Development of novel low-cost readout electronics for large field-of-view gamma camera detectors.

PURPOSE: Large scintillation crystals-based gamma cameras play a crucial role in nuclear medicine imaging. In this study, a large field-of-view (FOV) gamma detector consisting of 48 square PMTs developed using a new readout electronics, reducing 48 (6 × 8) analog signals to 14 (6 + 8) analog sums of each row and column, with reduced complexity and cost while preserving image quality. METHODS: All 14 analog signals were converted to digital signals using AD9257 high-speed analog to digital (ADC) converters driven by the SPARTAN-6 family of field-programmable gate arrays (FPGA) in order to calculate the signal integrals. The positioning algorithm was based on the digital correlated signal enhancement (CSE) algorithm implemented in the acquisition software. The performance characteristics of the developed gamma camera were measured using the NEMA NU 1-2018 standards. RESULTS: The measured energy resolution of the developed detector was 8.7 % at 140 keV, with an intrinsic spatial resolution of 3.9 mm. The uniformity was within 0.6 %, while the linearity was within 0.1 %. CONCLUSION: The performance evaluation demonstrated that the developed detector has suitable specifications for high-end nuclear medicine imaging.

Development and internal validation of a dynamic fall risk prediction and monitoring tool in aged care using routinely collected electronic health data: a landmarking approach.

OBJECTIVES: Falls pose a significant challenge in residential aged care facilities (RACFs). Existing falls prediction tools perform poorly and fail to capture evolving risk factors. We aimed to develop and internally validate dynamic fall risk prediction models and create point-based scoring systems for residents with and without dementia. MATERIALS AND METHODS: A longitudinal cohort study using electronic data from 27 RACFs in Sydney, Australia. The study included 5492 permanent residents, with a 70%-30% split for training and validation. The outcome measure was the incidence of falls. We tracked residents for 60 months, using monthly landmarks with 1-month prediction windows. We employed landmarking dynamic prediction for model development, a time-dependent area under receiver operating characteristics curve (AUROCC) for model evaluations, and a regression coefficient approach to create point-based scoring systems. RESULTS: The model identified 15 independent predictors of falls in dementia and 12 in nondementia cohorts. Falls history was the key predictor of subsequent falls in both dementia (HR 4.75, 95% CI, 4.45-5.06) and nondementia cohorts (HR 4.20, 95% CI, 3.87-4.57). The AUROCC across landmarks ranged from 0.67 to 0.87 for dementia and from 0.66 to 0.86 for nondementia cohorts but generally remained between 0.75 and 0.85 in both cohorts. The total point risk score ranged from -2 to 57 for dementia and 0 to 52 for nondementia cohorts. DISCUSSION: Our novel risk prediction models and scoring systems provide timely person-centered information for continuous monitoring of fall risk in RACFs. CONCLUSION: Embedding these tools within electronic health records could facilitate the implementation of targeted proactive interventions to prevent falls.

Electrochemical Doping Effect on the Conductivity of Melanin-Inspired Materials.

Eumelanin is a natural pigment that can be particularly valuable for sustainable bioelectronic devices due to its inherent biocompatibility and hydration-dependent conductivity. However, the low conductivity of eumelanin limits its technological development. In this research, electrochemical doping was proposed as an alternative route to increase the electronic conductivity of synthetic eumelanin derivatives. Thin films of sulfonated eumelanin were deposited on platinum interdigitated electrodes and electrochemically treated by using cyclic voltammetry and chronoamperometry treatments. X-ray photoelectron spectroscopy analysis confirmed ion doping in sulfonated melanin. Current-voltage, current-time, and electrochemical impedance measurements were used to investigate the effect of different aqueous electrolytes (including KCl and LiClO4) treatments on the charge transport of sulfonated eumelanin. We show that the conductivity depends on the type and size of the anion used and can reach 10-3 S·cm-1. Additionally, depending on the electrolyte, there is a change in charge transport from mixed ionic/electronic to a predominantly electronic-only conduction. Our results show that the chemical nature of the ion plays an important role in the electrochemical doping and, consequently, in the charge transport of eumelanin. These insights serve as inspiration to explore the use of alternative electrolytes with different compositions further and develop eumelanin-based devices with tunable conductivities.

An Analysis of Incident Reports Related to Electronic Medication Management: How They Change Over Time.

OBJECTIVE: Electronic medication management (EMM) systems have been shown to introduce new patient safety risks that were not possible, or unlikely to occur, with the use of paper charts. Our aim was to examine the factors that contribute to EMM-related incidents and how these incidents change over time with ongoing EMM use. METHODS: Incidents reported at 3 hospitals between January 1, 2010, and December 31, 2019, were extracted using a keyword search and then screened to identify EMM-related reports. Data contained in EMM-related incident reports were then classified as unsafe acts made by users and the latent conditions contributing to each incident. RESULTS: In our sample, 444 incident reports were determined to be EMM related. Commission errors were the most frequent unsafe act reported by users (n = 298), whereas workarounds were reported in only 13 reports. User latent conditions (n = 207) were described in the highest number of incident reports, followed by conditions related to the organization (n = 200) and EMM design (n = 184). Over time, user unfamiliarity with the system remained a key contributor to reported incidents. Although fewer articles to electronic transfer errors were reported over time, incident reports related to the transfer of information between different computerized systems increased as hospitals adopted more clinical information systems. CONCLUSIONS: Electronic medication management-related incidents continue to occur years after EMM implementation and are driven by design, user, and organizational conditions. Although factors contribute to reported incidents in varying degrees over time, some factors are persistent and highlight the importance of continuously improving the EMM system and its use.

The BLISTER Score: A Novel, Externally Validated Tool for Predicting Cardiac Implantable Electronic Device Infections, and Its Cost-Utility Implications for Antimicrobial Envelope Use.

BACKGROUND: Antimicrobial envelopes reduce the incidence of cardiac implantable electronic device infections, but their cost restricts routine use in the United Kingdom. Risk scoring could help to identify which patients would most benefit from this technology. METHODS: A novel risk score (BLISTER [Blood results, Long procedure time, Immunosuppressed, Sixty years old (or younger), Type of procedure, Early re-intervention, Repeat procedure]) was derived from multivariate analysis of factors associated with cardiac implantable electronic device infection. Diagnostic utility was assessed against the existing PADIT score (Prior procedure, Age, Depressed renal function, Immunocompromised, Type of procedure) in both standard and high-risk external validation cohorts, and cost-utility models examined different BLISTER and PADIT score thresholds for TYRX (Medtronic; Minneapolis, MN) antimicrobial envelope allocation. RESULTS: In a derivation cohort (n=7383), cardiac implantable electronic device infection occurred in 59 individuals within 12 months of a procedure (event rate, 0.8%). In addition to the PADIT score constituents, lead extraction (hazard ratio, 3.3 [95% CI, 1.9-6.1]; P<0.0001), C-reactive protein >50 mg/L (hazard ratio, 3.0 [95% CI, 1.4-6.4]; P=0.005), reintervention within 2 years (hazard ratio, 10.1 [95% CI, 5.6-17.9]; P<0.0001), and top-quartile procedure duration (hazard ratio, 2.6 [95% CI, 1.6-4.1]; P=0.001) were independent predictors of infection. The BLISTER score demonstrated superior discriminative performance versus PADIT in the standard risk (n=2854, event rate: 0.8%, area under the curve, 0.82 versus 0.71; P=0.001) and high-risk validation cohorts (n=1961, event rate: 2.0%, area under the curve, 0.77 versus 0.69; P=0.001), and in all patients (n=12 198, event rate: 1%, area under the curve, 0.8 versus 0.75, P=0.002). In decision-analytic modeling, the optimum scenario assigned antimicrobial envelopes to patients with BLISTER scores ≥6 (10.8%), delivering a significant reduction in infections (relative risk reduction, 30%; P=0.036) within the National Institute for Health and Care Excellence cost-utility thresholds (incremental cost-effectiveness ratio, £18 446). CONCLUSIONS: The BLISTER score (https://qxmd.com/calculate/calculator_876/the-blister-score-for-cied-infection) was a valid predictor of cardiac implantable electronic device infection, and could facilitate cost-effective antimicrobial envelope allocation to high-risk patients.

The Economics of Medication Safety: A Cost-Benefits Analysis Framework for Evaluating an Electronic Medication System.

Medication prescribing in paediatrics is complex and compounded by the need to provide age and weight related doses, and errors continue to be problematic. Electronic medication systems (EMS) can reduce errors through dosing calculators and computerised decision support. However, evidence on costs and benefits of these systems is limited, particularly in paediatric hospitals. This paper presents the development of a cost-benefit analysis (CBA) framework to assess the impact of an EMS implementation in a paediatric tertiary hospital. An innovative component of the framework is the incorporation of the impact of the effects of the EMS for both the health system as well as for patients and their wider family networks, allowing a net social benefit assessment. We describe the impact of non-clinical out-of-pocket costs of admission and use discrete choice experiments to measure both medication related harm and the importance of medication safety to families and members of the community.

Patients' Experiences of Demanded Access to Online Health Records.

Patient-Accessible Electronic Health Records (PAEHR) is particularly controversial in mental healthcare. We aim to explore if there is any association between patients with mental health conditions and the experience of someone demanding access to their PAEHR. A chi-square test showed a significant association between group belonging and experiences of someone demanding access to the PAEHR.

A Narrative Review of Sociodemographic Disparities in Relation to PEHR Access.

Personal electronic health records (PEHRs) enable patients access to their own medical records. Differences in access and use of PEHRs may create health disparities. We conducted a narrative literature review regarding the effects of race, language preference, education, income, and homelessness on PEHR usage as well as PEHRs content, particularly stigmatizing language. Of 3177 citations found, 75 articles were relevant. Patient race, language, income, and education predicted PEHR use, which could potentially exacerbate health disparities.

Evolutionary game analysis of multi-stakeholders in the WEEE recycling industry under propaganda subsidies and environmental damage taxes.

With an increase in the amount of waste electrical and electronic equipment (WEEE), the waste of resources and environmental hazards caused by WEEE cannot be ignored. Meanwhile, the lack of environmental awareness among consumers and the existence of informal recyclers pose a great challenge to the government in governing the WEEE recycling industry. This study constructs a tripartite evolutionary game model consisting of the government and formal and informal recyclers. Then, the payoff matrix, replicator dynamic equations and all the equilibrium points are obtained, and a stability analysis of the equilibrium points is performed to derive the evolutionary stability strategies (ESSs) and their formation conditions. Finally, the influence of important parameters on the WEEE recycling industry is examined through numerical analysis. The results suggest that the government cannot ignore the existence of informal recyclers but should take governance measures to intervene in informal recycling and guide such recyclers to upgrade their processing technology. Moreover, the willingness of informal recyclers to invest in processing technology increases with the increase in environmental damage taxes. Second, the government should provide formal recyclers with appropriate promotional subsidies. Third, the government should control its own cost of governance and reduce its financial burden. Fourth, with government subsidies, formal recyclers should decide whether to make promotional investments based on the investment cost and the sum of the benefits from the investment and government subsidy. Finally, under government tax pressure and the influence of formal recyclers' promotional investments, informal recyclers should actively invest in processing technology.

Driving sustainable circular economy in electronics: A comprehensive review on environmental life cycle assessment of e-waste recycling.

E-waste, encompassing discarded materials from outdated electronic equipment, often ends up intermixed with municipal solid waste, leading to improper disposal through burial and incineration. This improper handling releases hazardous substances into water, soil, and air, posing significant risks to ecosystems and human health, ultimately entering the food chain and water supply. Formal e-waste recycling, guided by circular economy models and zero-discharge principles, offers potential solutions to this critical challenge. However, implementing a circular economy for e-waste management due to chemical and energy consumption may cause environmental impacts. Consequently, advanced sustainability assessment tools, such as Life Cycle Assessment (LCA), have been applied to investigate e-waste management strategies. While LCA is a standardized methodology, researchers have employed various routes for environmental assessment of different e-waste management methods. However, to the authors' knowledge, there lacks a comprehensive study focusing on LCA studies to discern the opportunities and limitations of this method in formal e-waste management strategies. Hence, this review aims to survey the existing literature on the LCA of e-waste management under a circular economy, shedding light on the current state of research, identifying research gaps, and proposing future research directions. It first explains various methods of managing e-waste in the circular economy. This review then evaluates and scrutinizes the LCA approach in implementing the circular bioeconomy for e-waste management. Finally, it proposes frameworks and procedures to enhance the applicability of the LCA method to future e-waste management research. The literature on the LCA of e-waste management reveals a wide variation in implementing LCA in formal e-waste management, resulting in diverse results and findings in this field. This paper underscores that LCA can pinpoint the environmental hotspots for various pathways of formal e-waste recycling, particularly focusing on metals. It can help address these concerns and achieve greater sustainability in e-waste recycling, especially in pyrometallurgical and hydrometallurgical pathways. The recovery of high-value metals is more environmentally justified compared to other metals. However, biometallurgical pathways remain limited in terms of environmental studies. Despite the potential for recycling e-waste into plastic or glass, there is a dearth of robust background in LCA studies within this sector. This review concludes that LCA can offer valuable insights for decision-making and policy processes on e-waste management, promoting environmentally sound e-waste recycling practices. However, the accuracy of LCA results in e-waste recycling, owing to data requirements, subjectivity, impact category weighting, and other factors, remains debatable, emphasizing the need for more uncertainty analysis in this field.

A Roadmap from Functional Materials to Plant Health Monitoring (PHM).

Soft bioelectronics have great potential for the early diagnosis of plant diseases and the mitigation of adverse outcomes such as reduced crop yields and stunted growth. Over the past decade, bioelectronic interfaces have evolved into miniaturized conformal electronic devices that integrate flexible monitoring systems with advanced electronic functionality. This development is largely attributable to advances in materials science, and micro/nanofabrication technology. The approach uses the mechanical and electronic properties of functional materials (polymer substrates and sensing elements) to create interfaces for plant monitoring. In addition to ensuring biocompatibility, several other factors need to be considered when developing these interfaces. These include the choice of materials, fabrication techniques, precision, electrical performance, and mechanical stability. In this review, some of the benefits plants can derive from several of the materials used to develop soft bioelectronic interfaces are discussed. The article describes how they can be used to create biocompatible monitoring devices that can enhance plant growth and health. Evaluation of these devices also takes into account features that ensure their long-term durability, sensitivity, and reliability. This article concludes with a discussion of the development of reliable soft bioelectronic systems for plants, which has the potential to advance the field of bioelectronics.

Implantable Flexible Sensors for Health Monitoring.

Flexible sensors, as a significant component of flexible electronics, have attracted great interest the realms of human-computer interaction and health monitoring due to their high conformability, adjustable sensitivity, and excellent durability. In comparison to wearable sensor-based in vitro health monitoring, the use of implantable flexible sensors (IFSs) for in vivo health monitoring offers more accurate and reliable vital sign information due to their ability to adapt and directly integrate with human tissue. IFSs show tremendous promise in the field of health monitoring, with unique advantages such as robust signal reading capabilities, lightweight design, flexibility, and biocompatibility. Herein, a review of IFSs for vital signs monitoring is detailly provided, highlighting the essential conditions for in vivo applications. As the prerequisites of IFSs, the stretchability and wireless self-powered properties of the sensor are discussed, with a special attention paid to the sensing materials which can maintain prominent biosafety (i.e., biocompatibility, biodegradability, bioresorbability). Furthermore, the applications of IFSs monitoring various parts of the body are described in detail, with a summary in brain monitoring, eye monitoring, and blood monitoring. Finally, the challenges as well as opportunities in the development of next-generation IFSs are presented.

Circular economy through waste reverse logistics under extended producer responsibility in Finland.

Extended producer responsibility (EPR) is commonly implemented as a strategy in waste management. The core of the concept itself is a waste reverse logistics (WRL), which dictates how the collection, inspection and processing of end-of-life products are performed. Existing studies of EPR mainly focused on single products instead of using broader perspective on national level. Its contribution towards circular economy through slowing and closing the loops also has not been widely discussed. This study examined the system architecture of the policy instruments used in the EPR and the similarities of the WRL networks across different products. A case study was used to investigate six products: portable batteries and accumulators, paper, packaging, vehicles, electrical and electronic equipment (EEE) and tyres. The study generated a WRL framework. It is also observed that closing the loop through recycling is the primary circular strategy and is found in all products, whereas closing and slowing the loop strategy through reuse/repair, remanufacture and repurposing is found in packaging, tyres, vehicles and EEE. This study shows that EPR can close the material loop, although improvement in design for the environment is necessary. It creates challenges and opportunities for the government, producer responsibility organization and producers to improve existing conditions by implementing new initiatives such as design for the environment indicators, standardization, tax and subsidy systems and tariffs for disposal fees.

Validation of the Spanish version of the Electronic Facial Palsy Assessment (eFACE).

PURPOSE: The clinician-graded electronic facial paralysis assessment (eFACE) is a relatively new digital tool for assessing facial palsy. The present study aimed to determine the validity and reliability of the Spanish version of the eFACE. METHODS: Forward-backward translation from the original English version was performed. Videos and photographs from 65 adult patients with unilateral facial paralysis (any severity, time course, and etiology) were evaluated twice by five otolaryngologists with varying levels of experience in facial palsy evaluation. Internal consistency was measured using Cronbach's α and the intra- and inter-rater reliability were measured using intraclass correlation coefficient. Concurrent validity was established by calculating Spearman's rho correlation (ρ) between the eFACE and the House-Brackmann scale (H-B) and Pearson's correlation (r) between the eFACE and the Sunnybrook Facial Grading System (SFGS). RESULTS: The Spanish version of the eFACE showed good internal consistency (Cronbach's α > 0.8). The intra-rater reliability was nearly perfect for the total score (intraclass correlation coefficient: 0.95-0.99), static score (0.92-0.96), and dynamic score (0.96-0.99) and important-to-excellent for synkinesis score (0.79-0.96). The inter-rater reliability was excellent for the total score (0.85-0.93), static score (0.80-0.90), and dynamic score (0.90-0.95) and moderate-to-important for the synkinesis score (0.55-0.78). The eFACE had a very strong correlation with the H-B (ρ = - 0.88 and - 0.85 for each evaluation, p < 0.001) and the SFGS (r = 0.92 and 0.91 each evaluation, p < 0.001). CONCLUSION: The Spanish version of the eFACE is a reliable and valid instrument for assessment of facial function in the diagnosis and treatment of patients with facial paralysis.

Unconstrained Piezoelectric Vascular Electronics for Wireless Monitoring of Hemodynamics and Cardiovascular Health.

The patient-centered healthcare requires timely disease diagnosis and prognostic assessment, calling for individualized physiological monitoring. To assess the postoperative hemodynamic status of patients, implantable blood flow monitoring devices are highly expected to deliver real time, long-term, sensitive, and reliable hemodynamic signals, which can accurately reflect multiple physiological conditions. Herein, an implantable and unconstrained vascular electronic system based on a piezoelectric sensor immobilized is presented by a "growable" sheath around continuously growing arterial vessels for real-timely and wirelessly monitoring of hemodynamics. The piezoelectric sensor made of circumferentially aligned polyvinylidene fluoride nanofibers around pulsating artery can sensitively perceive mechanical signals, and the growable sheath bioinspired by the structure and function of leaf sheath has elasticity and conformal shape adaptive to the dynamically growing arterial vessels to avoid growth constriction. With this integrated and smart design, long-term, wireless, and sensitive monitoring of hemodynamics are achieved and demonstrated in rats and rabbits. It provides a simple and versatile strategy for designing implantable sensors in a less invasive way.

Electrochemical sensing fibers for wearable health monitoring devices.

Real-time monitoring of health conditions is an emerging strong issue in health care, internet information, and other strongly evolving areas. Wearable electronics are versatile platforms for non-invasive sensing. Among a variety of wearable device principles, fiber electronics represent cutting-edge development of flexible electronics. Enabled by electrochemical sensing, fiber electronics have found a wide range of applications, providing new opportunities for real-time monitoring of health conditions by daily wearing, and electrochemical fiber sensors as explored in the present report are a promising emerging field. In consideration of the key challenges and corresponding solutions for electrochemical sensing fibers, we offer here a timely and comprehensive review. We discuss the principles and advantages of electrochemical sensing fibers and fabrics. Our review also highlights the importance of electrochemical sensing fibers in the fabrication of "smart" fabric designs, focusing on strategies to address key issues in fiber-based electrochemical sensors, and we provide an overview of smart clothing systems and their cutting-edge applications in therapeutic care. Our report offers a comprehensive overview of current developments in electrochemical sensing fibers to researchers in the fields of wearables, flexible electronics, and electrochemical sensing, stimulating forthcoming development of next-generation "smart" fabrics-based electrochemical sensing.

Evaluation of a Clinic-Based, Electronic Social Determinants of Health Screening and Intervention in Primary Care Pediatrics.

OBJECTIVE: Social determinants of health (SDOH) significantly affect individuals' health outcomes, yet universal electronic SDOH screening is not standard in primary care. Our study explores the implementation of an electronic SDOH screening in the electronic health record (EHR) and follow-up intervention among primary care pediatric patients within an academic clinic. METHODS: Beginning in August of 2022, patients and their families determined to have at least one SDOH need qualified for an in-clinic referral to a coordinated care team member. We assessed the overall efficacy and feasibility of the implementation. RESULTS: Over the 4-month pilot, 1473 of 2064 (71.4%) eligible patients were screened, with 472 (32%) patients screening positive on at least one SDOH domain. Of the 472 screened positive, 48 (10.2%) declined a referral. Two hundred and forty-seven of the 424 (58.3%) received a referral to a care coordination team member. CONCLUSIONS: This study demonstrates the feasibility of a universal electronic SDOH screening tool within the EHR within an urban, academic-based clinic.

A Discolorable Flexible Synaptic Transistor for Wearable Health Monitoring.

Multifunctional intelligent wearable electronics, providing integrated physiological signal analysis, storage, and display for real-time and on-site health status diagnosis, have great potential to revolutionize health monitoring technologies. Advanced wearable systems combine isolated digital processor, memory, and display modules for function integration; however, they suffer from compatibility and reliability issues. Here, we introduce a flexible multifunctional electrolyte-gated transistor (EGT) that integrates synaptic learning, memory, and autonomous discoloration functionalities for intelligent wearable application. This device exhibits synergistic light absorption coefficient changes during voltage-gated ion doping that modulate the electrical conductance changes for synaptic function implementation. By adaptively changing color, the EGT can differentiate voltage pulse inputs with different frequency, amplitude, and duration parameters, exhibiting excellent reversibility and reliability. We developed a smart wearable monitoring system that incorporates EGT devices and sensors for respiratory and electrocardiogram signal analysis, providing health warnings through real-time and on-site discoloration. This study represents a significant step toward smart wearable technologies for health management, offering health evaluation through intelligent displays.

Toward an Interdisciplinary Approach to Constructing Care Delivery Pathways From Electronic Health Care Databases to Support Integrated Care in Chronic Conditions: Systematic Review of Quantification and Visualization Methods.

BACKGROUND: Electronic health care databases are increasingly used for informing clinical decision-making. In long-term care, linking and accessing information on health care delivered by different providers could improve coordination and health outcomes. Several methods for quantifying and visualizing this information into data-driven care delivery pathways (CDPs) have been proposed. To be integrated effectively and sustainably into routine care, these methods need to meet a range of prerequisites covering 3 broad domains: clinical, technological, and behavioral. Although advances have been made, development to date lacks a comprehensive interdisciplinary approach. As the field expands, it would benefit from developing common standards of development and reporting that integrate clinical, technological, and behavioral aspects. OBJECTIVE: We aimed to describe the content and development of long-term CDP quantification and visualization methods and to propose recommendations for future work. METHODS: We conducted a systematic review following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) recommendations. We searched peer-reviewed publications in English and reported the CDP methods by using the following data in the included studies: long-term care data and extracted data on clinical information and aims, technological development and characteristics, and user behaviors. The data are summarized in tables and presented narratively. RESULTS: Of the 2921 records identified, 14 studies were included, of which 13 (93%) were descriptive reports and 1 (7%) was a validation study. Clinical aims focused primarily on treatment decision-making (n=6, 43%) and care coordination (n=7, 50%). Technological development followed a similar process from scope definition to tool validation, with various levels of detail in reporting. User behaviors (n=3, 21%) referred to accessing CDPs, planning care, adjusting treatment, or supporting adherence. CONCLUSIONS: The use of electronic health care databases for quantifying and visualizing CDPs in long-term care is an emerging field. Detailed and standardized reporting of clinical and technological aspects is needed. Early consideration of how CDPs would be used, validated, and implemented in clinical practice would likely facilitate further development and adoption. TRIAL REGISTRATION: PROSPERO CRD42019140494; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=140494. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.1136/bmjopen-2019-033573.

Fatigue Assessment from Facial Videos using Deep Neural Networks and Engineered Features Informed by Domain Knowledge.

Fatigue impairs cognitive and motor function, potentially leading to mishaps in high-pressure occupations such as aviation and emergency medical services. The current approach is primarily based on self-assessment, which is subjective and error-prone. An objective method is needed to detect severe and likely dangerous levels of fatigue quickly and accurately. Here, we present a quantitative evaluation tool that uses less than two minutes of facial video, captured using an iPad, to assess fatigue vs. alertness. The tool is fast, easy to use, and scalable since it uses cameras readily available on consumer-electronic devices. We compared the classification performance between a Long Short-Term Memory (LSTM) deep neural network and a Random Forest (RF) classifier applied to engineered features informed by domain knowledge. The preliminary results on an 11-subject dataset show that RF outperforms LSTM, with added interpretability on the features used. For the RF classifiers, the average areas under the receiver operating characteristic curve, based on the 11-fold and individualized 11-fold cross validations, are 0.72 ± 0.16 and 0.8 ± 0.12, respectively. Equal error rates are 0.34 and 0.26, respectively. This study presents a promising approach for rapid fatigue detection. Additional data will be collected to assess the generalizability across populations.