Association of Depression With Myocardial Infarction With Non-obstructive Coronary Arteries: A Systematic Review.

This systematic review examined the association between depression and myocardial infarction with non-obstructive coronary arteries (MINOCA). A comprehensive literature search was conducted using electronic databases, resulting in the inclusion of six small case-control and cohort studies reported from Spain, Australia, China, and Pakistan. The studies included various study designs, such as cohort studies, case-control studies, and prospective cohort studies. The results of the systematic review indicate a significant association between depression and MINOCA. Several studies reported a higher prevalence of depression among MINOCA patients compared to those with obstructive coronary artery disease. Additionally, depression was found to be associated with worse outcomes in MINOCA patients, including increased cardiovascular events, all-cause mortality, and reduced quality of life. Some studies suggest that psychological factors, such as chronic stress, inflammation, and altered sympathetic nervous system activity, may play a role in the development and progression of MINOCA in individuals with depression. The findings highlight the importance of considering depression as a potential risk factor and prognostic marker in MINOCA patients. Early identification and management of depression in these individuals may improve outcomes and quality of life. A multi-center randomized controlled trial is needed to better understand the underlying mechanisms and to develop targeted interventions for individuals with depression and MINOCA.

Enabling biomedical technologies for chronic myelogenous leukemia (CML) biomarkers detection.

Chronic myelogenous/myeloid leukemia (CML) is a type of cancer of bone marrow that arises from hematopoietic stem cells and affects millions of people worldwide. Eighty-five percent of the CML cases are diagnosed during chronic phase, most of which are detected through routine tests. Leukocytes, micro-Ribonucleic Acids, and myeloid markers are the primary biomarkers for CML diagnosis and are mainly detected using real-time reverse transcription polymerase chain reaction, flow cytometry, and genetic testing. Though multiple therapies have been developed to treat CML, early detection still plays a pivotal role in the overall patient survival rate. The current technologies used for CML diagnosis are costly and are confined to laboratory settings which impede their application in the point-of-care settings for early-stage detection of CML. This study provides detailed analysis and insights into the significance of CML, patient symptoms, biomarkers used for testing, and best possible detection techniques responsible for the enhancement in survival rates. A critical and detailed review is provided around potential microfluidic devices that can be adapted to detect the biomarkers associated with CML while enabling point-of-care testing for early diagnosis of CML to improve patient survival rates.

AQAFI: a bioanalytical method for automated KPIs quantification of fluorescent images of human leukocytes and micro-nano particles.

Micro-nanoparticle and leukocyte imaging find significant applications in the areas of infectious disease diagnostics, cellular therapeutics, and biomanufacturing. Portable fluorescence microscopes have been developed for these measurements, however, quantitative assessment of the quality of images (micro-nanoparticles, and leukocytes) captured using these devices remains a challenge. Here, we present a novel method for automated quality assessment of fluorescent images (AQAFI) captured using smartphone fluorescence microscopes (SFM). AQAFI utilizes novel feature extraction methods to identify and measure multiple features of interest in leukocyte and micro-nanoparticle images. For validation of AQAFI, fluorescent particles of different diameters (8.3, 2, 1, 0.8 µm) were imaged using custom-designed SFM at a range of excitation voltages (3.8-4.5 V). Particle intensity, particle vicinity intensity, and image background noise were chosen as analytical parameters of interest and measured by the AQAFI algorithm. A control method was developed by manual calculation of these parameters using ImageJ which was subsequently used to validate the performance of the AQAFI method. For micro-nanoparticle images, correlation coefficients with R2 > 0.95 were obtained for each parameter of interest while comparing AQAFI vs. control (ImageJ). Subsequently, key performance indicators (KPIs) i.e., signal difference to noise ratio (SDNR) and contrast to noise ratio (CNR) were defined and calculated for these micro-nano particle images using both AQAFI and control methods. Finally, we tested the performance of the AQAFI method on the fluorescent images of human peripheral blood leukocytes captured using our custom SFM. Correlation coefficients of R2 = 0.99 were obtained for each parameter of interest (leukocyte intensity, vicinity intensity, background noise) calculated using AQAFI and control (ImageJ). A high correlation was also found between the CNR and SDNR values calculated using both methods. The developed AQAFI method thus presents an automated and precise way to quantify and assess the quality of fluorescent images (micro-nano particles and leukocytes) captured using portable SFMs. Similarly, this study finds broader applicability and can also be employed with benchtop microscopes for the quantitative assessment of their imaging performance.

Multi-modal sensing with integrated machine learning to differentiate specific leukocytes targeted by electrically sensitive hybrid particles.

The growing need for personalized, accurate, and non-invasive diagnostic technology has resulted in significant advancements, from pushing current mechanistic limitations to innovative modality developments across various disease-related biomarkers. However, there still lacks clinical solutions for analyzing multiple biomarkers simultaneously, limiting prognosis for patients suffering with complicated diseases or comorbidities. Here, we conceived, fabricated, and validated a multifrequency impedance cytometry apparatus with novel frequency-sensitive barcoded metal oxide Janus particles (MOJPs) as cell-receptor targeting agents. These microparticles are modulated by a metal oxide semi-coating which exhibit electrical property changes in a multifrequency electric field and are functionalized to target CD11b and CD66b membrane proteins on neutrophils. A multi-modal system utilizing supervised machine learning and simultaneous high-speed video microscopy classifies immune-specific surface receptors targeted by MOJPs as they form neutrophil-MOJP conjugates, based on multivariate multifrequency electrical recordings. High precision and sensitivity were determined based on the type of MOJPs conjugated with cells (>90% accuracy between neutrophil-MOJP conjugates versus cells alone). Remarkably, the design could differentiate the number of MOJPs conjugated per cell within the same MOJP class (>80% accuracy); which also improved comparing electrical responses across different MOJP types (>75% accuracy) as well. Such trends were consistent in individual blood samples and comparing consolidated data across multiple samples, demonstrating design robustness. The configuration may further expand to include more MOJP types targeting critical biomarker receptors in one sample and increase the modality's multiplexing potential.

Can antidepressant use be associated with emotional blunting in a subset of patients with depression? A scoping review of available literature.

INTRODUCTION: Despite frequent recognition of emotional blunting in the published literature, either as a primary symptom of depression or as an adverse effect of antidepressants, there is no systematic synthesis on this topic to our knowledge. We undertook this scoping review to assess the prevalence, clinical features, implicated causes and management of emotional blunting, outlining the phenomenological and clinical gaps in research. METHOD: A systematic search was done until March 15, 2022, to include all original studies (i.e., interventional trials, cohort & cross-sectional studies, case reports, and case series). All reviewed data were delineated to answer pertinent clinical, phenomenological, and management questions related to the phenomenon of emotional blunting. RESULTS: A total of 25 original studies were included in our scoping review. Emotional blunting was described as a persistent diminution in both positive and negative feelings in depressed patients, who could subjectively differentiate it from their acute symptoms. However, the literature lacked the distinction between emotional blunting as a primary symptom of depression or an adverse effect of antidepressants. Common clinical strategies to manage antidepressant-induced emotional blunting included dose reduction or switching to a different antidepressant. CONCLUSION: Emotional blunting was a significant patient-reported concern with antidepressants. Future research should clarify phenomenological and neurobiological constructs underlying emotional blunting to improve diagnostic and management skills.

Point-of-Care Portable 3D-Printed Multispectral Sensor for Real-Time Enzyme Activity Monitoring in Healthcare Applications.

Absorbance spectroscopy finds many biomedical and physical applications ranging from studying the atomic and molecular details of the analyte to determination of unknown biological species and their concentration or activity in the samples. Commercially available laboratory-based spectrometers are usually bulky and require high power and laborious manual processing, making them unsuitable to be deployed in portable and space-constrained environments, thereby further limiting their utility for real-time on-site monitoring. To address these challenges, here we developed a portable 3D-printed multispectral spectrophotometer based on absorbance spectroscopy for real-time monitoring of enzyme molecular activity. Monitoring enzyme (such as tyrosinase) activity is critical, as it quantifies its reaction rate, which is dependent on many factors such as the enzyme and substrate concentrations, temperature, pH, and other regulators such as inhibitors and effectors. Tyrosinase is a critical enzyme responsible for melanin synthesis in living beings and exhibits enzymatic browning in fruits and vegetables. It finds various commercial applications in the fields of healthcare (skin pigmentation, wound healing, etc.), forensics, and food processing. Here, tyrosinase activity was monitored using a 3D-printed spectral sensor at different rates and compared against measurements obtained from laboratory instruments. The enzyme activity was also studied using kojic acid (i.e., a commonly employed commercial tyrosinase inhibitor) while varying its molar and volume concentrations to control the reaction rate at discrete activity levels. For tyrosinase activity monitoring, the fabricated device has shown significant correlation (R2 = 0.9999) compared to measurements from the standard table-top spectrophotometer. We also provide a performance comparison between the 3D-printed and the laboratory spectrophotometer instruments by studying tyrosinase enzyme activity with and without the influence of an inhibitor. Such a device can be translated into various absorbance spectroscopy-based point-of-care biomedical and healthcare applications.

Digital filtering dissemination for optimizing impedance cytometry signal quality and counting accuracy.

Improving biosensor performance which utilize impedance cytometry is a highly interested research topic for many clinical and diagnostic settings. During development, a sensor's design and external factors are rigorously optimized, but improvements in signal quality and interpretation are usually still necessary to produce a sensitive and accurate product. A common solution involves digital signal processing after sample analysis, but these methods frequently fall short in providing meaningful signal outcome changes. This shortcoming may arise from a lack of investigative research into selecting and using signal processing functions, as many choices in current sensors are based on either theoretical results or estimated hypotheses. While a ubiquitous condition set is improbable across diverse impedance cytometry designs, there lies a need for a streamlined and rapid analytical method for discovering those conditions for unique sensors. Herein, we present a comprehensive dissemination of digital filtering parameters applied on experimental impedance cytometry data for determining the limits of signal processing on signal quality improvements. Various filter orders, cutoff frequencies, and filter types are applied after data collection for highest achievable noise reduction. After designing and fabricating a microfluidic impedance cytometer, 9 µm polystyrene particles were measured under flow and signal quality improved by 6.09 dB when implementing digital filtering. This approached was then translated to isolated human neutrophils, where similarly, signal quality improved by 7.50 dB compared to its unfiltered original data. By sweeping all filtering conditions and devising a system to evaluate filtering performance both by signal quality and object counting accuracy, this may serve as a framework for future systems to determine their appropriately optimized filtering configuration.

Excitation modalities for enhanced micro and nanoparticle imaging in a smartphone coupled 3D printed fluorescent microscope.

Smartphone fluorescent microscopes (SFM) offer many functional characteristics similar to their benchtop counterparts at a fraction of the cost and have been shown to work for biomarker detection in many biomedical applications. However, imaging and quantification of bioparticles in the sub-micron and nanometer range remains challenging as it requires aggressive robustness and high-performance metrics of the building blocks of SFM. Here, we explored multiple excitation modalities and their performance on the imaging capability of an SFM. Employing spatial positional variations of the excitation source with respect to the imaging sample plane (i.e., parallel, perpendicular, oblique), we developed three distinct SFM variants. These SFM variants were tested using green-fluorescent beads of four different sizes (8.3, 2, 1, 0.8 µm). Optimal excitation voltage range was determined by imaging these beads at multiple excitation voltages to optimize for no data loss and acceptable noise levels for each SFM variant. The SFM with parallel excitation was able to only image 8.3 µm beads while the SFM variants with perpendicular and oblique excitation were able to image all four bead sizes. Relative performance of the SFM variants was quantified by calculating signal difference to noise ratio (SDNR) and contrast to noise ratio (CNR) from the captured images. SFM with oblique excitation generated the highest SDNR and CNR values, whereas, for power consumption, SFM with perpendicular excitation generated the best results. This study sheds light on significant findings related to performance of SFM systems and their potential utility in biomedical applications involving sub-micron imaging. Similarly, findings of this study are translatable to benchtop microscopy instruments as well as to enhance their imaging performance metrics.

Aluminum Oxide-Coated Particle Differentiation Employing Supervised Machine Learning and Impedance Cytometry.

This article uses a supervised machine learning (ML) system for identifying groups of nanoparticles coated with metal oxides of varying thicknesses using a microfluidic impedance cytometer. These particles generate unique impedance signatures when probed with a multifrequency electric field and finds applications in enabling many multiplexed biosensing technologies. However, current experimental and data processing techniques are unable to sensitively differentiate different metal oxide coated particle types. Here, we employ various machine learning models and collect multiple particle metrics measured. In reported experiments, a 75% accuracy was determined to separate aluminum oxide coated (10nm and 30nm), which is significantly greater than observing only univariate data between different microparticle types. This approach will enable ML models to differentiate such particles with greater accuracies.

Antibody-functionalized aluminum oxide-coated particles targeting neutrophil receptors in a multifrequency microfluidic impedance cytometer.

Personalized diagnostics of infectious diseases require monitoring disease progression due to their ever-changing physiological conditions and the multi-faceted organ system mechanisms involved in disease pathogenesis. In such instances, the recommended clinical strategies involve multiplexing data collection from critical biomarkers related to a patient's conditions along with longitudinal frequent patient monitoring. Numerous detection technologies exist both in research and commercial settings to monitor these conditions, however, they fail to provide biomarker multiplexing ability with design and data processing simplicity. For a recently conceived multiplexing biomarker modality, this work demonstrates the use of electrically sensitive microparticles targeting and identifying membrane receptors on leukocytes using a single detection source, with a high potential for multiplexing greater than any existing impedance-based single-detection scheme. Here, polystyrene microparticles are coated with varying thicknesses of metal oxides, which generate quantifiable impedance shifts when exposed to multifrequency electric fields depending on the metal oxide thickness. Using multifrequency impedance cytometry, these particles can be measured and differentiated rapidly across one coplanar electrode scheme. After surface-functionalizing particles with antibodies targeting CD11b and CD66b receptors, the particles are combined with isolated neutrophils to measure receptor expression. A combination of data analysis techniques including multivariate analysis, supervised machine learning, and unsupervised machine learning was able to accurately differentiate samples with up to 91% accuracy. This proof-of-concept study demonstrates the potential for these oxide-coated particles for enumerating specific leukocytes enabling multiplexing. Further, additional coating thicknesses or different metal oxide materials can enable a compendium of multiplexing targeting resource to be used to develop a high-multiplexing sensor for targeting membrane receptor expression.

Bioelectronic Sensor with Magnetic Modulation to Quantify Phagocytic Activity of Blood Cells Employing Machine Learning.

Microbial infections result in activating an immune response in the human body, which triggers inflammatory pathways resulting in recognition and subsequent killing of the pathogens. Quantifying the blood cells' natural ability to kill pathogens, i.e., phagocytosis, is critical to demonstrating the effectiveness of an individual's response in combating pathogens. Current laboratory processes and equipment that can be used to monitor phagocytic activity are costly and time-consuming and require significant technical expertise to run such assays. Here, we design and develop a novel biosensing platform capable of quantifying the phagocytic ability of blood cells. The sensor design is composed of electronic sensing and magnetic modulation sub-systems that work in conjunction to monitor phagocytic activity in microfluidic channels. The phagocytes internalize the IgG-coated magnetic beads, and when infused into the sensor, their speed will be modulated using the quadrupole magnetic field configuration as they pass through microfluidic channels where microfabricated electrodes are placed. The electronic sensor will generate the voltage pulse for each passage of the phagocyte, whose distinct features are correlative to the phagocytic activity. We experimentally tested this device using 17 blood samples collected from patients at Robert Wood Johnson Medical Hospital. Further, we developed artificial neural networks (ANN) to improve the accuracy of the phagocytic activity detection. ANN model detected the phagocytic activity with 88.2% accuracy. This novel sensing platform can potentially be used to triage high risk patients and develop personalized theranostics for the septic patients in the future.

Development of myocarditis and pericarditis after COVID-19 vaccination in adult population: A systematic review.

Objectives: A clear temporal relationship between myocarditis and pericarditis after COVID-19 vaccination has led to the belief that the vaccine may act as a trigger for these cardiologic complications. The aim of this systematic review is to explore the incidence, clinical presentation, management, and association between them. Methods: We conducted a systematic literature search on Cochrane, MEDLINE, and EMBASE as per guidelines of PRISMA (Preferred Reporting Items for Systematic Reviews). A total of 41 case reports and case series describing 97 patients, and 5 original articles describing 15,585,309 participants were selected as part of this review. Results: Of the 97 reported cases describing vaccine-associated myocarditis/pericarditis, 67 (69%) patients received Pfizer-BioNTech and 25 (25.7%) received Moderna. The mean onset of symptoms after vaccine administration was 3.8 ± 4.5 days with three-quarters developing symptoms after the second dose. Chest pain (n = 88, 90%) and fever (n = 33, 34%) were the most common presenting complaints. Out of 97, 80 (82.5%) patients recovered while 4 (4.1%) patients expired. The pooled incidence of myocarditis and pericarditis extrapolated from original studies is 0.001% and 0.0004%, respectively. In the original studies, nearly all the cases of myocarditis and pericarditis were mild. Chest pain and fever were the most common presenting symptoms. Conclusion: Myocarditis and pericarditis after the COVID-19 vaccine have been reported more in young adult males and are most likely to occur after the second dose of mRNA vaccines. The presentation is mild and the majority of the patients recover either completely or partially.

De-novo fabrication of sunlight irradiated silver nanoparticles and their efficacy against E. coli and S. epidermidis.

Silver nanoparticles (AgNPs) gained significant attention due to their activity against microbial pathogens, cancer cells, and viral particles etc. Traditional fabrication methods require hazardous chemicals as reducing agents and their usage and disposal pose a significant hazard to environmental ecosystem. Here, a de novo, robust, cost effective and an eco-friendly method is reported to fabricate AgNPs irradiated with sunlight (SL) while using Salvadora persica root extract (SPE) as reducing agent. Sunlight (SL) irradiated S. persica silver nanoparticles (SpNPs) i.e., SL-SpNPs were characterized using multiple techniques and their antibacterial efficacy was evaluated. The SL-SpNPs were synthesized in 10 min. Field emission scanning electron microscopy (FE-SEM) and transmission electron microscopy (TEM) analysis revealed their spherical morphology with a size range of 4.5-39.7 nm, while surface plasmon resonance (SPR) peaked at 425 nm. Fourier transform infrared spectroscopy (FTIR) analysis suggested that the reduction of SL-SpNPs was due to the presence of phytochemicals in the SPE. Furthermore, X-ray powder diffraction (P-XRD) pattern depicted the crystal structure of SL-SpNPs, hence proving the presence of AgNPs. Further the antibacterial studies were carried out against Escherichia coli (ATCC 11229) and Staphylococcus epidermidis (ATCC 12228) using Kirby Bauer method. The minimum inhibitory concentration (MIC) and minimum bactericidal concentration (MBC) for E. coli were determined to be 1.5 µg/mL and 3.0 µg/mL respectively while MIC and MBC values for S. epidermidis were found to be 12.5 µg/mL and 25 µg/mL respectively. The solar irradiation-based fabrication method and resulting SL-SpNPs can find their utility in many biomedical and environmental applications.

Deep Learning Application for Effective Classification of Different Types of Psoriasis.

Psoriasis is a chronic inflammatory skin disorder mediated by the immune response that affects a large number of people. According to latest worldwide statistics, 125 million individuals are suffering from psoriasis. Deep learning techniques have demonstrated success in the prediction of skin diseases and can also lead to the classification of different types of psoriasis. Hence, we propose a deep learning-based application for effective classification of five types of psoriasis namely, plaque, guttate, inverse, pustular, and erythrodermic as well as the prediction of normal skin. We used 172 images of normal skin from the BFL NTU dataset and 301 images of psoriasis from the Dermnet dataset. The input sample images underwent image preprocessing including data augmentation, enhancement, and segmentation which was followed by color, texture, and shape feature extraction. Two deep learning algorithms of convolutional neural network (CNN) and long short-term memory (LSTM) were applied with the classification models being trained with 80% of the images. The reported accuracies of CNN and LSTM are 84.2% and 72.3%, respectively. A paired sample T-test exhibited significant differences between the accuracies generated by the two deep learning algorithms with a p < 0.001. The accuracies reported from this study demonstrate potential of this deep learning application to be applied to other areas of dermatology for better prediction.

A prelude to wearable technology for the measurement and restoration of core body temperature and heart rate in athletes suffering from hypothermia.

An individual who is in good physical health tends to exhibit an internal core temperature of 37°C and a heart rate of 60-100 beats per minute. Increase in the temperature of the surrounding environment can serve as the basis for the onset of the condition of Hypothermia. Hypothermia acts as one of the most significant barriers being faced by winter athletes and starts initially with an increase in the heart and breathing rate. However, if the condition persists it can lead to reduction in the heart and breathing rate and ultimately results in cardiac failure. Although, jackets are commercially available, they tend to operate manually and furthermore, do not serve the primary purpose of counteracting the condition of hypothermia, particularly experienced by athletes taking part in winter sports. The objective of this study is to design a heating jacket that enables effective counteraction of the condition of Hypothermia. It enables precise measurement of the of core body temperature with the aid of a pyroelectric sensor. Along with this, a pulse rate sensor for detecting the accurate heart rate has been incorporated on the index finger. Five heating pads would get activated to attain optimal temperature, in case the core body temperature of <37°C is detected. If the condition of hypothermia advances to the moderate stage, two additional heating pads will get activated and provide extra warmth to attain normal heart rate along with core body temperature. Overall, this wearable technology serves as a definitive solution to counteract the condition of hypothermia only when the internal parameters exhibit that you actually have it. The results of the study exhibited that this prototype can be utilized for detecting and treating the condition of Hypothermia.

MACHINE LEARNING ENABLES QUANTIFYING CELL-JANUS PARTICLE CONJUGATES THROUGH MICROFLOWING IMPEDANCE SIGNALS.

In this work, we demonstrate the differentiation of demodulated multifrequency signals from impedance sensitive microparticles when targeting surface receptors on neutrophils in a microfluidic impedance cytometer. These scheme uses a single signal input and detection configuration, and machine learning can differentiate particle types with up to 82% accuracy.

Frequency-Time Domain (FTD) Impedance Data Analysis to Improve Accuracy of Microparticle Enumeration in a Microfluidic Electronic Counter.

Experimental background noise present in biosensors' data hinders the ability for sensitive and accurate detection of critical biomarkers. Here, we report our digital signal processing analysis with respect to frequency and time domain (FTD) data to reduce noise in an experimental microfluidic impedance cytometer. We evaluated the effectiveness of employed noise filtering techniques independently, including baseline drift correction, high frequency noise filtering, and powerline interference mitigation. We further explored the combined effect of all filters and determine improvements in signal-to-noise (SNR) ratio and particle counting accuracy. By removing noise regimes, SNR improved with this impedance cytometer device, and our future efforts will explore filtering effects of more specific and uncommon noise spectrums to greater optimize device performance.

Investigating Cell-Particle Conjugate Orientations in a Microfluidic Channel to Ameliorate Impedance-based Signal Acquisition and Detection.

Many biomedical experimental assays rely on cell-to-microparticle conjugation and their subsequent detection to quantify disease-related biomarkers. In this report, we investigated the effect of particle attachment position on a cell's surface to a signal acquired using impedance cytometry. We also present a novel configuration of independent coplanar microelectrodes positioned at the bottom and top of the microfluidic channel. In simulation results, our configuration accurately identifies different particle positions around the cell. We implemented a channel design with focusing regions between electrodes, and considered external factors around the channel such as polydimethylsiloxane (PDMS) interacting with the electric field and physical constraints of top electrodes placed farther away from the channel which improves detection accuracy.

Time-domain signal averaging to improve microparticles detection and enumeration accuracy in a microfluidic impedance cytometer.

Microfluidic impedance cytometry is a powerful system to measure micro and nano-sized particles and is routinely used in point-of-care disease diagnostics and other biomedical applications. However, small objects near a sensor's detection limit are plagued with relatively significant background noise and are difficult to identify for every case. While many data processing techniques can be utilized to reduce noise and improve signal quality, frequently they are still inadequate to push sensor detection limits. Here, we report the first demonstration of a novel signal averaging algorithm effective in noise reduction of microfluidic impedance cytometry data, improving enumeration accuracy, and reducing detection limits. Our device uses a 22 µm tall × 100 µm wide (with 30 µm wide focused aperture) microchannel and gold coplanar microelectrodes that generate an electric field, recording bipolar pulses from polystyrene microparticles flowing through the channel. In addition to outlining a modified moving signal averaging technique theoretically and with a model data set, we also performed a compendium of characterization experiments including variations in flow rate, input voltage, and particle size. Multivariate metrics from each experiment are compared including signal amplitude, pulse width, background noise, and signal-to-noise ratio (SNR). Incorporating our technique resulted in improved SNR and counting accuracy across all experiments conducted, and the limit of detection improved from 5 to 1 µm particles without modifying microchannel dimensions. Succeeding this, we envision implementing our modified moving average technique to develop next-generation microfluidic impedance cytometry devices with an expanded dynamic range and improved enumeration accuracy. This can be exceedingly useful for many biomedical applications, such as infectious disease diagnostics where devices may enumerate larger-scale immune cells alongside sub-micron bacterium in the same sample.

Classification Framework for Healthy Hairs and Alopecia Areata: A Machine Learning (ML) Approach.

Alopecia areata is defined as an autoimmune disorder that results in hair loss. The latest worldwide statistics have exhibited that alopecia areata has a prevalence of 1 in 1000 and has an incidence of 2%. Machine learning techniques have demonstrated potential in different areas of dermatology and may play a significant role in classifying alopecia areata for better prediction and diagnosis. We propose a framework pertaining to the classification of healthy hairs and alopecia areata. We used 200 images of healthy hairs from the Figaro1k dataset and 68 hair images of alopecia areata from the Dermnet dataset to undergo image preprocessing including enhancement and segmentation. This was followed by feature extraction including texture, shape, and color. Two classification techniques, i.e., support vector machine (SVM) and k-nearest neighbor (KNN), are then applied to train a machine learning model with 70% of the images. The remaining image set was used for the testing phase. With a 10-fold cross-validation, the reported accuracies of SVM and KNN are 91.4% and 88.9%, respectively. Paired sample T-test showed significant differences between the two accuracies with a p < 0.001. SVM generated higher accuracy (91.4%) as compared to KNN (88.9%). The findings of our study demonstrate potential for better prediction in the field of dermatology.