Sierra Willens is a medical student at Stanford interested in the intersection of healthcare and technology. For the past several years, Sierra has worked on numerous artificial intelligence projects designed to combat socioeconomic and geographic barriers to medicine through innovative healthcare technology. In 2018, she worked with an international team to diagnose retinal diseases through convolutional neural networks with subsequent efforts gauged at integrating this technology with iPhone ophthalmoscope attachments, bringing healthcare into the hands of our patients. Now, at Stanford, she has spearheaded a research project under the mentorship of Dr. Katherine Bianco which is designed to detect preterm birth in high-risk pregnancies and eventually merge this technology with platforms like IButterfly to further mobilize access to care to our most vulnerable population, preterm infants. In addition to her research pursuits, Sierra is co-founder of Stanford's new MEDX student initiation: a coalition between Biodesign and Stanford School of Medicine, designed to train future generations of physicians and physician associates how to become critical, impactful collaborators in the sector of health care innovation.
Honors & Awards
Tiffany Award for Best Scientific Presentation, The American Society for Aesthetic Plastic Surgery (2017)
Service, Volunteer and Community Work
Founder of Mask A Hero Campaign (March 2020 - July 2020)
Raised $3.5K in donations
Provided healthcare heroes equivalent of 3K masks to frontline workers
Former CEO of Race to Cure Foundation (May 2018 - May 2019)
Raised $54K in donations for early cancer detection
Filed SOI, 501(c)(3), and state solicitations
Set up a registered agent, business P.O. box, and nonprofit bank account
Filed fiscal year 990 form
Supervised and controlled all business and legal affairs of the Corporation
Conducted oversight of fundraising logistics
Developed website, online forms, waiver forms, automatic personalized emails
Foster Youth Mentor Program Mentor (July 2016 - July 2018)
Intern at Rady Children’s Hospital (January 2014 - 6/2014)
Scripps Memorial Hospital ER Volunteer (January 2013 - June 2013)
International Fellowship, UC San Diego School of Medicine (7/1/2017 - 4/1/2019)
Project 1: Artificial Intelligence project to diagnose disease from EHR records
Published in Nature Medicine
Liaison between the medical team and AI coding team
Project 2: Artificial Intelligence to diagnose common diseases from Fundus Images
Individually diagnosed over 50K retinal diseases from Fundus Images
Oversaw and managed a team of 20+ volunteers
Ran trials of a convolutional neural network for image analysis
Project 3: Artificial Intelligence to diagnose referral-based OCT images
Individually diagnosed 25K OCT images
Published in Cell
Clinical Research Assistant, Faces Plus - Plastic Surgery, Skin and Laser Center (December 1, 2013 - July 1, 2019)
Conducted over 2000 hours of clinical research
Presented study findings at the 50th Anniversary ASAPS conference with over 3,000 attendees
Won the Tiffany Award for Best Scientific Presentation
Medical Assistant, Shiley Eye Institute | UC San Diego (May 2018 - April 2019)
Diagnosing Fundus and OCT images from retinal photometry
Moving patients from and to rooms
Preparing rooms for injections
Standardized Anatomic and Regenerative Facial Fat Grafting: Objective Photometric Evaluation From 1-19 Months After Injectable Tissue Replacement and Regeneration (ITR2).
Aesthetic surgery journal
BACKGROUND: A standardized technique for facial fat grafting, Injectable Tissue Replacement and Regeneration (ITR 2), was developed to address both anatomic volume losses in superficial and deep fat compartments as well as skin aging, incorporating newer regenerative approaches.OBJECTIVES: The authors sought to track the short and long terms effects of a new standardized technique for facial fat grafting in the midfacial zone across a 19-month time period.METHODS: Twenty-nine female were analyzed for mid-facial volume changes after autologous fat transfer with ITR 2. Across 19 months, volumes were evaluated using the Vectra XT 3D Imaging System to calculate differences between a predefined, 3-dimensional mid-facial zone measured preoperatively and serially after fat grafting with novel approach using varying fat parcel sizes.RESULTS: Patient data was analyzed collectively as well as separately by age (< and > 55 years). Collective analysis revealed a trend of initial volume loss within the first 1-7 months followed by an increase within the 8-19-month range, averaging 56.6% postoperative gain and ending at an average of 52.3% gain in volume by 14-19 months. A similar trend was observed for patients <55 years of age, but to a greater extent, with a 54.1% average postoperative gain and final average of 75.2%. Conversely, patients above 55 years of age revealed a linear decay beginning at 60.6% and steadily declining to 29.5%. Multiple regression analysis revealed no statistically significant influence of weight change during the study duration.CONCLUSIONS: Preliminary evidence shows a dynamic change in facial volume, with an initial decrease in facial volume followed by a rebound effect that demonstrated improvement of facial volume regardless of patient weight change or amount of fat injected 19 months after treatment. Volume improvement occurred to a greater extent in patients under 55 years old, whereas in patients older than 55 volume gradually decreased. To our knowledge, this study represents the first time that progressive improvement in facial volume has been shown 19 months after treatment with a new standardized technique of fat grafting.
View details for DOI 10.1093/asj/sjab379
View details for PubMedID 34724035
- Commentary on: Fat Grafting to Improve Results of Facelift: Systematic Review of Safety and Effectiveness of Current Treatment Paradigms. Aesthetic surgery journal 2021; 41 (1): 13-15
In-Vitro Comparative Examination of the Effect of Stromal Vascular Fraction Isolated by Mechanical and Enzymatic Methods on Wound Healing
AESTHETIC SURGERY JOURNAL
2020; 40 (11): 1232–40
Enzymatic digestion has been the gold standard for stromal vascular fraction (SVF) isolation but remains expensive and raises practical and legal concerns. Mechanical SVF isolation methods have been known to produce lower cell yields, but may potentially produce a more robust product by preserving the extracellular matrix niche.The aim of this study was to compare mechanically dissociated SVF (M-SVF) and enzymatically digested SVF (E-SVF) in terms of wound-healing efficacy.Lipoaspirate was partitioned into 2 equal groups and processed by either mechanical or enzymatic isolation methods. After SVF isolation, cell counts and viabilities were determined by flow cytometry and cell proliferation rates were measured by the WST-1 test. A wound-healing scratch assay test, which is commonly used to model in-vitro wound healing, was performed with both cell cocktails. Collagen type 1 (Col1A) gene expression level, which is known for its role in wound healing, was also measured for both groups.As predicted, E-SVF isolated more cells (mean [standard deviation], 1.74 [3.63] × 106/mL, n = 10, P = 0.015) than M-SVF (0.94 [1.69] × 106/mL, n = 10, P = 0.015), but no significant difference was observed in cell viability. However, M-SVF expressed over 2-fold higher levels of stem cell surface markers and a 10% higher proliferation rate compared with E-SVF. In addition, the migration rate and level of Col1A gene expression of M-SVF were found to be significantly higher than those of E-SVF.Although the cell yield of M-SVF was less than that of E-SVF, M-SVF appears to have superior wound-healing properties.
View details for DOI 10.1093/asj/sjaa154
View details for Web of Science ID 000592519100019
View details for PubMedID 32514571
Facelift With Power-Assisted Dissection: A Preliminary Report.
Aesthetic surgery journal
Subcutaneous elevation of the skin has remained a key component in all facelift techniques.In this preliminary report, the ABC facelift is introduced as a three-step method addressing photodamage, soft tissue laxity, and areas of bone and volume loss.The procedure consists of: (A) Anatomic and regenerative adipose grafting prior to skin elevation; (B) Baraf elevator for takedown of perpendicular subcutaneous fibers following hydro-dissection of the skin flaps with tumescent solution; and (C) Cautery dissection of the SMAS and platysma in the neck.Thirty-four patients, (31 females; 3 male) 50-77 years of age at the date of service, underwent an ABC facelift. Dissection of the skin flaps and SMAS elevation was faster compared to traditional methods, averaging 10-15 minutes per hemiface. Bleeding was reduced (average EBL, 12 ml) and the skin flaps appeared better perfused with less venous engorgement and ecchymosis compared to sharp scissor dissection. In general, patients appeared to have shorter postoperative recovery courses and less social downtime secondary to bruising and edema.The ABC facelift addresses facial laxity, volume loss, and skin aging with three simple steps: anatomic and regenerative fat grafting, combined with power-assisted dissection of the skin and cautery elevation of the SMAS. Further improvements in layer separation using more advanced tools for hydro-dissection are currently being investigated.
View details for DOI 10.1093/asj/sjaa213
View details for PubMedID 32722753
Progressive Improvement in Midfacial Volume 18 to 24 Months After Simultaneous Fat Grafting and Facelift: An Insight to Fat Graft Remodeling
OXFORD UNIV PRESS INC. 2020: 235–42
Although many facelift techniques incorporate fat grafting with tissue repositioning and removal, the intermediate and long-term changes in facial volume after these techniques is unknown. Whereas fillers for facial volume have predictable life spans, we know little about the facial volume changes following fat grafting with facelift surgery.The authors sought to track the short-term and long-term effects on midfacial volume change.We evaluated a subset of patients who were followed by 3-dimensional (3D) photometric imaging 18 to 24 months after facelift with fat grafting to the deep midfacial fat compartments and buccal fat pads. Volume changes were measured preoperatively and postoperatively every 1, 3, 6, 12, 18, and 24 months using the 3D photometry.At the 1- to 2-month follow-up period, average facial volume was 49.60% of the initial fat injected. At the 18- to 24-month follow-up period, average facial volume was 73.64% of the initial fat injected, indicating an increase in midfacial volume. Upon graphing available photometric data, dynamic changes in facial volume were observed. In 5 midfacial zones, facial volume appeared to initially decline (average decline, 49.0% of original fat injection), troughing at 10 months (range, 2-15 months), but later inclined (average increase in volume, 95.9% of original fat injection), peaking around 16 months (range, 4-24 months).Progressive improvement in midfacial volume in part may be explained by the graft replacement theory of Suga and Yoshimura, which suggests that grafted adipose tissue immediately dies after transplantation and is replaced by adipose-derived stem or progenitor cells.
View details for DOI 10.1093/asj/sjy279
View details for Web of Science ID 000515095700008
View details for PubMedID 30335128
Evaluation and accurate diagnoses of pediatric diseases using artificial intelligence
2019; 25 (3): 433-+
Artificial intelligence (AI)-based methods have emerged as powerful tools to transform medical care. Although machine learning classifiers (MLCs) have already demonstrated strong performance in image-based diagnoses, analysis of diverse and massive electronic health record (EHR) data remains challenging. Here, we show that MLCs can query EHRs in a manner similar to the hypothetico-deductive reasoning used by physicians and unearth associations that previous statistical methods have not found. Our model applies an automated natural language processing system using deep learning techniques to extract clinically relevant information from EHRs. In total, 101.6 million data points from 1,362,559 pediatric patient visits presenting to a major referral center were analyzed to train and validate the framework. Our model demonstrates high diagnostic accuracy across multiple organ systems and is comparable to experienced pediatricians in diagnosing common childhood diseases. Our study provides a proof of concept for implementing an AI-based system as a means to aid physicians in tackling large amounts of data, augmenting diagnostic evaluations, and to provide clinical decision support in cases of diagnostic uncertainty or complexity. Although this impact may be most evident in areas where healthcare providers are in relative shortage, the benefits of such an AI system are likely to be universal.
View details for DOI 10.1038/s41591-018-0335-9
View details for Web of Science ID 000460643100021
View details for PubMedID 30742121
Ethnic Rhinoplasty in Female Patients: The Neoclassical Canons Revisited
AESTHETIC PLASTIC SURGERY
2018; 42 (2): 565–76
Despite the substantial amount of research devoted to objectively defining facial attractiveness, the canons have remained a paradigm of aesthetic facial analysis, yet their omnipresence in clinical assessments revealed their limitations outside of a subset of North American Caucasians, leading to criticism about their validity as a standard of facial beauty. In an effort to introduce more objective treatment planning into ethnic rhinoplasty, we compared neoclassical canons and other current standards pertaining to nasal proportions to anatomic proportions of attractive individuals from seven different ethnic backgrounds.Beauty pageant winners (Miss Universe and Miss World nominees) between 2005 and 2015 were selected and assigned to one of seven regionally defined ethnic groups. Anteroposterior and lateral images were obtained through Google, Wikipedia, Miss Universe, and Miss World Web sites. Anthropometry of facial features was performed via Adobe Photoshop TM. Individual facial measurements were then standardized to proportions and compared to the neoclassical canons.Our data reflected an ethnic-dependent preference for the multiple fitness model. Wide-set eyes, larger mouth widths, and smaller noses were significantly relevant in Eastern Mediterranean and European ethnic groups. Exceptions lied within East African and Asian groups.As in the attractive face, the concept of the ideal nasal anatomy varies between different ethnicities. Using objective criteria and proportions of beauty to plan and execute rhinoplasty in different ethnicities can help the surgeon plan and deliver results that are in harmony with patients' individual background and facial anatomy.This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors www.springer.com/00266 .
View details for DOI 10.1007/s00266-017-1051-4
View details for Web of Science ID 000426847500031
View details for PubMedID 29273934
Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning.
2018; 172 (5): 1122–31.e9
The implementation of clinical-decision support algorithms for medical imaging faces challenges with reliability and interpretability. Here, we establish a diagnostic tool based on a deep-learning framework for the screening of patients with common treatable blinding retinal diseases. Our framework utilizes transfer learning, which trains a neural network with a fraction of the data of conventional approaches. Applying this approach to a dataset of optical coherence tomography images, we demonstrate performance comparable to that of human experts in classifying age-related macular degeneration and diabetic macular edema. We also provide a more transparent and interpretable diagnosis by highlighting the regions recognized by the neural network. We further demonstrate the general applicability of our AI system for diagnosis of pediatric pneumonia using chest X-ray images. This tool may ultimately aid in expediting the diagnosis and referral of these treatable conditions, thereby facilitating earlier treatment, resulting in improved clinical outcomes. VIDEO ABSTRACT.
View details for PubMedID 29474911
Regenerative Cells For Facial Surgery: Biofilling and Biocontouring
AESTHETIC SURGERY JOURNAL
2017; 37: S16–S32
Zuk et al in 2001 identified stem and regenerative cells within the stromal vascular fraction of fat. In preclinical studies, these cells appeared to stimulate angiogenesis and reduce inflammation, and soon thereafter, clinical use of stromal vascular fraction (SVF) evolved as researchers such as Rigotti, Coleman, Mojallal, our group, and others demonstrated that fat can be used for both therapeutic and aesthetic indications. The regenerative effects of fat and its contents on facial aesthetics have been shown at the histologic and cellular level. Regeneration of elastin and collagen fibers as well as improvement in capillary density and reduction of inflammation have been reported. We review our current approach to the use of regenerative cells and different types of fat grafts in facial surgery. The fat graft is classified, both from a regenerative point of view as well as a tissue product that can be modified into different tissue characteristics, depending on the area and condition treated. Clinical use of SVF enriched fat, millifat, microfat, and nanofat grafts as well as composite fat grafts are reviewed. Based on clinical experience and evidence to date, it appears that the regenerative effects seen with the use of SVF in aesthetic surgery are modest, but there appear to be definite histologic findings of regeneration. These improvements may not be clinically apparent to a patient when cell enriched fat grafts are compared to fat grafts alone. However, the subtle changes seen in histology may be cumulative over time. Three types of fat grafts are defined: millifat (parcel size 2.4<), microfat (1.2<), and nanofat (400-600 μm). Each are characterized by their injectability ratings and emulsification parcel size as well as amount of sSVF cells. Newer concepts of periosteal fat grafting, buccal fat pad grafting, pyriform aperture fat grafting, intraorbital fat grafting, and nanofat grafting are discussed. Composite fat grafts are presented as a new concept as is biofilling and biocontouring. The use of regenerative cells in facial surgery is evolving rapidly. Our understanding of the anatomic changes that occur with aging has become more precise and our ability to target histologic changes seen with aging has become more effective. Deep fat compartment grafting, superficial fat grafting, nanofat, and SVF are becoming important components of contemporary facial rejuvenation. The use of regenerative approaches in facial rejuvenation is a logical step in changing the paradigm from surgical treatment of aging to a more proactive prevention and maintenance approach that keeps up with changes in the tissues as they age.
View details for DOI 10.1093/asj/sjx078
View details for Web of Science ID 000424144500004
View details for PubMedID 29025218
Buccal Fat Pad Augmentation for Facial Rejuvenation
PLASTIC AND RECONSTRUCTIVE SURGERY
2017; 139 (6): 1273E–1276E
The buccal space, with its fat pad, is a valuable, overlooked target in facial rejuvenation procedures. The authors identified a specific group of patients who have normal or prominent malar projection in the presence of atrophy of the buccal fat pad, with or without prominent gonial angles. Eight of 24 prospectively studied patients (Biomedical Research Institute of America) who had fat grafts and face lifts received an average of 2.7 ml of fat transferred into the buccal space. Immediate visual correction of the buccal depression was noted. No overcorrection was carried out. None of the eight patients suffered an adverse event from transoral buccal space fat grafting. Persistent facial volume in this area has been noted up to 24 months after treatment. In patients with buccal fat pad atrophy, fat grafting into the buccal space can be safely performed through an intraoral approach.
View details for DOI 10.1097/PRS.0000000000003384
View details for Web of Science ID 000404715000006
View details for PubMedID 28538560