Artificial intelligence for multimodal data integration in oncology.
Cancer cell
In oncology, the patient state is characterized by a whole spectrum of modalities, ranging from radiology, histology, and genomics to electronic health records. Current artificial intelligence (AI) models operate mainly in the realm of a single modality, neglecting the broader clinical context, which inevitably diminishes their potential. Integration of different data modalities provides opportunities to increase robustness and accuracy of diagnostic and prognostic models, bringing AI closer to clinical practice. AI models are also capable of discovering novel patterns within and across modalities suitable for explaining differences in patient outcomes or treatment resistance. The insights gleaned from such models can guide exploration studies and contribute to the discovery of novel biomarkers and therapeutic targets. To support these advances, here we present a synopsis of AI methods and strategies for multimodal data fusion and association discovery. We outline approaches for AI interpretability and directions for AI-driven exploration through multimodal data interconnections. We examine challenges in clinical adoption and discuss emerging solutions.
10.1016/j.ccell.2022.09.012
The bioengineering of changing lifestyle and wearable technology: a mini review.
Geib Roy W,Swink Phil J,Vorel Alyssa J,Shepard Cynthia S,Gurovich Alvaro N,Waite Gabi N
Biomedical sciences instrumentation
Chronic diseases are a major health concern at the national and global level. According to the CDC, 86% of US health dollars go toward the treatment of chronic diseases. Many chronic diseases are manageable or preventable if individuals make appropriate lifestyle choices. Wearable technology both consumer and medical provides a unique opportunity to track lifestyle choices, such as increasing physical activity. It is estimated the market for consumer wearables will grow from $9.2 billion in 2014 to $30 billion by 2018. With such a potential market growth, it is important to understand the potential benefits and limitations of wearable technology to impact chronic disease management and prevention.
The Promise and Perils of Wearable Physiological Sensors for Diabetes Management.
Schwartz Frank L,Marling Cynthia R,Bunescu Razvan C
Journal of diabetes science and technology
Development of truly useful wearable physiologic monitoring devices for use in diabetes management is still in its infancy. From wearable activity monitors such as fitness trackers and smart watches to contact lenses measuring glucose levels in tears, we are just at the threshold of their coming use in medicine. Ultimately, such devices could help to improve the performance of sense-and-respond insulin pumps, illuminate the impact of physical activity on blood glucose levels, and improve patient safety. This is a summary of our experience attempting to use such devices to enhance continuous glucose monitoring-augmented insulin pump therapy. We discuss the current status and present difficulties with available devices, and review the potential for future use.
10.1177/1932296818763228
Estimating metabolic equivalents for activities in daily life using acceleration and heart rate in wearable devices.
Biomedical engineering online
BACKGROUND:Herein, an algorithm that can be used in wearable health monitoring devices to estimate metabolic equivalents (METs) based on physical activity intensity data, particularly for certain activities in daily life that make MET estimation difficult. RESULTS:Energy expenditure data were obtained from 42 volunteers using indirect calorimetry, triaxial accelerations and heart rates. The proposed algorithm used the percentage of heart rate reserve (%HRR) and the acceleration signal from the wearable device to divide the data into a middle-intensity group and a high-intensity group (HIG). The two groups were defined in terms of estimated METs. Evaluation results revealed that the classification accuracy for both groups was higher than 91%. To further facilitate MET estimation, five multiple-regression models using different features were evaluated via leave-one-out cross-validation. Using this approach, all models showed significant improvements in mean absolute percentage error (MAPE) of METs in the HIG, which included stair ascent, and the maximum reduction in MAPE for HIG was 24% compared to the previous model (HJA-750), which demonstrated a 70.7% improvement ratio. The most suitable model for our purpose that utilized heart rate and filtered synthetic acceleration was selected and its estimation error trend was confirmed. CONCLUSION:For HIG, the MAPE recalculated by the most suitable model was 10.5%. The improvement ratio was 71.6% as compared to the previous model (HJA-750C). This result was almost identical to that obtained from leave-one-out cross-validation. This proposed algorithm revealed an improvement in estimation accuracy for activities in daily life; in particular, the results included estimated values associated with stair ascent, which has been a difficult activity to evaluate so far.
10.1186/s12938-018-0532-2
Wearable and digital devices to monitor and treat metabolic diseases.
Nature metabolism
Cardiometabolic diseases are a major public-health concern owing to their increasing prevalence worldwide. These diseases are characterized by a high degree of interindividual variability with regards to symptoms, severity, complications and treatment responsiveness. Recent technological advances, and the growing availability of wearable and digital devices, are now making it feasible to profile individuals in ever-increasing depth. Such technologies are able to profile multiple health-related outcomes, including molecular, clinical and lifestyle changes. Nowadays, wearable devices allowing for continuous and longitudinal health screening outside the clinic can be used to monitor health and metabolic status from healthy individuals to patients at different stages of disease. Here we present an overview of the wearable and digital devices that are most relevant for cardiometabolic-disease-related readouts, and how the information collected from such devices could help deepen our understanding of metabolic diseases, improve their diagnosis, identify early disease markers and contribute to individualization of treatment and prevention plans.
10.1038/s42255-023-00778-y
Sleep disorders associated with primary mitochondrial diseases.
Ramezani Ryan J,Stacpoole Peter W
Journal of clinical sleep medicine : JCSM : official publication of the American Academy of Sleep Medicine
STUDY OBJECTIVES:Primary mitochondrial diseases are caused by heritable or spontaneous mutations in nuclear DNA or mitochondrial DNA. Such pathological mutations are relatively common in humans and may lead to neurological and neuromuscular complication that could compromise normal sleep behavior. To gain insight into the potential impact of primary mitochondrial disease and sleep pathology, we reviewed the relevant English language literature in which abnormal sleep was reported in association with a mitochondrial disease. DESIGN:We examined publication reported in Web of Science and PubMed from February 1976 through January 2014, and identified 54 patients with a proven or suspected primary mitochondrial disorder who were evaluated for sleep disturbances. MEASUREMENTS AND RESULTS:Both nuclear DNA and mitochondrial DNA mutations were associated with abnormal sleep patterns. Most subjects who underwent polysomnography had central sleep apnea, and only 5 patients had obstructive sleep apnea. Twenty-four patients showed decreased ventilatory drive in response to hypoxia and/ or hyperapnea that was not considered due to weakness of the intrinsic muscles of respiration. CONCLUSIONS:Sleep pathology may be an underreported complication of primary mitochondrial diseases. The probable underlying mechanism is cellular energy failure causing both central neurological and peripheral neuromuscular degenerative changes that commonly present as central sleep apnea and poor ventilatory response to hyperapnea. Increased recognition of the genetics and clinical manifestations of mitochondrial diseases by sleep researchers and clinicians is important in the evaluation and treatment of all patients with sleep disturbances. Prospective population-based studies are required to determine the true prevalence of mitochondrial energy failure in subjects with sleep disorders, and conversely, of individuals with primary mitochondrial diseases and sleep pathology.
10.5664/jcsm.4212
Metabolic consequences of sleep and circadian disorders.
Depner Christopher M,Stothard Ellen R,Wright Kenneth P
Current diabetes reports
Sleep and circadian rhythms modulate or control daily physiological patterns with importance for normal metabolic health. Sleep deficiencies associated with insufficient sleep schedules, insomnia with short-sleep duration, sleep apnea, narcolepsy, circadian misalignment, shift work, night eating syndrome, and sleep-related eating disorder may all contribute to metabolic dysregulation. Sleep deficiencies and circadian disruption associated with metabolic dysregulation may contribute to weight gain, obesity, and type 2 diabetes potentially by altering timing and amount of food intake, disrupting energy balance, inflammation, impairing glucose tolerance, and insulin sensitivity. Given the rapidly increasing prevalence of metabolic diseases, it is important to recognize the role of sleep and circadian disruption in the development, progression, and morbidity of metabolic disease. Some findings indicate sleep treatments and countermeasures improve metabolic health, but future clinical research investigating prevention and treatment of chronic metabolic disorders through treatment of sleep and circadian disruption is needed.
10.1007/s11892-014-0507-z
Obstructive Sleep Apnea Syndrome and Metabolic Diseases.
Li Min,Li Xiaoying,Lu Yan
Endocrinology
With the rapid changes in lifestyle in modern society, including the high nutritional intake and reduced physical activity, the incidence of metabolic diseases has been increasing year by year. Obstructive sleep apnea syndrome (OSAS) is a sleep disorder, usually characterized by sudden pauses of breathing during sleep and an interrupted sleep rhythm. Although the pathological mechanism remains poorly understood, it has been strongly associated with metabolic diseases, including obesity, insulin resistance, type 2 diabetes mellitus (T2DM), and nonalcoholic fatty liver disease (NAFLD). In the present mini-review, we briefly summarize the connections between OSAS, obesity, T2DM, and NAFLD, which might help us to better understand the pathogenesis of human diseases.
10.1210/en.2018-00248
Cardiovascular screening in low-income settings using a novel 4-lead smartphone-based electrocardiograph (D-Heart®).
Maurizi Niccolo',Faragli Alessandro,Imberti Jacopo,Briante Nicolò,Targetti Mattia,Baldini Katia,Sall Amadou,Cisse Abibou,Berzolari Francesca Gigli,Borrelli Paola,Avvantaggiato Fulvio,Perlini Stefano,Marchionni Niccolo',Cecchi Franco,Parigi Gianbattista,Olivotto Iacopo
International journal of cardiology
BACKGROUND:MHealth technologies are revolutionizing cardiovascular medicine. However, a low-cost, user-friendly smartphone-based electrocardiograph is still lacking. D-Heart® is a portable device that enables the acquisition of the ECG on multiple leads which streams via Bluetooth to any smartphone. Because of the potential impact of this technology in low-income settings, we determined the accuracy of D-Heart® tracings in the stratification of ECG morphological abnormalities, compared with 12-lead ECGs. METHODS:Consecutive African patients referred to the Ziguinchor Regional Hospital (Senegal) were enrolled (n=117; 69 males, age 39±11years). D-Heart® recordings (3 peripheral leads plus V5) were obtained immediately followed by 12 lead ECGs and were assessed blindly by 2 independent observers. Global burden of ECG abnormalities was defined by a semi-quantitative score based on the sum of 9 criteria, identifying four classes of increasing severity. RESULTS:D-Heart® and 12-lead ECG tracings were respectively classified as: normal: 72 (61%) vs 69 (59%); mildly abnormal: 42 (36%) vs 45 (38%); moderately abnormal: 3 (3%) vs 3 (3%). None had markedly abnormal tracings. Cohen's weighted kappa (k) test demonstrated a concordance of 0,952 (p<0,001, agreement 98,72%). Concordance was high as well for the Romhilt-Estes score (k=0,893; p<0,001 agreement 97,35%). PR and QRS intervals comparison with Bland-Altman method showed good accuracy for D-Heart® measurements (95% limit of agreement ±20ms for PR and ±10ms for QRS). CONCLUSIONS:D-Heart® proved effective and accurate stratification of ECG abnormalities comparable to the 12-lead electrocardiographs, thereby opening new perspectives for low-cost community cardiovascular screening programs in low-income settings.
10.1016/j.ijcard.2017.02.027
A Preliminary Study on Infrared Thermograph of Metabolic Syndrome.
Frontiers in endocrinology
Objective:To explore the temperature distribution characteristics of the face, palms, feet and the trunk area of metabolic syndrome (MS) through infrared thermography (IRT) and provide evidence for the application of IRT in the assistant evaluation of MS population. Methods:We collected thermographs of 184 participants (91 males, 93 females) and further divided participants of each gender into 4 groups according to the number of abnormal metabolic indexes. Mean temperatures of 6 Region of Interests (ROIs) (face, anterior trunk, bilateral palms and dorsum of feet) were calculated. Comparisons of the mean temperatures between genders, among groups and ROIs were carried out. Results:Male participants had higher mean temperature in their face, palms (<0.01) and dorsum of feet (<0.05), and lower mean temperature in the anterior trunk (<0.01). Female participants with MS had higher mean temperature in their palms and dorsum of feet (<0.01) and lower mean temperature in the anterior trunk (P<0.01) than normal participants. Similar tendencies were shown in the mean temperature of the left palms and trunk of MS males. With the increase of the number of abnormal metabolic indexes, it seems that the mean temperature gradually increased in palms and dorsum of feet, and decreased in the anterior trunk. Conclusion:The thermograph of MS exhibits certain characteristics. This may help reveal the correlations between Infrared thermography and metabolic disorders.
10.3389/fendo.2022.851369
Emerging evidence for the opposite role of circulating irisin levels and brown adipose tissue activity measured by infrared thermography in anthropometric and metabolic profile during childhood.
De Meneck Franciele,de Souza Livia Victorino,Brioschi Marcos Leal,Franco Maria do Carmo
Journal of thermal biology
Irisin is an adipomyokine that increases browning of adipose tissue and thermogenesis, thereby protecting against obesity and insulin resistance. However, the correlation between irisin, brown adipose tissue (BAT), and childhood obesity, as well as its association with an increased risk of developing metabolic diseases, has not been completely elucidated. This study aimed to investigate the association between irisin levels and BAT activity measured by infrared thermography among children and verify their correlation with anthropometric and metabolic parameters. This study included 42 children with normal weight and 18 overweight/obese children. Anthropometric data, irisin levels, lipid and glucose profile were evaluated. The percentage of the thermally active portion of the supraclavicular area (%Area) before and after a cold stimulus was measured by infrared thermography, and the differences between the percentages of thermally active (Δ%Area) was calculated as an index of BAT activation. The results were correlated with anthropometric and metabolic parameters. Circulating irisin levels was positive correlated with age (rho=0.327, P= 0.011), body mass index (BMI) (rho=0.707, P<0.001), waist circumference (rho=0.624, P<0.001), total cholesterol (rho=0.361, P=0.044), triglycerides (rho=0.419, P=0.001), and low-density lipoprotein cholesterol (LDLc) (rho=0.381, P= 0.003). Active BAT was negatively correlated with BMI, waist circumference, triglycerides, LDLc and irisin levels. We observed that normal weight children increased significantly the Δ% Area as compared to overweight/obese children. In conclusion, circulating irisin levels and BAT activity appear to have opposing roles, since normal weight children had greater BAT activity and lower circulating levels of irisin.
10.1016/j.jtherbio.2021.103010
An exploration of new methods for metabolic syndrome examination by infrared thermography and knowledge mining.
Scientific reports
Metabolic syndrome (MS) is a clinical syndrome with multiple metabolic disorders. As the diagnostic criteria for MS still lacking of imaging laboratory method, this study aimed to explore the differences between healthy people and MS patients through infrared thermography (IRT). However, the observation region of the IRT image is uncertain, and the research tried to solve this problem with the help of knowledge mining technology. 43 MS participants were randomly included through a cross-sectional method, and 43 healthy participants were recruited through number matching. The IRT image of each participant was segmented into the region of interest (ROI) through the preprocessing method proposed in this research, and then the ROI features were granulated by the K-means algorithm to generate the formal background, and finally, the two formal background were separately built into a knowledge graph through the knowledge mining method based on the attribute partial order structure. The baseline data shows that there is no difference in age, gender, and height between the two groups (P > 0.05). The image preprocessing method can segment the IRT image into 18 ROI. Through the K-means method, each group of data can be separately established with a 43 × 36 formal background and generated a knowledge graph. It can be found through knowledge mining and independent-samples T test that the average temperature and maximum temperature difference between the chest and face of the two groups are statistically different (P < 0.01). IRT could reflect the difference between healthy people and MS people. The measurement regions were found by the method of knowledge mining on the premise of unknown. The method proposed in this paper may add a new imaging method for MS laboratory examinations, and at the same time, through knowledge mining, it can also expand a new idea for clinical research of IRT.
10.1038/s41598-022-10422-6
Abdominal adiposity and cardiometabolic risk factors in children and adolescents: a Mendelian randomization analysis.
The American journal of clinical nutrition
BACKGROUND:Mendelian randomization studies in adults suggest that abdominal adiposity is causally associated with increased risk of type 2 diabetes and coronary artery disease in adults, but its causal effect on cardiometabolic risk in children remains unclear. OBJECTIVE:We aimed to study the causal relation of abdominal adiposity with cardiometabolic risk factors in children by applying Mendelian randomization. METHODS:We constructed a genetic risk score (GRS) using variants previously associated with waist-to-hip ratio adjusted for BMI (WHRadjBMI) and examined its associations with cardiometabolic factors by linear regression and Mendelian randomization in a meta-analysis of 6 cohorts, including 9895 European children and adolescents aged 3-17 y. RESULTS:WHRadjBMI GRS was associated with higher WHRadjBMI (β = 0.021 SD/allele; 95% CI: 0.016, 0.026 SD/allele; P = 3 × 10-15) and with unfavorable concentrations of blood lipids (higher LDL cholesterol: β = 0.006 SD/allele; 95% CI: 0.001, 0.011 SD/allele; P = 0.025; lower HDL cholesterol: β = -0.007 SD/allele; 95% CI: -0.012, -0.002 SD/allele; P = 0.009; higher triglycerides: β = 0.007 SD/allele; 95% CI: 0.002, 0.012 SD/allele; P = 0.006). No differences were detected between prepubertal and pubertal/postpubertal children. The WHRadjBMI GRS had a stronger association with fasting insulin in children and adolescents with overweight/obesity (β = 0.016 SD/allele; 95% CI: 0.001, 0.032 SD/allele; P = 0.037) than in those with normal weight (β = -0.002 SD/allele; 95% CI: -0.010, 0.006 SD/allele; P = 0.605) (P for difference = 0.034). In a 2-stage least-squares regression analysis, each genetically instrumented 1-SD increase in WHRadjBMI increased circulating triglycerides by 0.17 mmol/L (0.35 SD, P = 0.040), suggesting that the relation between abdominal adiposity and circulating triglycerides may be causal. CONCLUSIONS:Abdominal adiposity may have a causal, unfavorable effect on plasma triglycerides and potentially other cardiometabolic risk factors starting in childhood. The results highlight the importance of early weight management through healthy dietary habits and physically active lifestyle among children with a tendency for abdominal adiposity.
10.1093/ajcn/nqz187
Can the body mass index influence the skin temperature of adolescents assessed by infrared thermography?
Journal of thermal biology
Infrared thermography (IRT) is a technology that has been used as an auxiliary tool in the diagnostic process of several diseases and in sports monitoring to prevent injuries. However, the evaluation of a thermogram can be influenced by several factors that need to be understood and controlled to avoid a misinterpretation of the thermogram and, consequently, an inappropriate clinical action. Among the possible factors that can affect IRT are anthropometric factors, especially those related to body composition. Based on these, our objective was to verify the influence of Body Mass Index (BMI) on skin temperature (Tsk) in male adolescents. One hundred male adolescents (age: 16.83 ± 1.08 years; body mass: 66.51 ± 13.35 kg; height: 1.75 ± 7.04 m and BMI: 21.57 ± 4.06 kg/m) were evaluated and divided into three groups, based on the World Health Organization (WHO) proposed classification ranges: underweight (n = 33), normal weight (n = 34) and overweight/obesity (n = 34). Thermograms were obtained using the FLIR T420 thermal imager after a period of acclimatization of the subjects in a controlled environment (temperature: 21.3 ± 0.7 °C and humidity: 55.3 ± 2.2%); they were evaluated using the ThermoHuman® software, integrating the original regions of interest (ROI) into seven larger ROIs. The results showed that underweight individuals had higher Tsk values than normal weight and overweight/obese individuals for all evaluated ROIs, and overweight/obese individuals had lower Tsk values than normal weight individuals for most evaluated ROIs, except for arms region. BMI showed a correlation of -0.68 and -0.64 for the anterior and posterior regions of the trunk, respectively. Thermal normality tables were proposed for various ROIs according to BMI classification. Our study demonstrated that BMI can affect the Tsk values assessed by IRT and needs to be considered to interpret the thermograms.
10.1016/j.jtherbio.2022.103424
Obesity as a tumour development triggering factor.
Budny Agnieszka,Grochowski Cezary,Kozłowski Piotr,Kolak Agnieszka,Kamińska Marzena,Budny Bożena,Abramiuk Monika,Burdan Franciszek
Annals of agricultural and environmental medicine : AAEM
INTRODUCTION:The overweight and obesity epidemic represents a rapidly growing threat to the health of populations in an increasing number of countries. Nearly one-third of the world's population has excess adipose tissue. Nowadays, obesity occurrence is so common that it is replacing more traditional problems, such as an undernutrition and infectious diseases, as the most significant causes of ill health. If the current trend continues, almost half of the world's adult population will be overweight or obese by 2030. OBJECTIVE:The aim of this study is to show the connection between recent trends in body mass index, and the globally changing cancer profile. STATE OF KNOWLEDGE:A range of clinical and epidemiological studies have shown the relationship between excess body fat and the most frequently occurring malignancies. Obesity is associated with many cancers, such as: breast, colorectal, liver, lung, kidney, oesophageal, pancreatic, endometrium, ovarian, prostate, thyroid, and gallbladder cancer. CONCLUSIONS:In the light of this information, the study supports the claimed statement that obesity is one of the major health problems of the 21st century. Considering the increase in the number of obese people worldwide, it is necessary to develop a strategy allowing to prevent it. Fighting against unhealthy lifestyle in order to reduce overweight and obesity in society may have an essential impact on decreasing the number of incidences of cancer.
10.26444/aaem/100664
Aetiology of Type 2 diabetes in people with a 'normal' body mass index: testing the personal fat threshold hypothesis.
Clinical science (London, England : 1979)
Weight loss in overweight or obese individuals with Type 2 diabetes (T2D) can normalize hepatic fat metabolism, decrease fatty acid oversupply to β cells and restore normoglycaemia. One in six people has BMI <27 kg/m2 at diagnosis, and their T2D is assumed to have different aetiology. The Personal Fat Threshold hypothesis postulated differing individual thresholds for lipid overspill and adverse effects on β-cell function. To test this hypothesis, people with Type 2 diabetes and body mass index <27kg/m2 (n = 20) underwent repeated 5% weight loss cycles. Metabolic assessments were carried out at stable weight after each cycle and after 12 months. To determine how closely metabolic features returned to normal, 20 matched normoglycemic controls were studied once. Between baseline and 12 months: BMI fell (mean ± SD), 24.8 ± 0.4 to 22.5 ± 0.4 kg/m2 (P<0.0001) (controls: 21.5 ± 0.5); total body fat, 32.1 ± 1.5 to 27.6 ± 1.8% (P<0.0001) (24.6 ± 1.5). Liver fat content and fat export fell to normal as did fasting plasma insulin. Post-meal insulin secretion increased but remained subnormal. Sustained diabetes remission (HbA1c < 48 mmol/mol off all glucose-lowering agents) was achieved by 70% (14/20) by initial weight loss of 6.5 (5.5-10.2)%. Correction of concealed excess intra-hepatic fat reduced hepatic fat export, with recovery of β-cell function, glycaemic improvement in all and return to a non-diabetic metabolic state in the majority of this group with BMI <27 kg/m2 as previously demonstrated for overweight or obese groups. The data confirm the Personal Fat Threshold hypothesis: aetiology of Type 2 diabetes does not depend on BMI. This pathophysiological insight has major implications for management.
10.1042/CS20230586
Synchrotron-based FTIR microspectroscopy reveals DNA methylation profile in DNA-HALO structure.
Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy
Fourier transform infrared (FTIR) spectroscopy is a rapid, non-destructive and label-free technique for identifying subtle changes in all bio-macromolecules, and has been used as a method of choice for studying DNA conformation, secondary DNA structure transition and DNA damage. In addition, the specific level of chromatin complexity is introduced via epigenetic modifications forcing the technological upgrade in the analysis of such an intricacy. As the most studied epigenetic mechanism, DNA methylation is a major regulator of transcriptional activity, involved in the suppression of a broad spectrum of genes and its deregulation is involved in all non-communicable diseases. The present study was designed to explore the use of synchrotron-based FTIR analysis to monitor the subtle changes in molecule bases regarding the DNA methylation status of cytosine in the whole genome. In order to reveal the conformation-related best sample for FTIR-based DNA methylation analysis in situ, we used methodology for nuclear HALO preparations and slightly modified it to isolated DNA in HALO formations. Nuclear DNA-HALOs represent samples with preserved higher-order chromatin structure liberated of any protein residues that are closer to native DNA conformation than genomic DNA (gDNA) isolated by the standard batch procedure. Using FTIR spectroscopy we analyzed the DNA methylation profile of isolated gDNA and compared it with the DNA-HALOs. This study demonstrated the potential of FTIR microspectroscopy to detect DNA methylation marks in analyzed DNA-HALO specimens more precisely in comparison with classical DNA extraction procedures that yield unstructured whole genomic DNA. In addition, we used different cell types to assess their global DNA methylation profile, as well as defined specific infrared peaks that can be used for screening DNA methylation.
10.1016/j.saa.2023.123090
Experimental Verification of Objective Visual Fatigue Measurement Based on Accurate Pupil Detection of Infrared Eye Image and Multi-Feature Analysis.
Kim Taehyung,Lee Eui Chul
Sensors (Basel, Switzerland)
As the use of electronic displays increases rapidly, visual fatigue problems are also increasing. The subjective evaluation methods used for visual fatigue measurement have individual difference problems, while objective methods based on bio-signal measurement have problems regarding motion artifacts. Conventional eye image analysis-based visual fatigue measurement methods do not accurately characterize the complex changes in the appearance of the eye. To solve this problem, in this paper, an objective visual fatigue measurement method based on infrared eye image analysis is proposed. For accurate pupil detection, a convolutional neural network-based semantic segmentation method was used. Three features are calculated based on the pupil detection results: (1) pupil accommodation speed, (2) blink frequency, and (3) eye-closed duration. In order to verify the calculated features, differences in fatigue caused by changes in content color components such as gamma, color temperature, and brightness were compared with a reference video. The pupil detection accuracy was confirmed to be 96.63% based on the mean intersection over union. In addition, it was confirmed that all three features showed significant differences from the reference group; thus, it was verified that the proposed analysis method can be used for the objective measurement of visual fatigue.
10.3390/s20174814
Dry Electrode-Based Fully Isolated EEG/fNIRS Hybrid Brain-Monitoring System.
Lee Seungchan,Shin Younghak,Kumar Anil,Kim Minhee,Lee Heung-No
IEEE transactions on bio-medical engineering
A portable hybrid brain monitoring system is proposed to perform simultaneous 16-channel electroencephalogram (EEG) and 8-channel functional near-infrared spectroscopy (fNIRS) measurements. Architecture-optimized analog frontend integrated circuits (Texas Instruments ADS1299 and ADS8688A) were used to simultaneously achieve 24-bit EEG resolution and reliable latency-less (<0.85 μs) bio-optical measurements. Suppression of the noise and crosstalk generated by the digital circuit components and flashing NIR light sources was maximized through linear regulator-based fully isolated circuit design. Gel-less EEG measurements were enabled by using spring-loaded dry electrodes. Several evaluations were carried out by conducting an EEG phantom test and an arterial occlusion experiment. An alpha rhythm detection test (eye-closing task) and a mental arithmetic experiment (cumulative subtraction task) were conducted to determine whether the system is applicable to human subject studies. The evaluation results show that the proposed system is sufficiently capable of detecting microvoltage EEG signals and hemodynamic responses. The results of the studies on human subjects enabled us to verify that the proposed system is able to detect task-related EEG spectral features such as eye-closed event-related synchronization and mental-arithmetic event-related desynchronization in the alpha and beta rhythm ranges. An analysis of the fNIRS measurements with an arithmetic operation task also revealed a decreasing trend in oxyhemoglobin concentration.
10.1109/TBME.2018.2866550
Smart Patch for Skin Temperature: Preliminary Study to Evaluate Psychometrics and Feasibility.
Kim Heejung,Kim Sunkook,Lee Mingoo,Rhee Yumie,Lee Sungho,Jeong Yi-Rang,Kang Sunju,Naqi Muhammad,Hong Soyun
Sensors (Basel, Switzerland)
There is a need for continuous, non-invasive monitoring of biological data to assess health and wellbeing. Currently, many types of smart patches have been developed to continuously monitor body temperature, but few trials have been completed to evaluate psychometrics and feasibility for human subjects in real-life scenarios. The aim of this feasibility study was to evaluate the reliability, validity and usability of a smart patch measuring body temperature in healthy adults. The smart patch consisted of a fully integrated wearable wireless sensor with a multichannel temperature sensor, signal processing integrated circuit, wireless communication feature and a flexible battery. Thirty-five healthy adults were recruited for this test, carried out by wearing the patches on their upper chests for 24 h and checking their body temperature six times a day using infrared forehead thermometers as a gold standard for testing validity. Descriptive statistics, one-sampled and independent -tests, Pearson's correlation coefficients and Bland-Altman plot were examined for body temperatures between two measures. In addition, multiple linear regression, receiver operating characteristic (ROC) and qualitative content analysis were conducted. Among the 35 participants, 29 of them wore the patch for over 19 h (dropout rate: 17.14%). Mean body temperature measured by infrared forehead thermometers and smart patch ranged between 32.53 and 38.2 °C per person and were moderately correlated (r = 0.23-0.43) overall. Based on a Bland-Altman plot, approximately 94% of the measurements were located within one standard deviation (upper limit = 4.52, lower limit = -5.82). Most outliers were identified on the first measurement and were located below the lower limit. It is appropriate to use 37.5 °C in infrared forehead temperature as a cutoff to define febrile conditions. Users' position while checking and ambient temperature and humidity are not affected to the smart patch body temperature. Overall, the participants showed high usability and satisfaction on the survey. Few participants reported discomfort due to limited daily activity, itchy skin or detaching concerns. In conclusion, epidermal electronic sensor technologies provide a promising method for continuously monitoring individuals' body temperatures, even in real-life situations. Our study findings show the potential for smart patches to monitoring non-febrile condition in the community.
10.3390/s21051855