United States

Background
Pulmonary hypertension (PH) in heart failure with preserved ejection fraction (HFpEF; PH-HFpEF) is a relatively newly recognized condition that poses a leading healthcare burden. The development of PH is the strongest predictor of adverse outcomes in HFpEF patients, with a staggering 60% 5-year mortality rate. Incomplete understanding of pathophysiology, ineffective therapies, and limited non-invasive diagnostic methods contribute to this growing epidemic. HFpEF patients initially develop reversible isolated postcapillary PH (ipc-PH) from passively transmitted backward pressures. If not diagnosed promptly, ipc-PH can transform into pre- and postcapillary PH (cpc-PH), characterized by irreversible pulmonary vascular remodeling. Progression to cpc-PH is not explained by traditional risk factors alone, suggesting the need to examine novel regulatory mechanisms. 
Polyunsaturated Fatty Acid (PUFA) metabolites have emerged as pivotal players in cardiovascular health by regulating balance between anti-inflammatory, pro-inflammatory, and pro-resolutory lipid mediators. Previous research has revealed that an imbalance of these lipids leads to metabolic syndrome, an established risk factor of PH-HFpEF. We aimed to identify PUFA-derived lipid mediators that can predict PH in HFpEF patients.
Methods
A single center prospective cohort study was conducted on 88 enrolled patients with a new diagnosis of HFpEF who were grouped into PH subtypes post-diagnostic right heart catheterization: HFpEF without PH (control, n=40), HFpEF with ipc-PH (ipc-PH-HFpEF, n=30), and HFpEF with cpc-PH (cpc-PH-HFpEF, n=18). Venous samples were collected during catheterization. Levels of 143 PUFA metabolites were analyzed using mass spectroscopy with Multiple Reaction Monitoring. Regression models assessed which PUFA metabolites predicted the PH subtypes. Statistics: p&lt;0.05.
Results
Clinical demographics were similar among all groups. Ipc-PH-HFpEF was characterized by low pro-resolutory 7(S)-Maresin1 (p=0.0003), low anti-inflammatory 11(12)-EpETrE (p=0.02), and low anti-inflammatory 8(S)-HETrE (p=0.02) compared to control. These metabolites collectively predicted ipc-PH-HFpEF with 69% diagnostic accuracy. Cpc-PH-HFpEF was distinguishable from control by low pro-resolutory 7(S)-Maresin1 (p=0.004), high pro-inflammatory 5,6-DiHETrE (p=0.001), and high pro-inflammatory tetranor prostaglandin E2 (p=0.007). Collectively, these metabolites predicted cpc-PH-HFpEF with 83% diagnostic accuracy. High pro-resolutory 12(13)-EpOME (p=0.013) distinguished cpc-PH-HFpEF from ipc-PH-HFpEF, with a 75% predictive value. Interestingly, low pro-resolutory 7(S)-Maresin1 yielded the greatest predictive value of 67% in predicting cpc-PH-HFpEF compared to all groups. 
Conclusion
Our findings demonstrate that distinct PUFA inflammatory mediators are associated with PH pathogenesis in HFpEF. This novel lipidomics framework introduces new non-invasive biomarkers to predict PH and facilitates further experimental study of innovative therapeutic molecular targets.

AMA Research Challenge 2023

The Lipid Link: Predicting Pulmonary Hypertension in Heart Failure with Preserved Ejection Fraction

Welcome to the largest national, multi-specialty research event **featuring research from 750 medical students, residents and fellows, and international medical graduates.**


#### Event Details
The 2022 American Medical Association Research Challenge includes a poster symposium hall and a semifinals hall with the top scored research. Log in at any time throughout the event to:
* **View posters and presentations** on a variety of topics and specialties
* **Score posters in the semifinals** to help decide the top five finalists (AMA member exclusive opportunity)
* **Connect with participants** and provide feedback to help advance their research

At the conclusion of this event, the AMA will announce the top five finalists who will advance to the AMA Research Challenge finals, present their research to an elite panel of judges and compete to win a $10,000 grand prize sponsored by Laurel Road.
 

#### Attend Live Forums
**Oct. 20, 6 — 7 p.m. Central**
 **How to plan a career in academic medicine** 
 Learn how to plan a career in academic medicine and get your questions answered. [Access Here](https://underline.io/events/363/lounge)
 
 **Speakers**
![](https://assets.underline.io/uploads/markdown_image/1/image/d5adb133dfc58eb0a6d469e9cedcd5d4.jpg)
Ricardo Correa, MD, EdD
![](https://assets.underline.io/uploads/markdown_image/1/image/5f9437ab87861538bf02b9ca7c0d926e.jpg)
Stuart M. Greenstein, MD
![](https://assets.underline.io/uploads/markdown_image/1/image/05b1b637c99286d558c371f8e8b185ce.jpg)
Stephanie Strohbeen, MD
 
 **Oct. 22, 11 a.m. — Noon Central**
 **How to get published**
 Learn tips to get your research published and get your questions answered. [Access Here](https://underline.io/events/363/lounge)
 
 **Speakers**
![](https://assets.underline.io/uploads/markdown_image/1/image/8ce6235e957d31cb5e6f9097cc6f6972.jpg)
Jessica Li, MD/PhD Candidate
![](https://assets.underline.io/uploads/markdown_image/1/image/9950ef2e0237f54cb3d8280334d42491.jpg)
Charles Lopresto, DO

### Sponsor
AMA would like to thank Laurel Road for sponsoring a $10,000 grand prize for the winner of the AMA Research Challenge. Laurel Road is not involved in the judging or scoring process to select the winner. The winner will be announced on Dec. 7 during the AMA Research Challenge finals. Payment of the grand prize will be directly from Laurel Road. See the AMA Research Challenge Official Rules for terms and conditions.

![](https://assets.underline.io/uploads/markdown_image/1/image/611e331d4a0eba0920f240cfc04b4d77.png)

**There is no registration fee for this event! **

Register to explore research in a variety of topics. AMA members get exclusive access to score posters in the semifinals.

**Please use the link below to register for free if you have not already done so:**

https://www.ama-assn.org/about/events/ama-research-challenge

Registration Is Required

AMA Research Challenge 2022

Welcome to the largest national, multi-specialty research event featuring research from 750 medical students, residents and fellows, and international medical graduates.


Background
Pulmonary hypertension (PH) in heart failure with preserved ejection fraction (HFpEF; PH-HFpEF) is a relatively newly recognized condition that poses a leading healthcare burden. The development of PH is the strongest predictor of adverse outcomes in HFpEF patients, with a staggering 60% 5-year mortality rate. Incomplete understanding of pathophysiology, ineffective therapies, and limited non-invasive diagnostic methods contribute to this growing epidemic. HFpEF patients initially develop reversible isolated postcapillary PH (ipc-PH) from passively transmitted backward pressures. If not diagnosed promptly, ipc-PH can transform into pre- and postcapillary PH (cpc-PH), characterized by irreversible pulmonary vascular remodeling. Progression to cpc-PH is not explained by traditional risk factors alone, suggesting the need to examine novel regulatory mechanisms. 
Polyunsaturated Fatty Acid (PUFA) metabolites have emerged as pivotal players in cardiovascular health by regulating balance between anti-inflammatory, pro-inflammatory, and pro-resolutory lipid mediators. Previous research has revealed that an imbalance of these lipids leads to metabolic syndrome, an established risk factor of PH-HFpEF. We aimed to identify PUFA-derived lipid mediators that can predict PH in HFpEF patients.
Methods
A single center prospective cohort study was conducted on 88 enrolled patients with a new diagnosis of HFpEF who were grouped into PH subtypes post-diagnostic right heart catheterization: HFpEF without PH (control, n=40), HFpEF with ipc-PH (ipc-PH-HFpEF, n=30), and HFpEF with cpc-PH (cpc-PH-HFpEF, n=18). Venous samples were collected during catheterization. Levels of 143 PUFA metabolites were analyzed using mass spectroscopy with Multiple Reaction Monitoring. Regression models assessed which PUFA metabolites predicted the PH subtypes. Statistics: p<0.05.
Results
Clinical demographics were similar among all groups. Ipc-PH-HFpEF was characterized by low pro-resolutory 7(S)-Maresin1 (p=0.0003), low anti-inflammatory 11(12)-EpETrE (p=0.02), and low anti-inflammatory 8(S)-HETrE (p=0.02) compared to control. These metabolites collectively predicted ipc-PH-HFpEF with 69% diagnostic accuracy. Cpc-PH-HFpEF was distinguishable from control by low pro-resolutory 7(S)-Maresin1 (p=0.004), high pro-inflammatory 5,6-DiHETrE (p=0.001), and high pro-inflammatory tetranor prostaglandin E2 (p=0.007). Collectively, these metabolites predicted cpc-PH-HFpEF with 83% diagnostic accuracy. High pro-resolutory 12(13)-EpOME (p=0.013) distinguished cpc-PH-HFpEF from ipc-PH-HFpEF, with a 75% predictive value. Interestingly, low pro-resolutory 7(S)-Maresin1 yielded the greatest predictive value of 67% in predicting cpc-PH-HFpEF compared to all groups. 
Conclusion
Our findings demonstrate that distinct PUFA inflammatory mediators are associated with PH pathogenesis in HFpEF. This novel lipidomics framework introduces new non-invasive biomarkers to predict PH and facilitates further experimental study of innovative therapeutic molecular targets.

poster

Welcome to the **largest national, multi-specialty research** event featuring research from nearly 700 medical students, residents, fellows, and international medical graduates.

Use the buttons below or navigation menu to access the event.
 


[![](https://assets.underline.io/uploads/markdown_image/1/image/3e33a8c754cc49610b30950617d813e7.png)](https://underline.io/events/434/sessions?searchGroup=all)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/551404d429c4e274f9a54cbdd7081918.png)](https://underline.io/events/434/posters?searchGroup=all)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/677d92f566b880cebd36905fc738fc10.png)](https://underline.io/events/434/lounge)
 
[![](https://assets.underline.io/uploads/markdown_image/1/image/c7392833c7261c3874c5b43fa2f4df19.png)](https://underline.io/events/434/help-desk)
 

#### Event Details

The 2023 American Medical Association Research Challenge includes a poster symposium hall and a semifinals hall with the top scored research. **Log in at any time throughout the event to:**

* **View posters and presentations** on a variety of topics and specialties
* **Score posters in the semifinals** to help decide the top five finalists (AMA member exclusive opportunity)
* **Connect with participants** and provide feedback to help advance their research
* **Attend education sessions** with physician experts on key research topics

At the conclusion of this event, the AMA will announce the top five finalists who will advance to the AMA Research Challenge finals, present their research to an elite panel of judges, and compete to win a $10,000 grand prize sponsored by Laurel Road. 

### Grand Prize Sponsor

AMA would like to thank Laurel Road for sponsoring a $10,000 grand prize for the winner of the AMA Research Challenge. Laurel Road is not involved in the judging or scoring process to select the winner. The winner will be announced on February 4, 2024 during the AMA Research Challenge finals. Payment of the grand prize will be directly from Laurel Road. See the AMA Research Challenge Official Rules for terms and conditions.

![](https://assets.underline.io/uploads/markdown_image/1/image/611e331d4a0eba0920f240cfc04b4d77.png)

**There is no registration fee for this event! **

Register to explore research in a variety of topics. AMA members get exclusive access to score posters in the semifinals.

**Please use this link [here](https://www.ama-assn.org/about/events/ama-research-challenge) to register for free.**

Join the AMA Research Challenge poster symposium and semifinals to explore top research posters, score posters in the semifinals (an AMA member exclusive opportunity) and attend education sessions with experienced physicians to learn tips to advance your research and career. 

**Scoring is only possible in the semifinals hall**

**Abstract:**



The Impact of Insurance Status and Surgical Approach on Clinical Outcomes of Segmental Colectomy


Background: Scleroderma is a rare, autoimmune connective tissue disorder characterized by fibrotic hardening and tightening of the skin. Scleroderma has developed as a drug-induced and paraneoplastic phenomenon, but there has been little discussion on scleroderma associated with COVID-19. We present an updated review of scleroderma after COVID-19 infection and vaccination.
Methods: Literature searches were conducted on MEDLINE (PubMed), Embase, Scopus, and Google Scholar from 2019 to January 2023. Thirteen articles were selected based on subject relevance, and references within articles were also screened. 
Results: As of January 2023, there have been four cases of scleroderma after COVID-19 infection (Mage = 54.50 years, Rage = 47-61 years, Male:Female = 1:3) and ten cases of scleroderma after COVID-19 vaccination (Mage = 62.8 years, Rage = 45-73 years, Male:Female = 1:9). Moderna’s Spikevax accounted for two cases, Pfizer-BioNTech’s Tozinameran accounted for seven cases, and Oxford-AstraZeneca’s Vaxzevria accounted for one case. 
Conclusions: Hypotheses for the pathogenesis of scleroderma after COVID-19 infection and vaccination include molecular mimicry, cytokine activation, and endothelial injury, and we advise clinicians to monitor for this rare potential complication. However, the benefits of the COVID-19 vaccines still greatly outweigh the risks.

Scleroderma after COVID-19 Infection and Vaccination

PEMF has been shown to influence various signaling molecules involved in wound healing, including MMP-2, IL-6, and TGF-β. Studies have begun to explore the use of PEMF in other diseases, such as incision wound repair, diabetes-related foot ulcers, and pressure ulcers. The cellular response to PEMF is highly variable and likely influenced by multiple factors: frequency, duration, tissue type, stage of wound repair, and field strength. Before PEMF can be used in clinical practice, further research using standardized experimental guidelines is needed to determine precisely how different variables influence PEMF therapy. 


An Integrative Review Of Pulsed Electromagnetic Field Therapy And Wound Healing 


Linear IgA bullous dermatosis (LABD) is a rare autoimmune blistering disorder impacting children and adults. We aim to report the unifying and unique clinical features as well as treatment options for LABD in childhood.
A retrospective chart review was performed for pediatric patients with linear IgA bullous dermatosis our institution. Ten patients (6 male, 4 female) met the inclusion criteria and were included in the study. The mean time to diagnosis was 4.8 months and mean disease duration was 38 months (range: 6 months – 10 years). Dapsone, systemic glucocorticoids, and topical glucocorticoids were among the most common treatments. All patients recovered well and eventually experienced complete remission of their disease.
In conclusion, a variety of medications can be used in the management of LABD in children. Dapsone and systemic corticosteroids can be effective and reliable first-line treatments for pediatric LABD. Immunosuppressants may be used successfully as second-line treatment or steroid-sparing therapy. IVIG combined with prednisone was effective in the management of neonatal LABD.

Treatment of linear IgA bullous dermatosis of childhood at a tertiary referral center

Revealing the interactions of antihistamine with retinoic acid receptor beta (RARB) by molecular dynamics simulations and genome-wide meta-analysis.

Background
Vitiligo is a common autoimmune condition characterized by patchy skin depigmentation, affecting nearly 3 million individuals in the United States with nearly half of cases in both adolescents and adults remaining undiagnosed [1,2]. This condition is often associated with other autoimmune and connective tissue comorbidities and mental health problems, further complicating patients' overall health and quality of life [3,4]. Recent studies have also suggested a potential correlation between vitiligo and an increased risk of obesity and renal diseases [3]. Renal disease patients often require dialysis or kidney transplant as part of their treatment and thus, these individuals may be at higher risk of systemic infections due to various factors, including vascular and catheter access and immunosuppression [5,6]. Due to the disrupted epidermal barrier composition and recovery in vitiligo patients, it is reasonable to hypothesize that these patients undergoing dialysis may be more susceptible to systemic infections [7,8]. However, there is a lack of research exploring the relationship between dialysis patients with vitiligo and their risk of infection. To address this knowledge gap, we conducted a retrospective analysis utilizing data from the United States Renal Data System (USRDS) to determine if vitiligo presents as a risk factor for increased risk of bacteremia, septicemia, cellulitis, herpes zoster, and conjunctivitis.

Methods
All end-stage renal disease (ESRD) patients in the USRDS who started dialysis between 2004 and 2019 were eligible for inclusion in the study. Those who were less than 18 years or greater than 100 years of age, or had missing or unknown data on age, race, sex, ethnicity, access type or dialysis type were excluded. The total sample size was 1,526,270. Infectious outcomes of interest included bacteremia, septicemia, cellulitis, herpes zoster, and conjunctivitis. Among those included in the sample, a diagnosis of vitiligo after the incident date of dialysis was determined. All statistical analysis was performed using SAS 9.4. Descriptive statistics on all variables were determined overall, by vitiligo status, and by each type of infection.

Results
A total of 676 subjects had a vitiligo diagnosis. Based on a simple logistic regression model, vitiligo was associated with an increased risk of bacteremia (adjusted relative risk = 1.28), septicemia (1.20), cellulitis (1.27), and herpes zoster (1.69) but not conjunctivitis (1.22). Controlling for demographics and clinical covariates, vitiligo was no longer significantly associated with septicemia.

Conclusion
These results indicate that vitiligo-ESRD patients may have an increased risk of bacteremia, cellulitis, and herpes zoster but not significantly associated with septicemia and conjunctivitis. These findings justify further research into tailored care plans for patients with vitiligo receiving dialysis and improved prevention and monitoring of infection in these patients.

1. Patel R, Pandya AG, Sikirica V, Gandhi K, Daniel SR, Anastassopoulos KP, Yamaguchi Y, Napatalung L, Baik R, Ezzedine K. Prevalence of Vitiligo among Children and Adolescents in the United States. Dermatology. 2023;239(2):227-234. doi: 10.1159/000528180. Epub 2023 Jan 11. PMID: 36630928; PMCID: PMC10210084.
2. Gandhi K, Ezzedine K, Anastassopoulos KP, Patel R, Sikirica V, Daniel SR, Napatalung L, Yamaguchi Y, Baik R, Pandya AG. Prevalence of Vitiligo Among Adults in the United States. JAMA Dermatol. 2022 Jan 1;158(1):43-50. doi: 10.1001/jamadermatol.2021.4724. PMID: 34787670; PMCID: PMC8600454.
3. Al Houssien AO, Al Houssien RO, Al Ajroush W, Al Kahtani HS. Chronic diseases among vitiligo patients. A case control study. Saudi Med J. 2017 Apr;38(4):400-404. doi: 10.15537/smj.2017.4.17551. PMID: 28397947; PMCID: PMC5447193.
4. Lee JH, Ju HJ, Seo JM, Almurayshid A, Kim GM, Ezzedine K, Bae JM. Comorbidities in Patients with Vitiligo: A Systematic Review and Meta-Analysis. J Invest Dermatol. 2023 May;143(5):777-789.e6. doi: 10.1016/j.jid.2022.10.021. Epub 2022 Nov 28. PMID: 36574529. 
5. Ramakrishna, P., & Rajni, T. (2014). Psychiatric morbidity and quality of life in vitiligo patients. Indian journal of psychological medicine, 36(3), 302–303. https://doi.org/10.4103/0253-7176.135385
6. Levey AS, Coresh J. Chronic kidney disease. The lancet. 2012;379 (9811):165-180. https://doi.org/10.1016/S0140-6736(11)60178-5
7. Suzuki M, Satoh N, Nakamura M, Horita S, Seki G, Moriya K. Bacteremia in hemodialysis patients. World J Nephrol. 2016 Nov 6;5(6):489-496. doi: 10.5527/wjn.v5.i6.489. PMID: 27872830; PMCID: PMC5099594.
8. Kovacs, D., et al., Altered epidermal proliferation, differentiation, and lipid composition: Novel key elements in the vitiligo puzzle. Sci Adv, 2022. 8(35): p. eabn9299.


Assessment of Infection Risk in vitiligo patients undergoing dialysis for end-stage renal disease: A retrospective cohort study

This study introduces an advanced software tool designed for personalized diagnosis and comprehensive guidance in both the medical and surgical management of Androgenetic Alopecia (AGA). Developed through machine learning techniques, the software provides enhanced diagnostic accuracy and offers individualized follicular distribution guidance. The research is built upon a systematic review of 40 studies encompassing hair density measurements across multiple ethnicities. The software demonstrates good predictive accuracy in different scalp regions, with R2 values ranging from 0.42 to 0.67 and MAE values varying from 22.70 to 38.04 hairs/cm2. Compared to current clinical solutions, this software enables longitudinal response to treatment monitoring and delivers a personalized, data-driven diagnostic approach. It addresses existing gaps in the field by generating reliable predictions of normative scalp hair density, thereby assisting in tailored surgical planning and medical management. Future work aims to refine the model through real-world testing and integration of additional clinical variables.

Advanced Software for Personalized Diagnosis and Comprehensive Guidance in Medical and Surgical Management of Androgenetic Alopecia

Infection with SARS-COV-2 has shown the ability to damage nearly every organ system in the human body, including the largest organ - the skin. Granuloma annulare (GA) is a rare rash with unclear etiology that presents as annular, erythematous papules or plaques with central clearing. To our knowledge, there has only been one reported case of GA associated with COVID-19 vaccination published thus far. We present the cases of a 54-year-old female and a 66-year-old male who developed generalized GA and localized GA, respectively, following the administration of a COVID-19 vaccine, which worsened with subsequent boosters. This paper reviews the existing literature on GA associated with COVID-19 infection and vaccination, as well as the possible immunological mechanisms underlying the development of GA following vaccination. We especially note the striking similarities in disease morphology and temporal association with COVID-19 vaccination between our 54-year-old female and the first reported case of GA following COVID-19 vaccination. Despite the temporal association between COVID-19 vaccination and the development of GA, the exact causative relationship remains unclear. Further studies are needed to elucidate the underlying mechanisms and determine the true incidence and risk factors for GA associated with COVID-19 vaccination.

Granuloma Annulare Onset Following COVID-19 Vaccination

Background: 
Sunscreen use in people of color is less common than sunscreen use in people with lighter pigmentation, often due to low perceived risk. However, it is still recommended that people of color wear sunscreen to lower the risk of skin cancer, dyspigmentation and pigmentary disorders, and sunburns. Thus, public health efforts should be utilized to improve sunscreen use in people of color. TikTok, a popular social media platform, has been used by health professionals to disseminate educational information and for the purpose of public health outreach. This study looks at the discussion of sunscreen use in this population on this popular social media platform with the goal of understanding what information is being disseminated by and for this target population.

Objective: 
To understand the discussion of sunscreen-related topics on popular social media created for or by people of color.

Methods: 
The term “sunscreen” was searched on TikTok and the top 100 related hashtags were reviewed. Of these two hashtags, #SunscreenforBlackPeople and #Sunscreen for POC, were directed towards people of color. The top 50 videos for each of those hashtags were reviewed for content, creator characteristics including Fitzpatrick skin type and qualifications, and qualities of sunscreen discussed in the video. Analysis was performed to identify key themes in the videos.

Results: 
Most of the content creators discussing the topic of sunscreen for people of color were influencers without medical background. The majority of videos were focused on recommending or sampling different sunscreen brands. Common criteria for reviewing sunscreen brands included presence of “whitecasting”, the final finished look after sunscreen application, cost, and sunscreen density in regard to if the sunscreen feels heavy or lightweight. Only 5 of the top 50 videos contained an educational component. Educational topics included how much sunscreen to put on, importance of reapplication, and reasons to wear sunscreen. Additionally, few videos discussed reasons people of color should wear sunscreen. Of the reasons to wear sunscreen, most commonly discussed were anti-aging and prevention of hyperpigmentation.

Conclusions: 
The discussion of sunscreen for people of color is limited on TikTok. Of the top posts, few contained educational information and the majority were created by dermatologists. Given the popularity of TikTok and its use to promote other sources of health information, there is room to improve the outreach related to sunscreen on the popular social media platform. 


Analysis of Sunscreen-Related Posts Directed Toward People of Color (POC) on TikTok

Background 

Early melanoma detection has profound clinical impact with distant stages having a
32% 5-year relative survival rate. Traditionally, the automation of melanoma detection prior to biopsy has relied on broad-spectrum photography, thresholding in the frequency domain or analysis of electrical impedance. The advent of deep learning (DL) has enabled automation of dermoscopy.
However, most existing end-to-end DL approaches require annotated data, which is time-consuming to produce and cannot propose novel predictive markers. To address this, we utilized the Semantic Clustering by Adopting Nearest Neighbors (SCAN) algorithm, an unsupervised learning approach that decouples feature learning and clustering, enabling the automated detection of dermatoscopic features that predict disease.

Methods 

We employed the SCAN algorithm to analyze 7991 training and 2024 testing
dermatoscopic images of melanoma or benign nevi from the International Skin Imaging Collaboration dataset. Images are almost all Fitzpatrick type I-III. The model was trained to learn semantically meaningful features that were employed to build clusters of similar images.

Results 

The final clusters exhibited varying levels of homogeneity, with several clusters composed exclusively of one class (melanoma/benign nevi). Several highly predictive clusters for melanoma showed an absence of color uniformity, which is a Menzies method criterion to establish melanoma diagnosis. This indicates latent-space morphology congruent with established evidence-based practice.

Conclusion 

The application of the SCAN algorithm to dermatoscopic images presents a promising methodology for unsupervised learning in melanoma detection. Previous work has shown that AI models that offer explanations to clinicians, such as photos of similar lesions in that continuous area of the model’s latent space, boost physician satisfaction. The FDA approval process also prefers explainable paradigms to ensure model predictability spanning the input space. This study presents an unsupervised approach to melanoma detection via dermoscopy, which enables explainable AI and automated detection of features that predict disease. By providing explainability, the research addresses a key challenge in machine learning paradigms’ FDA approval pathway. Future research is warranted to see if analysis of nevi on dark skin (Fitzpatrick type >3) demonstrates alternate dermoscopic features, as has been previously reported in dermoscopic
literature.

Premium content

Next from AMA Research Challenge 2023

The Impact of Insurance Status and Surgical Approach on Clinical Outcomes of Segmental Colectomy

Similar lecture

Left Atrial Strain Echocardiography May Be Correlated with Coronary Microvascular Dysfunction