequency identification sensor data to track and record movement data. Occurrence of acute events was recorded each week. Unsupervised deep learning models were used to classify motor behaviors into 5 clusters; supervised decision tree algorithms used these clusters to predict acute health events (falls, delirium, and UTIs) the week before the week of the event.

RESULTS

Motor behaviors were classified into 5 categories (Silhouette score = 0.67), and these were significantly different from each other. Motor behavior classifications were sensitive and specific to falls, delirium, and UTI predictions 1 week before the week of the event (sensitivity range = 0.88-0.91; specificity range = 0.71-0.88).

CONCLUSION AND IMPLICATIONS

Intraindividual changes in motor behaviors predict some of the most common and detrimental acute events in LTC populations. Study findings suggest real-time locating system sensor data and machine learning techniques may be used in clinical applications to effectively prevent falls and lead to the earlier recognition of risk for delirium and UTIs in this vulnerable population.

Artificial Intelligence in Biological Sciences

Artificial intelligence (AI), currently a cutting-edge concept, has the potential to improve the quality of life of human beings. The fields of AI and biological research are becoming more intertwined, and methods for extracting and applying the information stored in live organisms are constantly being refined. As the field of AI matures with more trained algorithms, the potential of its application in epidemiology, the study of host–pathogen interactions and drug designing widens. AI is now being applied in several fields of drug discovery, customized medicine, gene editing, radiography, image processing and medication management. More precise diagnosis and cost-effective treatment will be possible in the near future due to the application of AI-based technologies. In the field of agriculture, farmers have reduced waste, increased output and decreased the amount of time it takes to bring their goods to market due to the application of advanced AI-based approaches. Moreover, with the use of AI through machine learning (ML) and deep-learning-based smart programs, one can modify the metabolic pathways of living systems to obtain the best possible outputs with the minimal inputs. Such efforts can improve the industrial strains of microbial species to maximize the yield in the bio-based industrial setup. This article summarizes the potentials of AI and their application to several fields of biology, such as medicine, agriculture, and bio-based industry.

Predicting Activity Duration in Smart Sensing Environments Using Synthetic Data and Partial Least Squares Regression: The Case of Dementia Patients

The accurate recognition of activities is fundamental for following up on the health progress of people with dementia (PwD), thereby supporting subsequent diagnosis and treatments. When monitoring the activities of daily living (ADLs), it is feasible to detect behaviour patterns, parse out the disease evolution, and consequently provide effective and timely assistance. However, this task is affected by uncertainties derived from the differences in smart home configurations and the way in which each person undertakes the ADLs. One adjacent pathway is to train a supervised classification algorithm using large-sized datasets; nonetheless, obtaining real-world data is costly and characterized by a challenging recruiting research process. The resulting activity data is then small and may not capture each person’s intrinsic properties. Simulation approaches have risen as an alternative efficient choice, but synthetic data can be significantly dissimilar compared to real data. Hence, this paper proposes the application of Partial Least Squares Regression (PLSR) to approximate the real activity duration of various ADLs based on synthetic observations. First, the real activity duration of each ADL is initially contrasted with the one derived from an intelligent environment simulator. Following this, different PLSR models were evaluated for estimating real activity duration based on synthetic variables. A case study including eight ADLs was considered to validate the proposed approach. The results revealed that simulated and real observations are significantly different in some ADLs (p-value < 0.05), nevertheless synthetic variables can be further modified to predict the real activity duration with high accuracy (R2(pred)>90%).

Application of a Deep Learning Neural Network for Voiding Dysfunction Diagnosis Using a Vibration Sensor

In a clinical context, there are increasing numbers of people with voiding dysfunction. To date, the methods of monitoring the voiding status of patients have included voiding diary records at home or urodynamic examinations at hospitals. The former is less objective and often contains missing data, while the latter lacks frequent measurements and is an invasive procedure. In light of these shortcomings, this study developed an innovative and contact-free technique that assists in clinical voiding dysfunction monitoring and diagnosis. Vibration signals during urination were first detected using an accelerometer and then converted into the mel-frequency cepstrum coefficient (MFCC). Lastly, an artificial intelligence model combined with uniform manifold approximation and projection (UMAP) dimensionality reduction was used to analyze and predict six common patterns of uroflowmetry to assist in diagnosing voiding dysfunction. The model was applied to the voiding database, which included data from 76 males aged 30 to 80 who required uroflowmetry for voiding symptoms. The resulting system accuracy (precision, recall, and f1-score) was around 98% for both the weighted average and macro average. This low-cost system is suitable for at-home urinary monitoring and facilitates the long-term uroflow monitoring of patients outside hospital checkups. From a disease treatment and monitoring perspective, this article also reviews other studies and applications of artificial intelligence-based methods for voiding dysfunction monitoring, thus providing helpful diagnostic information for physicians.

A semi-supervised decision support system to facilitate antibiotic stewardship for urinary tract infections

Urinary Tract Infections (UTIs) are among the most frequently occurring infections in the hospital. Urinalysis and urine culture are the main tools used for diagnosis. Whereas urinalysis is sufficiently sensitive for detecting UTI, it has a relatively low specificity, leading to unnecessary treatment with antibiotics and the risk of increasing antibiotic resistance. We performed an evaluation of the current diagnostic process with an expert-based label for UTI as outcome, retrospectively established using data from the Electronic Health Records. We found that the combination of urinalysis results with the Gram stain and other readily available parameters can be used effectively for predicting UTI. Based on the obtained information, we engineered a clinical decision support system (CDSS) using the reliable semi-supervised ensemble learning (RESSEL) method, and found it to be more accurate than urinalysis or the urine culture for prediction of UTI. The CDSS provides clinicians with this prediction within hours of ordering a culture and thereby enables them to hold off on prematurely prescribing antibiotics for UTI while awaiting the culture results.

Addressing Mild Cognitive Impairment and Boosting Wellness for the Elderly through Personalized Remote Monitoring

Mild cognitive impairment (MCI) may occur with old age and is associated with increased cognitive deterioration compared to what is normal. This may affect the person’s quality of life, health, and independence. In this ageing worldwide context, early diagnosis and personalized assistance for MCI therefore become crucial. This paper makes two important contributions: (1) a system (RO-SmartAgeing) to address MCI, which was developed for Romania; and (2) a set of criteria for evaluating its impact on remote health monitoring. The system aims to provide customized non-invasive remote monitoring, health assessment, and assistance for the elderly within a smart environment set up in their homes. Moreover, it includes multivariate AI-based predictive models that can detect the onset of MCI and its development towards dementia. It was built iteratively, following literature reviews and consultations with health specialists, and it is currently being tested in a simulated home environment. While its main strength is the potential to detect MCI early and follow its evolution, RO-SmartAgeing also supports elderly people in living independently, and it is safe, comfortable, low cost, and privacy protected. Moreover, it can be used by healthcare institutions to continuously monitor a patient’s vital signs, position, and activities, and to deliver reminders and alarms.

Identifying patterns of potentially preventable hospitalisations in people living with dementia

BACKGROUND

Older Australians make up 46% of all potentially preventable hospitalisations (PPHs) and people living with dementia are at significantly greater risk. While policy reforms aim to reduce PPHs, there is currently little evidence available on what drives this, especially for people living with dementia. This study examines patterns of PPHs in people living with dementia to inform service delivery and the development of evidence-based interventions.

METHODS

We used the Victorian Admitted Episodes Dataset from Victoria, Australia, to extract data for people aged 50 and over with a diagnosis of dementia between 2015 and 2016. Potentially avoidable admissions, known as ambulatory care sensitive conditions (ACSCs), were identified. The chi-square test was used to detect differences between admissions for ACSCs and non-ACSCs by demographic, geographical, and administrative factors. Predictors of ACSCs admissions were analysed using univariate and multiple logistic regression.

RESULTS

Of the 8156 hospital records, there were 3884 (48%) ACSCs admissions, of which admissions for urinary tract infections accounted for 31%, followed by diabetes complications (21%). Mean bed-days were 8.26 for non-ACSCs compared with 9.74 for ACSCs (p ≤ 0.001). There were no differences between admissions for ACSCs and non-ACSCs by sex, marital status, region (rural vs metro), and admission source (private accommodation vs residential facility). Culture and language predicted ASCS admission rates in the univariate regression analyses, with ACSC admission rates increasing by 20 and 29% if English was not the preferred language or if an interpreter was required, respectively. Results from the multiple regression analysis confirmed that language was a significant predictor of ACSC admission rates.

CONCLUSIONS

Improved primary health care may help to reduce the most common causes of PPHs for people living with dementia, particularly for those from culturally and linguistically diverse backgrounds.

Are Smart Homes Adequate for Older Adults with Dementia?

Smart home technologies can enable older adults, including those with dementia, to live more independently in their homes for a longer time. Activity recognition, in combination with anomaly detection, has shown the potential to recognise users’ daily activities and detect deviations. However, activity recognition and anomaly detection are not sufficient, as they lack the capacity to capture the progression of patients’ habits across the different stages of dementia. To achieve this, smart homes should be enabled to recognise patients’ habits and changes in habits, including the loss of some habits. In this study, we first present an overview of the stages that characterise dementia, alongside real-world personas that depict users’ behaviours at each stage. Then, we survey the state of the art on activity recognition in smart homes for older adults with dementia, including the literature that combines activity recognition and anomaly detection. We categorise the literature based on goals, stages of dementia, and targeted users. Finally, we justify the necessity for habit recognition in smart homes for older adults with dementia, and we discuss the research challenges related to its implementation.

Applications and Outcomes of Internet of Things for Patients with Alzheimer’s Disease/Dementia: A Scoping Review

Objectives

We aimed to identify and classify the Internet of Things (IoT) technologies used for Alzheimer's disease (AD)/dementia as well as the healthcare aspects addressed by these technologies and the outcomes of the IoT interventions. Methodology. We searched PubMed/MEDLINE, IEEE Explore, Web of Science, OVID, Scopus, Embase, Cochrane, and Google Scholar. In total, 13,005 papers were reviewed, 36 of which were finally selected. All the reviews were independently carried out by two researchers. In the case of any disagreement, the problem was resolved by holding a meeting and exchanging views. Due to the diversity of the reviewed studies, narrative analysis was performed.

Results

Among the technologies used for the patients including radio frequency identification (RFID), near field communication (NFC), ZigBee, Bluetooth, global positioning system (GPS), sensors, and cameras, the sensors were employed in 36 studies, most of which were switch and vital sign monitoring sensors. The most common aspects of AD/dementia care monitored using these technologies were activities of daily living (ADLs) in 27 studies, followed by sleep patterns and disease diagnosis in 19 and 14 studies, respectively. Sleeping, medication, vital signs, agitation, memory, social interaction, apathy, movement, tracking, and fall were other aspects monitored by IoT. Then, their outcomes were reported.

Conclusion

Using IoT for AD/dementia provides many opportunities for considering various aspects of this disease. Moreover, the ability to use various technologies for gathering patient-related data provides a comprehensive application for almost all aspects of the patients' care with high accuracy.

Analysis of Relationship between Natural Standing Behavior of Elderly People and a Class of Standing Aids in a Living Space

As the world’s population ages, technology-based support for the elderly is becoming increasingly important. This study analyzes the relationship between natural standing behavior measured in a living space of elderly people and the classes of standing aids, as well as the physical and cognitive abilities contributing to household fall injury prevention. In total, 24 elderly standing behaviors from chairs, sofas, and nursing beds recorded in an RGB-D elderly behavior library were analyzed. The differences in standing behavior were analyzed by focusing on intrinsic and common standing aid characteristics among various seat types, including armrests of chairs or sofas and nursing bed handrails. The standing behaviors were categorized into two types: behaviors while leaning the trunk forward without using an armrest as a standing aid and those without leaning the trunk forward by using an arrest or handrail as a standing aid. The standing behavior clusters were distributed in a two-dimensional map based on the seat type rather than the physical or cognitive abilities. Therefore, to reduce the risk of falling, it would be necessary to implement a seat type that the elderly can unconsciously and naturally use as a standing aid even with impaired physical and cognitive abilities.

Prediction of Poststroke Urinary Tract Infection Risk in Immobile Patients Using Machine Learning: a observational cohort study

BACKGROUND

Urinary tract infection (UTI) is one of major nosocomial infections significantly affecting the outcomes of immobile stroke patients. Previous studies have identified several risk factors, but it's still challenging to accurately estimate personal UTI risk.

OBJECTIVES

We aimed to develop predictive models for UTI risk identification for immobile stroke patients.

METHODS

Research data were collected from our previous multi-centre study. Derivation cohort included 3982 immobile stroke patients collected from November 1, 2015 to June 30, 2016; external validation cohort included 3837 patients collected from November 1, 2016 to July 30, 2017. 6 machine learning models and an ensemble learning model were derived based on 80% of derivation cohort and effectiveness was evaluated with the remaining 20%. We used Shapley additive explanation values to determine feature importance and examine the clinical significance of prediction models.

RESULTS

2.59% (103/3982) patients were diagnosed with UTI in derivation cohort, 1.38% (53/3837) in external cohort. The ensemble learning model performed the best in area under the receiver operating characteristic (ROC) curve in internal validation (82.2%); second best in external validation (80.8%). In addition, the ensemble learning model performed the best sensitivity in both internal and external validation sets (80.9% and 81.1%, respectively). We also identified seven UTI risk factors (pneumonia, glucocorticoid use, female sex, mixed cerebrovascular disease, increased age, prolonged length of stay, and duration of catheterization).

CONCLUSIONS

Our ensemble learning model demonstrated promising performance. Future work should continue to develop a more concise scoring tool based on machine learning models and prospectively examining the model in practical use, thus improving clinical outcomes.

Smart Home Sensing and Monitoring in Households With Dementia: User-Centered Design Approach

Background

As life expectancy grows, so do the challenges of caring for an aging population. Older adults, including people with dementia, want to live independently and feel in control of their lives for as long as possible. Assistive technologies powered by artificial intelligence and internet of things devices are being proposed to provide living environments that support the users’ safety, psychological, and medical needs through remote monitoring and interventions.

Objective

This study investigates the functional, psychosocial, and environmental needs of people living with dementia, their caregivers, clinicians, and health and social care service providers toward the design and implementation of smart home systems.

Methods

We used an iterative user-centered design approach comprising 9 substudies. First, semistructured interviews (9 people with dementia, 9 caregivers, and 10 academic and clinical staff) and workshops (35 pairs of people with dementia and caregivers, and 12 health and social care clinicians) were conducted to define the needs of people with dementia, home caregivers, and professional stakeholders in both daily activities and technology-specific interactions. Then, the spectrum of needs identified was represented via patient–caregiver personas and discussed with stakeholders in a workshop (14 occupational therapists; 4 National Health Service pathway directors; and 6 researchers in occupational therapy, neuropsychiatry, and engineering) and 2 focus groups with managers of health care services (n=8), eliciting opportunities for innovative care technologies and public health strategies. Finally, these design opportunities were discussed in semistructured interviews with participants of a smart home trial involving environmental sensors, physiological measurement devices, smartwatches, and tablet-based chatbots and cognitive assessment puzzles (10 caregivers and 2 people with dementia). A thematic analysis revealed factors that motivate household members to use these technologies.

Results

Outcomes of these activities include a qualitative and quantitative analysis of patient, caregiver, and clinician needs and the identification of challenges and opportunities for the design and implementation of remote monitoring systems in public health pathways.

Conclusions

Participatory design methods supported the triangulation of stakeholder perspectives to aid the development of more patient-centered interventions and their translation to clinical practice and public health strategy. We discuss the implications and limitations of our findings, the value and the applicability of our methodology, and directions for future research.

Artificial intelligence and the future of life sciences

Over the past few decades, the number of health and 'omics-related data' generated and stored has grown exponentially. Patient information can be collected in real time and explored using various artificial intelligence (AI) tools in clinical trials; mobile devices can also be used to improve aspects of both the diagnosis and treatment of diseases. In addition, AI can be used in the development of new drugs or for drug repurposing, in faster diagnosis and more efficient treatment for various diseases, as well as to identify data-driven hypotheses for scientists. In this review, we discuss how AI is starting to revolutionize the life sciences sector.

Use of machine learning in geriatric clinical care for chronic diseases: a systematic literature review

Objectives

Geriatric clinical care is a multidisciplinary assessment designed to evaluate older patients’ (age 65 years and above) functional ability, physical health, and cognitive well-being. The majority of these patients suffer from multiple chronic conditions and require special attention. Recently, hospitals utilize various artificial intelligence (AI) systems to improve care for elderly patients. The purpose of this systematic literature review is to understand the current use of AI systems, particularly machine learning (ML), in geriatric clinical care for chronic diseases.

Materials and Methods

We restricted our search to eight databases, namely PubMed, WorldCat, MEDLINE, ProQuest, ScienceDirect, SpringerLink, Wiley, and ERIC, to analyze research articles published in English between January 2010 and June 2019. We focused on studies that used ML algorithms in the care of geriatrics patients with chronic conditions.

Results

We identified 35 eligible studies and classified in three groups: psychological disorder (n = 22), eye diseases (n = 6), and others (n = 7). This review identified the lack of standardized ML evaluation metrics and the need for data governance specific to health care applications.

Conclusion

More studies and ML standardization tailored to health care applications are required to confirm whether ML could aid in improving geriatric clinical care.

Artificial Intelligence-Powered Digital Health Platform and Wearable Devices Improve Outcomes for Older Adults in Assisted Living Communities: Pilot Intervention Study

BACKGROUND

Wearables and artificial intelligence (AI)-powered digital health platforms that utilize machine learning algorithms can autonomously measure a senior's change in activity and behavior and may be useful tools for proactive interventions that target modifiable risk factors.

OBJECTIVE

The goal of this study was to analyze how a wearable device and AI-powered digital health platform could provide improved health outcomes for older adults in assisted living communities.

METHODS

Data from 490 residents from six assisted living communities were analyzed retrospectively over 24 months. The intervention group (+CP) consisted of 3 communities that utilized CarePredict (n=256), and the control group (-CP) consisted of 3 communities (n=234) that did not utilize CarePredict. The following outcomes were measured and compared to baseline: hospitalization rate, fall rate, length of stay (LOS), and staff response time.

RESULTS

The residents of the +CP and -CP communities exhibit no statistical difference in age (P=.64), sex (P=.63), and staff service hours per resident (P=.94). The data show that the +CP communities exhibited a 39% lower hospitalization rate (P=.02), a 69% lower fall rate (P=.01), and a 67% greater length of stay (P=.03) than the -CP communities. The staff alert acknowledgment and reach resident times also improved in the +CP communities by 37% (P=.02) and 40% (P=.02), respectively.

CONCLUSIONS

The AI-powered digital health platform provides the community staff with actionable information regarding each resident's activities and behavior, which can be used to identify older adults that are at an increased risk for a health decline. Staff can use this data to intervene much earlier, protecting seniors from conditions that left untreated could result in hospitalization. In summary, the use of wearables and AI-powered digital health platform can contribute to improved health outcomes for seniors in assisted living communities. The accuracy of the system will be further validated in a larger trial.

Technology Solutions for Nurse Leaders

Over the next 10 years, the World Health Organization estimates that there will be global shortage of 18 000 000 health care workers. A perfect storm of an aging demographic, long-term drop in birth rate, and a retiring workforce has all the factors contributing to this impending crisis. In nursing, efforts to narrow the shortage gap through strategies that increase the number of admissions to nursing schools, such as increasing faculty members, clinical sites, preceptors, and scholarships, will likely not be enough to offset the shortfall. Solutions, in part, will be to make nurses more productive by reducing waste through the use of technology. This article evaluates how various types of technology such as electronic health records, data analytics, predictive modeling, artificial intelligence, speech recognition, natural language processing, robotics, the Internet of Things, and others can improve nurse productivity by using a Lean framework to eliminate waste and create value.

Proactive and Integrated Management and Empowerment in Parkinson's Disease: Designing a New Model of Care

Parkinson's disease is the second most common neurodegenerative condition after Alzheimer's disease. The number of patients will rise dramatically due to ageing of the population and possibly also due to environmental issues. It is widely recognised that the current models of care for people with Parkinson's disease or a form of atypical parkinsonism lack continuity, are reactive to problems rather than proactive, and do not adequately support individuals to self-manage. Integrated models of care have been developed for other chronic conditions, with a range of positive effects. A multidisciplinary team of professionals in the United Kingdom and the Netherlands, all with a long history of caring for patients with movement disorders, used knowledge of deficiencies with the current model of care, an understanding of integrated care in chronic disease and the process of logic modelling, to develop a novel approach to the care of patients with Parkinson's disease. We propose a new model, termed PRIME Parkinson (Proactive and Integrated Management and Empowerment in Parkinson's Disease), which is designed to manage problems proactively, deliver integrated, multidisciplinary care, and empower patients and their carers. It has five main components: (1) personalised care management, (2) education and empowerment of patients and carers, (3) empowerment of healthcare professionals, (4) a population health approach, and (5) support of the previous four components by patient- and professional-friendly technology. Having mapped the processes required for the success of this initiative, there is now a requirement to assess its effect on health-related and quality of life outcomes as well as determining its cost-effectiveness. In the next phase of the project, we will implement PRIME Parkinson in selected areas of the United Kingdom and the Netherlands.

FilterK: A new outlier detection method for k-means clustering of physical activity

In this paper, a new algorithm denoted as FilterK is proposed for improving the purity of k-means derived physical activity clusters by reducing outlier influence. We applied it to physical activity data obtained with body-worn accelerometers and clustered using k-means. We compared its performance with three existing outlier detection methods: Local Outlier Factor, Isolation Forests and KNN using the ground truth (class labels), average cluster and event purity (ACEP). FilterK provided comparable gains in ACEP (0.581 → 0.596 compared to 0.580-0.617) whilst removing a lower number of outliers than the other methods (4% total dataset size vs 10% to achieve this ACEP). The main focus of our new outlier detection method is to improve the cluster purities of physical activity accelerometer data, but we also suggest it may be potentially applied to other types of dataset captured by k-means clustering. We demonstrate our method using a k-means model trained on two independent accelerometer datasets (training n = 90) and re-applied to an independent dataset (test n = 41). Labelled physical activities include lying down, sitting, standing, household chores, walking (laboratory and non-laboratory based), stairs and running. This type of clustering algorithm could be used to assist with identifying optimal physical activity patterns for health.

A Biopsychosocial Model of Chronic Pain for Older Adults

Population

Comprehensive evaluation of chronic pain in older adults is multifaceted.

Objective and Methods

Research on chronic pain in older adults needs to be guided by sound conceptual models. The purpose of this paper is to describe an adaptation of the Biopsychosocial Model (BPS) of Chronic Pain for older adults. The extant literature was reviewed, and selected research findings that provide the empiric foundation for this adaptation of the BPS model of chronic pain are summarized. The paper concludes with a discussion of specific recommendations for how this adapted model can be used to guide future research.

Conclusions

This adaptation of the BPS model of chronic pain for older adults provides a comprehensive framework to guide future research in this vulnerable population.

Analysis of the microarray gene expression for breast cancer progression after the application modified logistic regression

Methods based around statistics and linear algebra have been increasingly used in attempts to address emerging questions in microarray literature. Microarray technology is a long-used tool in the global analysis of gene expression, allowing for the simultaneous investigation of hundreds or thousands of genes in a sample. It is characterized by a low sample size and a large feature number created a non-square matrix, and by the incomplete rank, that can generate countless more solution in classifiers. To avoid the problem of the 'curse of dimensionality' many authors have performed feature selection or reduced the size of data matrix. In this work, we introduce a new logistic regression-based model to classify breast cancer tumor samples based on microarray expression data, including all features of gene expression and without reducing the microarray data matrix. If the user still deems it necessary to perform feature reduction, it can be done after the application of the methodology, still maintaining a good classification. This methodology allowed the correct classification of breast cancer sample data sets from Gene Expression Omnibus (GEO) data series GSE65194, GSE20711, and GSE25055, which contain the microarray data of said breast cancer samples. Classification had a minimum performance of 80% (sensitivity and specificity), and explored all possible data combinations, including breast cancer subtypes. This methodology highlighted genes not yet studied in breast cancer, some of which have been observed in Gene Regulatory Networks (GRNs). In this work we examine the patterns and features of a GRN composed of transcription factors (TFs) in MCF-7 breast cancer cell lines, providing valuable information regarding breast cancer. In particular, some genes whose αi ∗ associated parameter values revealed extreme positive and negative values, and, as such, can be identified as breast cancer prediction genes. We indicate that the PKN2, MKL1, MED23, CUL5 and GLI genes demonstrate a tumor suppressor profile, and that the MTR, ITGA2B, TELO2, MRPL9, MTTL1, WIPI1, KLHL20, PI4KB, FOLR1 and SHC1 genes demonstrate an oncogenic profile. We propose that these may serve as potential breast cancer prediction genes, and should be prioritized for further clinical studies on breast cancer. This new model allows for the assignment of values to the αi ∗ parameters associated with gene expression. It was noted that some αi ∗ parameters are associated with genes previously described as breast cancer biomarkers, as well as other genes not yet studied in relation to this disease.