Underserved Locations Research Articles

Telementoring in Endoscopy and Surgery

AbstractTelementoring is the remote guidance of a mentee by an expert mentor specialist through a procedure or surgery. Advances in technology and telecommunications have enabled live interactions connecting people across the world over the same surgical operating field. While galvanized by COVID-era restrictions on travel and increasing reliance on virtual interfaces, there are also many other drivers for interest in this modality. Rural, isolated, or underserved locations stand to gain from prompt access to specialists, and there is potential for this technology to be resource-efficient and cost-effective. This review describes some of the telementoring forays in the fields of endoscopy, laparoscopy, and robotic surgery. This is a rapidly evolving field as it is highly technology dependent. Some challenges lie ahead before it can enjoy broader adoption, but telementoring shows promise as an approach that can help address unmet needs in unique clinical settings.

IoT-Based Virtual Primary Clinic: Remote Patient Monitoring and Consultation System

Using Internet of Things technology, the Virtual Primary Clinic project is a cutting-edge healthcare endeavor that enables remote patient monitoring and consultation. The project collects essential health metrics including body temperature, oxygen saturation, heartbeat, and ECG signals by integrating a variety of sensors, including NodeMCU ESP32, SpO2, DHT11, and AD8232 ECG. The information collected by these sensors is sent via API to a specially created website and an online platform called ThingSpeak. With features including patient registration, appointment scheduling, access to medical histories, and doctor-patient contact, the website acts as a comprehensive interface between patients and physicians. Patients can register on the website, provide their medical information, and get medications sent to them remotely based on their conditions. However, without having to see patients in person, doctors can examine patient data, diagnose ailments, and write prescriptions or offer medical advice.The Virtual Primary Clinic project intends to improve healthcare accessible, especially in remote or underserved locations, by enabling remote monitoring and consultation. In addition to providing healthcare providers with an effective platform for remote patient care, it gives patients the ability to take charge of their health. This project is a major step toward using cutting-edge IoT-based technologies to improve patient outcomes and democratize healthcare.

NOAA's National Water Model: Advancing operational hydrology through continental‐scale modeling

AbstractThe National Weather Service (NWS) Office of Water Prediction (OWP), in conjunction with the National Center for Atmospheric Research and the NWS National Centers for Environmental Prediction (NCEP) implemented version 2.1 of the National Water Model (NWM) into operations in April of 2021. As with the initial version implemented in 2016, NWM v2.1 is an hourly cycling analysis and forecast system that provides streamflow guidance for millions of river reaches and other hydrologic information on high‐resolution grids. The NWM provides complementary hydrologic guidance at current NWS river forecast locations and significantly expands guidance coverage and water budget information in underserved locations. It produces a full range of hydrologic fields, which can be leveraged by a broad cross section of stakeholders ranging from the emergency responder and water resource communities, to transportation, energy, recreation and agriculture interests, to other water‐oriented applications in the government, academic and private sectors. Version 2.1 of the NWM represents the fifth major version upgrade and more than doubles simulation skill with respect to hourly streamflow correlation, Nash Sutcliffe Efficiency, and bias reduction, over its original inception in 2016. This paper will discuss the driving factors underpinning the creation of the NWM, provide a brief overview of the model configuration and performance, and discuss future efforts to improve NWM components and services.

Pharmacy technicians trained as community health workers: A prospective multicenter cohort study

BackgroundCommunity health workers (CHWs) are health professionals who are experts in linking patients to health resources. Although CHWs are employed in a variety of health institutions, access to their services may be challenging for patients in underserved locations. Community pharmacies are uniquely positioned to mitigate this barrier as they provide readily accessible care for patients residing in these areas. ObjectivesTo 1) quantify and report the CHW services provided by certified pharmacy technicians (CPhTs) in an underserved population and 2) provide an initial framework for the implementation of CHW services in community pharmacies or similar health care settings. MethodsThis prospective cohort study reports the findings of training CPhTs as CHWs in 3 independent community pharmacies from January 1, 2021 to July 1, 2021. CPhT-CHWs conducted monthly visits by phone, patient home, or pharmacy and documented services using a standardized assessment form. Descriptive statistics were used to summarize the baseline characteristics of the patient population, service codes, types of services and referrals made, and time spent per visit by CPhT-CHWs. ResultsA total of 198 patient visits by phone, patient home, or at the pharmacy were completed in a 6-month timespan. During these visits, the CPhT-CHW provided 351 services (203 primary services and 149 secondary services) and completed 51 referrals. The average time spent per visit (standard deviation) was 15.5 (11.5) 68.9 (35.4), and 30.6 (16.8) minutes for phone, home, and pharmacy visits, respectively. Patient home visits resulted in the highest average primary services per visit, longest time spent with the patient, and accounted for a majority of social services. ConclusionCPhT-CHWs were able to use various methods to contact these patients to further develop patient-to-provider and patient-to-pharmacy relationships. Training CPhTs as CHWs can be an effective way to increase patient contact and provide additional health services.

Optimal location of remote dental units

Dental care, though critical, may not be accessible for many rural populations. Remote dental units (RDUs) can address the gap in access by providing basic services to rural areas, since recent digital health advancements enable close data integration between field RDUs and regional medical center clinical experts. Yet, the economic viability of this remote/hybrid care delivery effort has not been clearly established. We explore the economics of a major dental hospital operating RDUs in a distant rural area. Specifically, we characterize the optimal location of an RDU and examine the impact of operating this RDU on the hospital’s profit. We prove that the ideal scenario, from a patient-coverage perspective, is to put the RDU far enough away from the hospital such that patients accessing the RDU are distinct from patients accessing the hospital. This positioning avoids coverage overlap (market cannibalization). However, we show that such a placement may not always be optimal for the hospital’s profit, and we derive conditions under which the optimal patient coverage for the hospital and the RDU overlaps. Our results remain consistent for a hospital operating an RDU at different locations. The RDU will not be deployed in another location if the previous two locations have some coverage overlap. Our characterization of the profit-maximizing location provides hospitals with a practical guideline by quantifying the key trade-off between service expansion and the costs incurred by sending the provider team to remote, underserved locations. Our findings lead to important operational implications for regional dental care service by RDUs.

Epileptic seizure prediction based on multiresolution convolutional neural networks

Epilepsy withholds patients’ control of their body or consciousness and puts them at risk in the course of their daily life. This article pursues the development of a smart neurocomputational technology to alert epileptic patients wearing EEG sensors of an impending seizure. An innovative approach for epileptic seizure prediction has been proposed to improve prediction accuracy and reduce the false alarm rate in comparison with state-of-the-art benchmarks. Maximal overlap discrete wavelet transform was used to decompose EEG signals into different frequency resolutions, and a multiresolution convolutional neural network is designed to extract discriminative features from each frequency band. The algorithm automatically generates patient-specific features to best classify preictal and interictal segments of the subject. The method can be applied to any patient case from any dataset without the need for a handcrafted feature extraction procedure. The proposed approach was tested with two popular epilepsy patient datasets. It achieved a sensitivity of 82% and a false prediction rate of 0.058 with the Children’s Hospital Boston-MIT scalp EEG dataset and a sensitivity of 85% and a false prediction rate of 0.19 with the American Epilepsy Society Seizure Prediction Challenge dataset. This technology provides a personalized solution for the patient that has improved sensitivity and specificity, yet because of the algorithm’s intrinsic ability for generalization, it emancipates from the reliance on epileptologists’ expertise to tune a wearable technological aid, which will ultimately help to deploy it broadly, including in medically underserved locations across the globe.

Complex Family Planning fellowship graduates’ intended practice plans and barriers to practicing in areas of unmet need

ObjectivesTo describe practice patterns and challenges encountered by Complex Family Planning (CFP) fellowship graduates. Study designWe invited all 110 obstetrics and gynecology physicians who graduated from the CFP fellowship from 2017–2020 via email to complete an anonymous online survey. We inquired about demographics, intended and obtained postfellowship positions, and successes and challenges in obtaining jobs. We used Fisher's exact test to assess if the proportion of graduates who grew up, attended residency, and completed fellowship in a US region (Northeast, Midwest, South, and West) and practiced in that same region differed. ResultsNinety-nine (90.0%) graduates completed the survey. When entering fellowship, most (n = 92 [92.9%]) expected to practice in an academic environment. About half (n = 49 [49.5%]) pursued fellowship with the intent to practice in a location with an unmet need for abortion providers, of which 22 (44.9%) did so. Forty-nine (49.5%) respondents did not practice after fellowship where they initially intended, citing common challenges of job availability, family-related concerns, safety concerns, and relationship status changes. We found associations between regions where graduates completed residency and currently practice (p = 0.004), driven primarily by higher associations in the South (76.9%) and West (70.6%) and a lower association in the Midwest (22.7%). We found no association between current practice region and where graduates grew up (p = 0.15) or completed fellowship (p = 0.23). ConclusionsCFP fellowship graduates from 2017–2020 primarily intended to practice in academic environments with half planning to practice in underserved locations. However, more than half of those who entered fellowship hoping to fill an unmet need for abortion providers did not do so. ImplicationsAbout half of CFP fellowship graduates from 2017–2020 intended to obtain positions in areas they defined as having an unmet need for abortion provision. Personal life and job barriers prevented many from serving in such positions after fellowship. Practice location intentions and outcomes may be different in a post-Dobbs environment.

Substance use, injection risk behaviors, and fentanyl-related overdose risk among a sample of PWID post-Hurricane Maria

BackgroundWhile natural disasters like hurricanes are increasingly common, their long-term effects on people who inject drugs are not well understood. Although brief in duration, natural disasters can radically transform risk environments, increasing substance use and drug-related harms.MethodsBased on a study of people who inject drugs (PWID) and injection risk behaviors in rural Puerto Rico, the present study uses data from two different phases of the parent study. Data for 110 participants were collected from December 2015 to January 2017, soon before Hurricane Maria landed in September 2017; the 2019 phase, in the aftermath of the hurricane, included a total of 103 participants. The present study’s main analyses used data from 66 PWID who participated in both the pre-Maria and post-Maria interviews (66 individuals measured at two time points, for a total of 132 observations), using mixed-effects binomial logistic regression to examine recent overdose experiences pre- and post-Maria. A separate descriptive analysis included all 103 participants from the 2019 interview.ResultsAfter Hurricane Maria, some declines in injection frequency were observed (the percentage of people reporting injecting monthly or less increased from 3.0% before Hurricane Maria to 22.7% after Hurricane Maria). However, fewer PWID reported using a new needle for most or all injections. In the pre-Maria interview, 10.6% of participants indicated they had experienced an overdose during the year of the interview and/or the calendar year prior, and this figure increased to 24.2% in the post-Maria interview. In the regression analysis, the odds of reporting an overdose during the interview year and/or calendar year prior were three times as high post-Maria, relative to pre-Maria (odds ratio 3.25, 95% confidence interval 1.06–9.97).ConclusionSubstance use patterns, injection risk behaviors, and overdose episodes and deaths differed after Hurricane Maria, relative to before the hurricane, yet it is unclear to what extent these changes also reflect the simultaneous arrival of fentanyl. In preparation for future natural disasters, it is imperative to strengthen the health infrastructure by enhancing access and curbing barriers to syringe services programs and medications for opioid use disorder, particularly in rural or underserved locations.

Hands-On Training in a Digital World: A Novel Simulation-Based Virtual Training Program for Placement and Removal of the Subdermal Contraceptive Implant

ObjectiveThe COVID-19 pandemic necessitated a shift from traditional in-person instruction for learning new technical skills to virtual delivery of medical education training. The objectives of this study were to develop and evaluate a virtual simulation-based training program for Canadian health care professionals (HCPs) on the insertion, localization, and removal of the etonogestrel subdermal contraceptive implant. MethodsA scientific committee of Canadian family planning experts developed a 2-part virtual training program during the COVID-19 pandemic. Core educational content (part 1) was provided in an asynchronous, self-directed, online format. Part 2 consisted of synchronous, simulation-based training using web conferencing. The HCPs were provided with model arms and placebo applicators; the trainers demonstrated implant insertion and removal techniques, and trainees received individual feedback. All trainees were asked to complete an online evaluation upon completion of the program. ResultsBetween September 22, 2020, and December 31, 2021, 83 trainers conducted 565 virtual training sessions. A total of 3162 HCPs completed part 1 of the training program, of whom 2740 had completed part 2 by December 31, 2021. Participants reported high levels of satisfaction with virtual simulation-based training; 96.5% of respondents (1570/1627) agreed that the virtual format was effective. Additional training prior to inserting the implant in clinical practice was requested by 4.5% of respondents (75/1671). ConclusionVirtual simulation-based learning provides effective education and technique training for etonogestrel implant insertion and removal. Online training for implant use can be scaled, as needed, to reach professionals in remote or underserved locations. This virtual training approach may be appropriate for other technical or minor surgical procedures.

Road less traveled

When I graduated from pharmacy school in New York City back in 2015, a lack of desirable positions made me venture out to remote locations. My search afield led me to a position at a small Indian Health Service (IHS) clinic in South Dakota. While working there, I learned about the U.S. Public Health Service Commissioned Corps. It is one of the 8 uniformed services of the United States with a mission to protect, promote, and advance the health and safety of our nation.1 The members of the U.S. Public Health Service, including physicians, dentists, pharmacists, nurses, veterinarians, scientists, and engineers, are stationed at various federal agencies (e.g., IHS), including underserved locations, and are also called upon to deploy to meet the needs of the nation (e.g., coronavirus disease 2019 [COVID-19] public health emergency) when necessary.

The Safety of Early Discharge Following Transcatheter Aortic Valve Implantation Among Patients in Northern Ontario and Rural Areas Utilizing the Vancouver 3M TAVI Study Clinical Pathway

BackgroundEarly hospital ( < 48 hours) discharge following transcatheter aortic valve implantation (TAVI) is an increasingly adopted practice; however, data on the safety of such an approach among patients residing in North Ontario, including remote and medically underserved areas, are lacking. MethodsThis retrospective study included patients who underwent TAVI in Sudbury, Ontario. The safety of early discharge after implementation of the Vancouver 3M (multidisciplinary, multimodality, but minimalist) clinical pathway was assessed. The primary endpoint was 30-day mortality. Resource utilization before vs after 3M clinical pathway implementation was also compared. ResultsA total of 291 patients who underwent TAVI between 2012 and 2021 were included in the study. One in-hospital death (0.6%) occurred after the 3M clinical pathway implementation, with no mortality observed beyond hospital discharge. Eleven patients (6.7%) required rehospitalization within 30 days. The need for mechanical ventilation and surgical vascular cut-down declined from 100% and 97%, respectively, at baseline, to 6% and 2%. The number of patients receiving TAVI on a given procedural day increased from 2 to 3 patients. The median post-TAVI hospital length of stay decreased from 5 days (2-6 days) to 1 day (1-3 days) after 3M clinical pathway implementation. ConclusionsFollowing TAVI, early discharge of selected patients residing in Northern Ontario, including rural areas, using the Vancouver 3M clinical pathway was associated with favourable outcomes, short length of stay, and more-efficient resource utilization. These data can help improve healthcare efficiency and bridge variations in TAVI funding and accessibility in underserved locations.

Phytochemical drug discovery for COVID-19 using high-resolution computational docking and machine learning assisted binder prediction

The COVID-19 pandemic has resulted in millions of deaths around the world. Multiple vaccines are in use, but there are many underserved locations that do not have adequate access to them. Variants may emerge that are highly resistant to existing vaccines, and therefore cheap and readily obtainable therapeutics are needed. Phytochemicals, or plant chemicals, can possibly be such therapeutics. Phytochemicals can be used in a polypharmacological approach, where multiple viral proteins are inhibited and escape mutations are made less likely. Finding the right phytochemicals for viral protein inhibition is challenging, but in-silico screening methods can make this a more tractable problem. In this study, we screen a wide range of natural drug products against a comprehensive set of SARS-CoV-2 proteins using a high-resolution computational workflow. This workflow consists of a structure-based virtual screening (SBVS), where an initial phytochemical library was docked against all selected protein structures. Subsequently, ligand-based virtual screening (LBVS) was employed, where chemical features of 34 lead compounds obtained from the SBVS were used to predict 53 lead compounds from a larger phytochemical library via supervised learning. A computational docking validation of the 53 predicted leads obtained from LBVS revealed that 28 of them elicit strong binding interactions with SARS-CoV-2 proteins. Thus, the inclusion of LBVS resulted in a 4-fold increase in the lead discovery rate. Of the total 62 leads, 18 showed promising pharmacokinetic properties in a computational ADME screening. Collectively, this study demonstrates the advantage of incorporating machine learning elements into a virtual screening workflow. Communicated by Ramaswamy H. Sarma

Valuing the Partnership Between the Veterans Health Administration and Academic Medicine.

Valuing the Partnership Between the Veterans Health Administration and Academic Medicine.

P153 Spatial Analysis of Perinatal Food Assistance Resources in Relation to Food Deserts in North Carolina

<h3>Background</h3> A number of risk factors can influence maternal and infant health including chronic conditions, health behaviors and prenatal care. Women with access to perinatal resources and healthy foods could limit the impact of these risk factors for the maternal and infant well-being. Geographic Information Systems (GIS) is a software used to capture, store, and analyze geographic data. The advantages of GIS allows understanding of maternal and perinatal food assistance gaps. <h3>Objectives</h3> To locate and map government food assistance perinatal resources such as WIC, SNAP Offices, WIC and SNAP approved vendors throughout North Carolina. Determine if there are spatial correlations between the density (ie number of physical locations at the census tract level) of food assistance clinics and approved retailers in comparison to areas classified as food deserts by the USDA (low access and low income designation). Assess the association between underlying population characteristics and WIC/SNAP locations. <h3>Study Design, Setting, Participants</h3> Undergraduate research assistants from Appalachian State University's Nutrition Department compiled a comprehensive list of WIC clinics, WIC-approved vendors, SNAP offices and SNAP retailers available in North Carolina from Google™. <h3>Measurable Outcome/Analysis</h3> These resources were geocoded to create a spatial distribution of the locations into ArcGIS Pro by ESRI by Appalachian State University's Geography/Planning Department. WIC and SNAP locations were spatially merged with USDA (food desert classification) and American Community Survey Data to create a relational GIS database. Bivariate map products and Kendall tau correlations were used to assess the association between underlying population characteristics and WIC/SNAP locations. <h3>Results</h3> Preliminary findings show limited WIC and SNAP office and retailer locations in rural, underserved locations with food deserts in NC. Spatially, variations in this association varies across the state with limited access in the far Eastern and Western regions of NC. <h3>Conclusions</h3> GIS and other simple spatial analysis allow for critical evaluation of WIC and SNAP offices/retailers and their relationship to food deserts, which could inform policies around support for more offices/retailers. <h3>Funding</h3> Internal Grant from University Research Council

GOVERNMENT ENCOURAGING SOCIAL AND ECONOMIC DEVELOPMENT THROUGH BY MIXED CAPITAL BANK: STIMULATING SOCIAL ENTREPRENEURSHIP

The analysis of government actions promoted by the state is present in several surveys. However, there are few contributions that analyze the social benefits of activities developed by public institutions of mixed capital, that reconcile social and economic aspects. This research aims to analyze the social effectiveness of a corporate social responsibility action of a mixed capital financial institution. Documentary research was developed in 11,377 projects, combined with the application of a questionnaire. It was identified that corporate social responsibility actions should prioritize social impact, positioning financial return and reputation as secondary aspects, in order to guarantee the social intentions of the institution promoting the activity, otherwise it will only be addressed how a investment for marketing strategies. Projects that seek to develop economic activities in underserved locations provide significant and lasting social impacts. A significant benefit of Corporate Social Responsibility is to empower people to be social entrepreneurs, and to encourage the dissemination of the culture of social entrepreneurship, thus enhancing the occurrence of more projects that serve the less favored economic classes.

Complex Family Planning Fellowship Graduates’ Practice Plans and Barriers to Practicing in Areas of Unmet Need [A42

INTRODUCTION: With recent changes in the political climate, complex family planning (CFP) fellowship directors have noted an increasing proportion of applicants expressing the intent to practice in areas with a dearth of abortion providers. However, data does not exist documenting fellowship graduates’ intended and post-training practice areas. METHODS: We anonymously surveyed 2017-2020 CFP fellowship graduates to inquire about demographics, intended and obtained post-fellowship positions, and successes and challenges in obtaining jobs. We used descriptive statistics and coded and analyzed open-ended responses for thematic content using grounded theory. RESULTS: One hundred (91%) of 110 invited CFP fellowship graduates responded. Most (92%) expected to practice in an academic environment. Half (49%) pursued fellowships with the intent to practice in a location with an unmet need for abortion providers. Of those, only 22 (45%) did so. When asked why they ultimately did not practice where intended, common themes included job availability, family-related concerns, safety concerns, and relationship status changes. CONCLUSION: CFP fellowship graduates primarily intend to practice in academic environments, with half planning to do so in underserved locations. However, the majority of those who entered fellowship hoping to fill an unmet need for abortion providers were unable to do so. While the CFP fellowship has laid the groundwork for training leaders in abortion provision, more work is needed to eliminate barriers that interfere with fellowship graduates’ willingness and ability to obtain positions in locations with unmet need.

An Exploratory Study of a Novel Approach to Improve Readiness for a Rural Family Medicine Residency.

Transitioning from medical school to residency is challenging, especially in rural training programs where a comprehensive scope of practice is needed to address rural health disparities. Oregon Health & Science University partnered with Cascades East Family Medicine Residency in Klamath Falls, Oregon to create an integrated fourth-year medical student experience (Oregon Family medicine Integrated Rural Student Training (Oregon FIRST). Participants may then enter this residency to complete their training with the intention to practice in rural underresourced settings. In this exploratory study, we conducted key informant interviews with 9 of ten Oregon FIRST participants to determine how Oregon FIRST contributed both to their readiness for residency training and their choice to practice in rural underserved locations. Interviews were conducted between June 10, 2020 and July 8, 2020. We analyzed field notes taken during interviews for emergent themes using classical content analysis. Emergent themes included logistical ease, relationship development, key curricular elements, and commitment to rural practice. Overwhelmingly, Oregon FIRST participants reported the experience had many challenging and demanding components because they served as subinterns for their entire fourth year of medical school, but this prepared them very well for internship. When asked if they would choose to enroll in Oregon FIRST again, given what they now know about physician training and patient care, all nine (100%) said they would. This study demonstrated that Oregon FIRST students felt better prepared for the rigors of residency and are committed to practicing in rural areas.

862-P: Impact of COVID-19 on Pediatric Endocrinology Practice and Diabetes Care in Children: A Survey

Objective: As the global pandemic caused by the SARS-CoV-2 virus continues unabated, healthcare delivery has been altered significantly impacting patients and providers. We examined the impact of COVID-19 on pediatric endocrinology practice and the challenges faced in pediatric diabetes care. Methods: A 27-item electronic survey was designed, pilot-tested, and deployed to pediatric endocrinology providers using the e-mail discussion lists of the American Academy of Pediatrics, Section on Endocrinology, and the Pediatric Endocrinology Clinical Case Mailing List (May and June 2020). The survey had questions regarding changes in practice, telemedicine use, and observed changes in diabetes disease manifestation. Results: 114 unique responses were analyzed, 79.3% were female respondents. Most (95.6%) providers surveyed were practicing in the United States, and 87.7% reported a decline in their patient volume. Telemedicine use was common [97% (95% CI: 92.4% - 99.4%)] and recent [83.3% (95% CI: 75.2% - 89.7%)] with 98% utilizing remote glycemia monitoring tools. Children with diabetes in underserved and remote locations faced significant barriers to telemedicine use such as lack of connectivity (61%), and devices (59%). Negative consequences on health due to the pandemic included, delay in diabetes diagnosis (33.3%), lack of follow-up (22.0%) and higher diabetic ketoacidosis cases (22.0%). Increased anxiety was commonly reported (66%). Conclusion: The COVID-19 pandemic has led to decline in patient volumes, with rapid adaptation to telemedicine use. Providers noted negative effects due to the pandemic on diabetes care including mental health. Benefits from telemedicine use were observed with a digital divide in underserved populations. Disclosure M. Chambers: None. M. Sinha: None. Funding National Institute of Diabetes and Digestive and Kidney Diseases

Reagent-free hemoglobin estimation on a spinning disc

Quantitative estimation of hemoglobin concentration is a commonly required clinical test to assess various manifestations of pathological conditions in blood. While several invasive and non-invasive approaches have been introduced for rapid low-cost determination of hemoglobin levels in patients, these methods have been reported to suffer from various constraints, limiting their applicability for precise quantitative analysis. Methods reporting high levels of quantitative accuracy, on the other hand, are severely challenged for their deployment in resource-limited settings, as these necessitate specialized reagents that demand exclusive storage and transportation facilities as well as trained human resources for deployment in the field. Circumventing these constraints, here we demonstrate a low cost (<$0.01 each test) reagent-free method for hemoglobin estimation on a simple portable unit that can be implemented in under-served locations without sacrificing the fundamental principle of direct evaluation of hemoglobin extracted from the human blood sample. Exploring the fundamental principle of osmotic hemolysis for extraction of hemoglobin from red blood cells, the method harnesses the dynamics of a blood drop on a rotating platform and simple imaging to come up with results in a turn-around time of about 13 min. The efficacy of the device has been justified by validating with established pathological gold standards. These results are likely to pave the pathway of establishing the paradigm of a first-principle based reagent-free evaluation of blood pathology in health and disease.

Detecting Diabetic Retinopathy Using Embedded Computer Vision

Diabetic retinopathy is one of the leading causes of vision loss in the United States and other countries around the world. People who have diabetic retinopathy may not have symptoms until the condition becomes severe, which may eventually lead to vision loss. Thus, the medically underserved populations are at an increased risk of diabetic retinopathy-related blindness. In this paper, we present development efforts on an embedded vision algorithm that can classify healthy versus diabetic retinopathic images. Convolution neural network and a k-fold cross-validation process were used. We used 88,000 labeled high-resolution retina images obtained from the publicly available Kaggle/EyePacs database. The trained algorithm was able to detect diabetic retinopathy with up to 76% accuracy. Although the accuracy needs to be further improved, the presented results represent a significant step forward in the direction of detecting diabetic retinopathy using embedded computer vision. This technology has the potential of being able to detect diabetic retinopathy without having to see an eye specialist in remote and medically underserved locations, which can have significant implications in reducing diabetes-related vision losses.