2023
Global Health Innovations
-
THE TEAM
Student Team: Braden Barlean, Khalil Merali, Meagan Smith, Poplar Yang
Advisors: Harshad Sanghvi, Tigistu Adamu Ashengo, John Varallo, Swaroop Vedula, Youseph Yazdi,Soumyadipta Acharya
ABSTRACT
ARISE is a modular simulation training platform for laparoscopic surgery focused on accessible, mentor facilitated training. ARISE uses a smartphone camera paired with a low-cost simulation box to deliver cost effective skills training. Furthermore, trainee performance is captured by our app-based platform for crowd sourced review from a community of mentorship. Currently, our platform is focused on allowing trainees to independently develop skills in laparoscopy without the need for an in-person mentor. We have integrated best practices from educational platforms, including high frequency, low dose training, progression systems and motivational content. This platform has been deployed at four Kenyan hospitals as part of a formative usability study, with unanimously positive feedback from surgeons and trainees. Our areas of future development include advanced skills training to deliver surgical training at every step of competency development, facilitated by AR and VR environments. We are also developing a series of machine learning algorithms to provide tailored surgical training based on performance and eventually deliver objective, goal-directed feedback with the assistance of AI mentorship. To facilitate development and sustainability we envision ARISE to be an open standard in which a variety of content can be distributed to trainees from medical device manufacturers and educational bodies. ARISE will be a paradigm shift in surgical education to accelerate and democratize surgical training globally
-
THE TEAM
Student Team: Bhavya Gopinath, Sam Dasari, Carter Gaulke, Sunny Patel
Advisors: Youseph Yazdi, Soumyadipta Acharya, April Zambelli Weiner, Kunal Parikh, Radha Taralekar, Aditya Polsani
ABSTRACT
Each year, malaria infects an estimated 227 million individuals, resulting in over 400,000 deaths, most of whom are pregnant women and children under five in sub-Saharan Africa. Currently, efforts to eliminate malaria rely on monitoring vector species composition, abundance, distribution, and behavior across different transmission geographies. For effective malaria control, targeted interventions and resource allocation should be driven by a robust vector surveillance system. For example, one primary vector of malaria, Anopheles funestus, has a different biting pattern than another, Anopheles arabiensis, and therefore necessitate different intervention strategies. The current structure of vector surveillance begins with mosquito collection, where mosquito specimens are collected at sentinel sites across a country using various collection methods such as CDC light traps, pyrethroid spray catches, and human landing catches. These specimens are transported to a central laboratory and morphologically identified for sex, species, and abdominal status by vector control officers (VCOs), who study entomology and vector surveillance for at least 3 years. Then a subset of the specimen is sent for molecular identification through polymerase chain reactions. However, the number of entomologists is limited and hard to retain in areas where the burden of malaria is the highest. Unfortunately, the global shortage of entomologists hinders large-scale surveillance efforts, especially where they are needed most. As a result, the sites where specimens are collected and analyzed are sparsely distributed across a target region, and treated as a representation of the entire country. These leads to inaccuracies in the interventions deployed, which is further worsened given the time lag between the capturing of specimens and the reporting time of usable data for decision-making. VectorCam aims to fill this gap, being the first low-cost AI-based tool that automatically detects a mosquito’s species, sex, and abdomen status, thereby deskilling the identification process. Task-shifting efforts to Village Health Teams (VHTs) will generate higher throughput and widespread surveillance coverage, enabling better-informed, data-driven malaria intervention decisions in a cost-effective manner.
-
THE TEAM
Student Team: Shri Prabha Shivram, Phoebe Dijour, Mitchell Turley, Dr. Anders Sideris
Advisors: Jordan Shuff, Dr. Kunal Parikh, Dr. Nakul Shekhawat, Dr. Rama Chellappa, David Green, Dr. David Friedman, Dr. Nicholas Durr, Corey Simmerer
ABSTRACT
90% of the world’s 275 million blind and visually impaired people live in low- and middle-income countries (LMICs). Cataract, refractive error, corneal opacities, and other anterior eye diseases account for the majority of global blindness. In rural LMIC settings, lack of access to highly trained eye care providers, such as ophthalmologists (1:91,000 patients in India), is a key barrier to timely diagnosis and treatment for anterior eye diseases. There is an unmet need for accessible, ongoing screening of underserved patients in order to enable access to care and eliminate avoidable vision loss.
Visilant is an end-to-end eye screening and management system consisting of a low-bandwidth telemedicine platform and proprietary anterior segment imaging device. For eye care systems, Visilant’s technology platform provides a way to improve patient outreach and increase revenue while reducing reliance on limited specialized eye care staff. For patients, Visilant enables timely treatment and sustainable, longitudinal integration into the healthcare system. Visilant’s service is currently being used and evaluated by the largest eye care system in the world to diagnose, refer, and enable access to vision care in hundreds of remote communities in India.
-
THE TEAM
Student Team: Kim Hwang, Pav Naicker, Leanne Pichay, Teja Sathi
Advisors: Youseph Yazdi, Soumyadipta Acharya, Harshad Sanghvi, Susan Harvey, Radha Taralekar, Aditya Polsani
ABSTRACT
Ekyaalo is an AI-assisted method of interpreting breast cytology from fine needle aspiration samples to increase the accessibility, speed, accuracy, and reliability of breast cancer diagnosis in low- and middle-income countries. Breast cancer is a leading cause of cancer death in women worldwide. In Uganda, breast cancer carries a 20x greater likelihood of mortality than in the United States in a 5-year period, with 1 in 2 Ugandan women diagnosed with breast cancer succumbing to the disease. Women in rural communities especially, face multiple barriers to accessing diagnosis, which contributes to precious time lost as their cancer progresses. It takes well-over the WHO guideline of 60 days for a woman to receive diagnostic results and many never do. Over 80% of women presenting for treatment in Uganda have late-stage disease which has a low survival rate even with treatment. (In contrast, in the US it is 53%). Thus, there is a need to decentralize the method of breast cancer diagnosis in order to reduce diagnostic turnaround-time and reduce mortality.
Ekyaalo intends to increase access to breast cancer diagnosis in rural resource limited communities, so that women presenting with breast cancer symptoms can receive immediate triage within traveling distance of their villages before being directed to actionable next steps in the care pathway. Stakeholder feedback that our team conducted with the 18 pathologists in Uganda established that moving preliminary diagnosis to lower-tier health centers could reduce late stage presentation of breast cancer. We aim to 1) Enable the use of fine needle aspiration cytology, which is minimally invasive, minimizes discomfort to patient, requires non-specialized resources to acquire and takes minutes to process 2) Implement digital pathology to share information between local health workers and pathologists; 3) Apply AI to enable on-site evaluation of adequacy and accurate classification of malignancy; 4) Create a standardized workflow through combination of hardware and software implementations.
U.S. Healthcare Innovations
-
THE TEAM
Student Team: Braden Barlean, Khalil Merali, Meagan Smith, Poplar Yang
Advisors: Peter Abadir, Youseph Yazdi, Soumyadipta Acharya
ABSTRACT
Fecal incontinence (FI) is defined as uncontrolled soilage that exists on a spectrum from mild, small volume leakage to more severe, complete involuntary bowel movements. This problem becomes more prevalent with age, affecting 11 million older adults in the United States alone. This is attributed to a variety of etiologies such as neurologic disorders, cognitive impairment, mechanical damage, diarrhea, and constipation. Regardless of cause, FI contributes to a significant reduction in quality of life due to the loss of independence, discomfort of continued soilage, and long-term consequences of FI associated with the increased risk of skin irritation and breakdown, infection, and poor wound healing. Furthermore, incontinence has an associated mortality risk where patients with incontinence have about a 30% increased risk of mortality, even after factoring for cognitive impairment, functional status, and other comorbidities. Many existing solutions that aid in the management of FI are not viable long-term, are ineffective, or are inaccessible. In the acute care setting, fecal management systems (FMS), a rectal balloon and catheter system, have been used over absorbent materials due to benefits in reduced skin exposure to excrement, decreased skilled nursing time requirements, and significant cost savings compared to traditional FI management practices. However, current FMS devices are only able to capture liquid and semi-liquid stools. Thus, FMS fails to address all patients who could benefit from this type of FI management, particularly those with a mix of harder stools. About 57% of patients within this acute care setting experience fecal loading, one of the main failure modes of an FMS used today. This problem is even more pronounced in nursing homes where 70% of residents experience fecal loading. Thus, the mainstay of solutions for fecal incontinence, particularly in the community-based setting are absorptive products like diapers and pads. The use of these absorbent materials contributes to UTIs, incontinence associated dermatitis, skin breakdown, and high rates of caregiver burnout, costing the healthcare system $13 billion dollars in community-based settings and $4 billion dollars in acute care.
We are developing the digni•FI Fecal Management System, to better manage incontinence both in the acute care and nursing home settings. It is comprised of a rectal catheter, collection bag, applicator and irrigation system. To manage harder stools, the biggest barrier to wider use of FMS devices, we are developing a stool morcellator and an emulsification system that can break down harder stools. The catheter consists of an anchoring mechanism that occupies the lower third of the rectum and secures the device in place. It also contains the main drainage tube and a morcellating device within the segment of the FMS that is inserted into the rectum. The catheter attaches to the collection bag where it attaches to the patient’s bed and houses the power supply needed to power the intermittent irrigation/emulsification and morcellator system. The applicator consists of a plastic sheath and a deployment mechanism with a bumper that rests against the patient’s anus to ensure the device is safely deployed in the rectum. All components of the device are made of biocompatible and bioinert materials. We have identified a path to market which involves submission of a 510(k) application to the FDA with an identified predicate device, and we aim to enter the market within the acute care setting where these devices are already widely used. Following this, we aim to expand to the long-term care setting where the need for this product is greatest. We have identified existing reimbursement codes for our device, particularly as we move outside of the acute care setting. Thus, we aim to improve the lives of older adults and their caregivers through patient centered solutions for fecal incontinence.
-
THE TEAM
Student Team: Bhavya Gopinath, Sam Dasari, Carter Gaulke, Sunny Patel
Advisors: Youseph Yazdi, Soumyadipta Acharya, April Zambelli Weiner, Kunal Parikh, Kolaleh Eskandanian, Aditya Polsani
ABSTRACT
MiraHeart is a company passionate about improving the lives of the vulnerable children with heart defects who are at risk of developing congestive heart failure (CHF). Every year in the United States, 35,000 children are affected by CHF, a disease with a 6.3% mortality rate. The pediatric cardiomyopathy population is particularly prone to developing CHF, as nearly 60% of diagnosed patients receive CHF treatments within their first month. Nearly 50% of those diagnosed with CHF are hospitalized, and for those with cardiomyopathy, an 11% in-hospital mortality rate is present. With hospitalizations costing $70,000 per patient, CHF costs $1B annually in inpatient costs. CHF occurs when the heart fails to meet the circulatory demands of the body, leading to an increase in intravascular fluid pressure, known as central venous pressure (CVP). CVP is critical to adjusting CHF medications; however, it can only be read in hospital settings, leaving no monitoring options at home. Therefore, families are left with no objective way to track their child’s CHF progression. This allows CHF to progress to a stage where hospitalization and more intensive treatments are necessary, resulting in higher treatment costs and more pain for this child.
MiraHeart addresses this gap in care. Our wearable, non-invasive device provides objective metrics of CHF by reading the child’s CVP and transmits this directly to physicians. MiraHeart consists of a small, optical sensor array and software system harbored in a neck band worn by a child twice daily, for 5 minutes each. MiraHeart is prescribed by the patient’s cardiologist and utilized by the child’s caretaker. MiraHeart facilitates proper decision-making on CHF medications, transforming care with little shift in the day-to-day workflow of clinicians and families. Our team submitted porcine and pediatric human protocols, hoping to further validate the accuracy of our device in April 2023 upon approval.
-
THE TEAM
Student Team: Shri Prabha Shivram, Phoebe Dijour, Mitchell Turley, Dr. Anders Sideris
Advisors: Nicholas Rowan, Youseph Yazdi, Ashish Nimgaonkar, April Zambelli-Weiner, Antony Fuleihan
ABSTRACT
Complete concentric collapse at the level of the palate (CCCp) is a severe form of obstructive sleep apnea (OSA), marked by repeated airway obstruction affecting up to 250 million people worldwide and 8 million in the US alone.1 Left untreated, it doubles risk of heart attack, stroke, and diabetes, and increases daytime sleepiness and neurocognitive dysfunction.2 OSA-related motor vehicle accidents alone kill 1400/year and contribute to $150B in US economic burden.3 The current treatment options (CPAP, upper airway surgery, neurostimulation) are expensive, invasive, and have poor outcomes, leaving 1 million people suffering with untreated severe disease every year.
The SomnOSA solution is a novel neurostimulation platform that increases airway musculature tone to prevent airway collapse. The patient deploys a removable device that activates during sleep. Neurostimulation is timed to patient inspiration, opening the airway and restoring normal breathing, to maximize its effect. The SomnOSA solution sets a new standard for non-invasive, clinically effective treatment of OSA by providing therapy targeted at the root cause of disease.
-
THE TEAM
Student Team: Kim Hwang, Pav Naicker, Leanne Pichay, Teja Sathi
Advisors: Youseph Yazdi, Soumyadipta Acharya, April Zambelli-Weiner, Fred Walker, Aditya Polsani
ABSTRACT
DiscOva is a comfortable and convenient method to collect, store, and transport menstrual effluent samples, while maintaining the integrity needed for these samples to be useful for the diagnosis of gynecologic disease. Menstrual effluent’s composition of endometrial tissue, live cells, and blood makes it uniquely suited for the diagnosis of gynecologic diseases like endometriosis. More than 1 in 10 women suffer from endometriosis, which causes extreme pelvic pain and has no good method of detection. The only method of diagnosis is an invasive surgery carrying the risk of many other complications. The live cells derived from menstrual effluent have demonstrated high diagnostic potential for endometriosis. This is but one initial application, as mononuclear cells isolated from menstrual samples show a strong resemblance with biopsy-derived endometrial mononuclear cells, suggesting many other promising uses.
DiscOva seeks to take a menstruating person-centered approach keeping collection simple and removing the need for extensive sampling handling. It also preserves the components of menstrual effluent, like live cells, that are critical to diagnostics. Through strategic partnerships with researchers in the space, DiscOva embeds itself in the clinical pathway as research in this space continues to grow. Work taken to progress DiscOva has included validation of methods of preserving cell viability, specifically the stromal fibroblast cells used in endometriosis detection research. Analogs such as Streck Tubes, BD Vacutainer tubes and other similar devices in sample preservation have been studied. In parallel, DiscOva has undergone user-centered design targeted at seamless at-home collection and preservation, including extensive customer discovery and exploration into menstrual products on the market. Each of these design considerations ensures that DiscOva will address the need it seeks to fulfill adequately.
