COVID-2019 Alert

Information about the 2019 Novel Coronavirus. Read the latest >

Información sobre el coronavirus 2019 (COVID-19). Aprenda más >


Justin Ko, MD

  • No Image



Work and Education

Professional Education

Tufts University, Boston, MA, 2008


St Luke's Roosevelt Hosp Center, New York, NY, 2009


Massachusetts General Hospital, Boston, MA, 2012

Board Certifications

Dermatology, American Board of Dermatology

All Publications

Development and validation of the Brigham Eyelash Tool for Alopecia (BELA): A measure of eyelash alopecia areata. Journal of the American Academy of Dermatology Manjaly, P., Li, S. J., Tkachenko, E., Ko, J. M., Liu, K. J., Scott, D. A., Senna, M. M., Joyce, C. J., Mostaghimi, A., Huang, K. P. 2021

View details for DOI 10.1016/j.jaad.2020.06.1034

View details for PubMedID 33741177

TrueImage: A Machine Learning Algorithm to Improve the Quality of Telehealth Photos. Pacific Symposium on Biocomputing. Pacific Symposium on Biocomputing Vodrahalli, K., Daneshjou, R., Novoa, R. A., Chiou, A., Ko, J. M., Zou, J. 2021; 26: 22031


Telehealth is an increasingly critical component of the health care ecosystem, especially due to the COVID-19 pandemic. Rapid adoption of telehealth has exposed limitations in the existing infrastructure. In this paper, we study and highlight photo quality as a major challenge in the telehealth workflow. We focus on teledermatology, where photo quality is particularly important; the framework proposed here can be generalized to other health domains. For telemedicine, dermatologists request that patients submit images of their lesions for assessment. However, these images are often of insufficient quality to make a clinical diagnosis since patients do not have experience taking clinical photos. A clinician has to manually triage poor quality images and request new images to be submitted, leading to wasted time for both the clinician and the patient. We propose an automated image assessment machine learning pipeline, TrueImage, to detect poor quality dermatology photos and to guide patients in taking better photos. Our experiments indicate that TrueImage can reject ~50% of the sub-par quality images, while retaining ~80% of good quality images patients send in, despite heterogeneity and limitations in the training data. These promising results suggest that our solution is feasible and can improve the quality of teledermatology care.

View details for PubMedID 33691019

Bridging to a selective Janus kinase 1 inhibitor in severe atopic dermatitis: An instructive case with upadacitinib. JAAD case reports Nguyen, J., Chen, J. K., Honari, G., Pol-Rodriguez, M., Ko, J. M., Chiou, A. S. 2021; 7: 6567

View details for DOI 10.1016/j.jdcr.2020.10.023

View details for PubMedID 33354610

Brigham Eyebrow Tool for Alopecia: A Reliable Assessment of Eyebrow Alopecia Areata. The journal of investigative dermatology. Symposium proceedings Tkachenko, E., Huang, K. P., Ko, J. M., Liu, K. J., Scott, D. A., Senna, M. M., Li, S. J., Joyce, C. J., Mostaghimi, A. 2020; 20 (1): S41S44


There are no tools to evaluate eyebrow involvement in patients with alopecia areata. We developed and assessed the reliability of the Brigham Eyebrow Tool for Alopecia (BETA) as a quantitative evaluation of eyebrow alopecia areata. BETA uses facial landmarks of eyebrow anatomy and is calculated using surface area and density. A total of 50 eyebrow images with varying levels of hair loss were distributed to six board-certified dermatologists at three academic medical centers with standardized instructions and examples. Interrater and intrarater reliability were calculated using intraclass correlation coefficients (ICCs). BETA demonstrated high interrater (ICC= 0.88, confidence interval= 0.83-0.92 right eyebrow scores and ICC= 0.90, confidence interval= 0.85-0.94 left eyebrow scores) and intrarater (ICC= 0.90, confidence interval= 0.85-0.93 right eyebrow scores and ICC= 0.91, confidence interval= 0.87-0.94 left eyebrow scores) reliability. When measured in the same patient with varying degrees of hair loss over time, BETA demonstrated sensitivity to change. BETA is a simple and reliable objective assessment of eyebrow alopecia areata. BETA is easy-to-use and quick to calculate, making it feasible for a variety of clinical and research settings. Although developed for alopecia areata, we hope that BETA will be investigated in other etiologies of eyebrow alopecia to serve as a universal tool for monitoring disease progression, improvement, and response to treatment.

View details for DOI 10.1016/j.jisp.2020.06.001

View details for PubMedID 33099383

Eyebrows Are Important in the Treatment of Alopecia Areata. The journal of investigative dermatology. Symposium proceedings Liu, L. Y., King, B. A., Ko, J. M. 2020; 20 (1): S37S40


Alopecia areata affects not only scalp hair but also other sites of body hair, including eyebrows. Our objective was to investigate the importance of eyebrows in the treatment goals of patients with alopecia areata. Through an online questionnaire, subjects were asked to assess satisfaction with the visually depicted level of response to treatment, using edited photographs depicting a range of eyebrows and scalp hair growth. The questionnaire was completed by 1,741 adults. Absent or partial growth of eyebrows and scalp hair elicited <25% satisfaction. Images depicting either complete eyebrows or complete scalp hair achieved satisfaction in >50% of participants. More participants were satisfied with complete eyebrows and no scalp hair (69%) than complete eyebrows and partial scalp hair (51%). Only when both eyebrows and scalp hair were completely regrown did extreme satisfaction levels reach 90.4%. Limitations include the online nature of the survey, lack of control group, and self-reported severity of alopecia areata in participants. These results suggest that eyebrows may be as important as scalp hair for patients assessing theoretical responses to treatment for alopecia areata. Future clinical studies should consider growth of eyebrows as an outcome measure on par with scalp hair growth.

View details for DOI 10.1016/j.jisp.2020.04.006

View details for PubMedID 33099382

Burden of Illness in Alopecia Areata: A Cross-Sectional Online Survey Study. The journal of investigative dermatology. Symposium proceedings Mesinkovska, N., King, B., Mirmirani, P., Ko, J., Cassella, J. 2020; 20 (1): S62S68


Previous QOL and disease burden studies have not captured all relevant aspects of living with alopecia areata (AA). To better understand the burden and everyday experience of living with moderate-to-severe AA, a cross-sectional, online, quantitative-qualitative survey was developed to assess symptoms, relationships, productivity, treatments, and financial burden. Adult patients were recruited from the National Alopecia Areata Foundation database. Data were analyzed descriptively. A total of 216 patients completed the survey. Most were female (83%), aged 45 years (59%), and white (78%). Nearly 2 of 3 respondents (62%) made different major life decisions (regarding relationships, education, or career) owing to AA. Most respondents (85%) stated coping with AA as a daily challenge, citing mental health issues, concealing hair loss, and others' reactions; 47% reported anxiety and/or depression. Many patients (75%) persistently concealed hair loss (mean time spent, 10.3 h/wk). Treatment discontinuation was common owing to lack of efficacy, side effects, and cost. Associated expenditures included buying wigs or hairpieces and psychotherapy (mean $2,000/y each). Survey respondents comprised a self-selected sample, which may not reflect the entire population. The impact of AA extends beyond cosmetic concerns and carries a considerable psychosocial burden. Efficacious, less burdensome AA treatments are needed to regrow hair and alleviate psychosocial sequelae.

View details for DOI 10.1016/j.jisp.2020.05.007

View details for PubMedID 33099390

The Role of Patients in Alopecia Areata Endpoint Development: Understanding Physical Signs and Symptoms. The journal of investigative dermatology. Symposium proceedings Wyrwich, K. W., Kitchen, H., Knight, S., Aldhouse, N. V., Macey, J., Nunes, F., Dutronc, Y., Mesinkovska, N. A., Ko, J. M., King, B. A. 2020; 20 (1): S71S77


Meaningful patient input to understand disease experience and patient expectations for improvement with treatment is essential for the selection and development of outcome measures for alopecia areata (AA) clinical trials. This study explored the physical signs and symptoms of AA through 30 semistructured interviews with adult (n= 25) and adolescent (n= 5) patients experienced with severe or very severe AA. Scalp hair loss was overwhelmingly the most important sign and symptom of AA. Nearly all patients (90%) considered scalp hair loss in their top three most bothersome physical signs and symptoms of AA, with 77% (n= 23) naming scalp hair loss as the most bothersome symptom. Other identified signs and symptoms in the top three most bothersome included eyebrow, eyelash, nose, body, and facial hair loss, as well as eye irritation and nail damage and/or appearance. Eyebrow (16%, n= 4), eyelash (4%, n= 1), nasal (4%, n= 1), and body (4%, n= 1) hair loss were identified by seven adult patients as the most bothersome signs and symptoms of AA. Conceptual saturation confirmed that a comprehensive understanding of this patient population's physical AA-related signs and symptoms was obtained. These findings indicate that the primary objective for new AA treatments for this patient population should be meaningful improvement in scalp hair growth to address the most troubling unmet need.

View details for DOI 10.1016/j.jisp.2020.05.006

View details for PubMedID 33099392

Clinical translation of choline and geranic acid deep eutectic solvent BIOENGINEERING & TRANSLATIONAL MEDICINE Ko, J., Mandal, A., Dhawan, S., Shevachman, M., Mitragotri, S., Joshi, N. 2020

View details for DOI 10.1002/btm2.10191

View details for Web of Science ID 000585792300001

Pernio-like eruption associated with COVID-19 in skin of color. JAAD case reports Daneshjou, R., Rana, J., Dickman, M., Yost, J. M., Chiou, A., Ko, J. 2020; 6 (9): 89297

View details for DOI 10.1016/j.jdcr.2020.07.009

View details for PubMedID 32835046

Innovation interest within dermatology: a needs assessment for novel thought processes. Archives of dermatological research Lee, K. C., Lee, I., Okhovat, J., Ko, J., Powers, J. G., Ellis, D. L., Cheeley, J., Garibyan, L. 2020


Medical innovation is crucial to advancing our field, and physicians have the potential to play a leading role due to their daily patient care experiences. The objective of this study was to evaluate the interest in, and barriers to participating in innovation. Two surveys were conducted; the first cross-sectional survey was conducted among attendees of the Advancing Innovation in Dermatology Forum in Feburary 2019. The second survey was conducted among trainees (resident/fellows) and faculty dermatologists at Brown, Emory, Iowa, Stanford, and Vanderbilt Universities between June and November 2019. Demographic data were collected, as well as factors involved with identifying problems, developing solutions, training in innovation, and perceived barriers to innovation. In the first survey, the greatest perceived benefits include bringing joy to one's work and increasing professional fulfillment with work. Innovation was also perceived to decrease burnout. In the second survey of academic centers, faculty more commonly expressed interest in identifying problems (p =0.04), and was also more confident in their ability to generate solutions to these problems as compared to trainees (p<0.01). Major barriers to participating in innovation processes included lack of time and lack of training or education in innovation. Both trainees and faculty groups noted a lack of knowledge in creating prototypes, understanding regulatory approval for medical products, and inexperience with pitching to investors or obtaining funding. Thesecross-sectional needs assessment surveys found a strong interest in innovation coupled with a lack of education in innovation processes. These findings suggest an urgent need and opportunity for providing formal training to empower dermatologists with the tools to lead innovation within our field.

View details for DOI 10.1007/s00403-020-02118-6

View details for PubMedID 32772260

Patient Perspectives on the Use of Artificial Intelligence for Skin Cancer Screening: A Qualitative Study. JAMA dermatology Nelson, C. A., Perez-Chada, L. M., Creadore, A., Li, S. J., Lo, K., Manjaly, P., Pournamdari, A. B., Tkachenko, E., Barbieri, J. S., Ko, J. M., Menon, A. V., Hartman, R. I., Mostaghimi, A. 2020


Importance: The use of artificial intelligence (AI) is expanding throughout the field of medicine. In dermatology, researchers are evaluating the potential for direct-to-patient and clinician decision-support AI tools to classify skin lesions. Although AI is poised to change how patients engage in health care, patient perspectives remain poorly understood.Objective: To explore how patients conceptualize AI and perceive the use of AI for skin cancer screening.Design, Setting, and Participants: A qualitative study using a grounded theory approach to semistructured interview analysis was conducted in general dermatology clinics at the Brigham and Women's Hospital and melanoma clinics at the Dana-Farber Cancer Institute. Forty-eight patients were enrolled. Each interview was independently coded by 2 researchers with interrater reliability measurement; reconciled codes were used to assess code frequency. The study was conducted from May 6 to July 8, 2019.Main Outcomes and Measures: Artificial intelligence concept, perceived benefits and risks of AI, strengths and weaknesses of AI, AI implementation, response to conflict between human and AI clinical decision-making, and recommendation for or against AI.Results: Of 48 patients enrolled, 26 participants (54%) were women; mean (SD) age was 53.3 (21.7) years. Sixteen patients (33%) had a history of melanoma, 16 patients (33%) had a history of nonmelanoma skin cancer only, and 16 patients (33%) had no history of skin cancer. Twenty-four patients were interviewed about a direct-to-patient AI tool and 24 patients were interviewed about a clinician decision-support AI tool. Interrater reliability ratings for the 2 coding teams were kappa=0.94 and kappa=0.89. Patients primarily conceptualized AI in terms of cognition. Increased diagnostic speed (29 participants [60%]) and health care access (29 [60%]) were the most commonly perceived benefits of AI for skin cancer screening; increased patient anxiety was the most commonly perceived risk (19 [40%]). Patients perceived both more accurate diagnosis (33 [69%]) and less accurate diagnosis (41 [85%]) to be the greatest strength and weakness of AI, respectively. The dominant theme that emerged was the importance of symbiosis between humans and AI (45 [94%]). Seeking biopsy was the most common response to conflict between human and AI clinical decision-making (32 [67%]). Overall, 36 patients (75%) would recommend AI to family members and friends.Conclusions and Relevance: In this qualitative study, patients appeared to be receptive to the use of AI for skin cancer screening if implemented in a manner that preserves the integrity of the human physician-patient relationship.

View details for DOI 10.1001/jamadermatol.2019.5014

View details for PubMedID 32159733

Dupilumab Treatment of Nummular Dermatitis: A Retrospective Cohort Study. Journal of the American Academy of Dermatology Choi, S. n., Zhu, G. A., Lewis, M. A., Honari, G. n., Chiou, A. S., Ko, J. n., Chen, J. K. 2020

View details for DOI 10.1016/j.jaad.2019.12.054

View details for PubMedID 31923445

Dupilumab for occupational irritant hand dermatitis in a nonatopic individual: A case report. JAAD case reports Zhu, G. A., Honari, G. n., Ko, J. M., Chiou, A. S., Chen, J. K. 2020; 6 (4): 29698

View details for DOI 10.1016/j.jdcr.2020.02.010

View details for PubMedID 32258302

View details for PubMedCentralID PMC7109358

The Alopecia Areata Investigator Global Assessment scale: a measure for evaluating clinically meaningful success in clinical trials. The British journal of dermatology Wyrwich, K. W., Kitchen, H. n., Knight, S. n., Aldhouse, N. V., Macey, J. n., Nunes, F. P., Dutronc, Y. n., Mesinkovska, N. n., Ko, J. M., King, B. A. 2020


Content-valid and clinically meaningful instruments are required to evaluate outcomes of therapeutic interventions in alopecia areata (AA).To develop an Investigator's Global Assessment (IGA) to interpret treatment response in AA treatment studies.Qualitative interviews were conducted in the USA with expert dermatologists and with patients with AA who had experienced 50% scalp-hair loss. Thematic data analysis identified critical outcomes and evaluated the content validity of the new IGA.Expert clinicians (n = 10) judged AA treatment success by the amount of scalp-hair growth (median 80% scalp hair). Adult (n = 25) and adolescent (n = 5) patients participated. Scalp-hair loss was the most bothersome AA sign/symptom for most patients. Perceived treatment success - short of 100% scalp hair - was the presence of ~ 70-90% scalp hair (median 80%). Using additional clinician and patient insights, the Alopecia Areata Investigator Global Assessment (AA-IGA) was developed. This clinician-reported outcome assessment is an ordinal, static measure comprising five severity categories of scalp-hair loss. Nearly all clinicians and patients in this study agreed that, for patients with 50% scalp-hair loss, successful treatment would be hair regrowth resulting in 20% scalp-hair loss.We recommend using the Severity of Alopecia Tool to assess the extent (0-100%) of scalp-hair loss. The AA-IGA is a robust ordinal measure providing distinct and clinically meaningful gradations of scalp-hair loss that reflects patients' and expert clinicians' perspectives and treatment expectations.

View details for DOI 10.1111/bjd.18883

View details for PubMedID 31970750

Development of the Scalp Hair Assessment PRO measure for alopecia areata. The British journal of dermatology Wyrwich, K. W., Kitchen, H. n., Knight, S. n., Aldhouse, N. V., Macey, J. n., Nunes, F. P., Dutronc, Y. n., Mesinkovska, N. n., Ko, J. M., King, B. A. 2020


Valid patient-reported outcome (PRO) measures are required to evaluate alopecia areata (AA) treatments.To develop a content-valid and clinically meaningful PRO measure to assess AA scalp hair loss with scores comparable with the five-response-level Alopecia Areata Investigator Global Assessment (AA-IGA).A draft PRO measure was developed based on input from 10 clinical experts in AA. The PRO measure was cognitively debriefed, modified and finalized through two rounds of qualitative semistructured interviews with patients with AA who had experienced 50% scalp hair loss. Data were thematically analysed.Adults (round 1: n = 25; round 2: n = 15) and adolescents aged 15-17 years (round 1: n = 5) in North America participated. All patients named scalp hair loss as a key AA sign or symptom. Patients demonstrated the ability to self-report their current amount of scalp hair using percentages. In round 1 not all patients interpreted the measurement concept consistently; therefore, the PRO was modified to clarify the measurement concept to improve usability. Following modifications, patients in round 2 responded without difficulty to the PRO measure. Patients confirmed that they could use the five-level response scale to rate their scalp hair loss: no missing hair, 0%; limited, 1-20%; moderate, 21-49%; large, 50-94%; nearly all or all, 95-100%. Almost all patients deemed hair regrowth resulting in 20% scalp hair loss a treatment success.The Scalp Hair Assessment PRO is a content-valid, clinically meaningful assessment of distinct gradations of scalp hair loss for evaluating AA treatment for patients with 50% hair loss at baseline.

View details for DOI 10.1111/bjd.19024

View details for PubMedID 32163589

Development of Clinician-Reported Outcome (ClinRO) and Patient-Reported Outcome (PRO) Measures for Eyebrow, Eyelash and Nail Assessment in Alopecia Areata. American journal of clinical dermatology Wyrwich, K. W., Kitchen, H. n., Knight, S. n., Aldhouse, N. V., Macey, J. n., Nunes, F. P., Dutronc, Y. n., Mesinkovska, N. n., Ko, J. M., King, B. A. 2020


Eyebrow and eyelash hair loss and nail damage-in addition to scalp hair loss-are important signs/symptoms of alopecia areata (AA) to patients and deserve assessment in AA clinical trials.Our objective was to develop clinician-reported outcome (ClinRO) and patient-reported outcome (PRO) measures and accompanying photoguides to aid in the assessment of AA-related eyebrow, eyelash and nail signs/symptoms.Iterative rounds of qualitative, semi-structured interviews were conducted with US expert dermatologists and North American patients with AA. Patients with eyebrow, eyelash and nail involvement were purposefully sampled. Interview transcripts were qualitatively analyzed.Dermatologists (n=10) described eyebrow and eyelash loss as concerning for affected patients and, along with nail appearance, as deserving assessment. Dermatologist data informed the development of single item, 4-point Likert-type ClinRO and PRO measures of current eyebrow loss, eyelash loss and nail appearance and a PRO measure of eye irritation. Patients (n=45, age 15-72years) confirmed the importance and relevance of these signs/symptoms. Interim revision resulted in measures that were understood by and relevant to patients. Dermatologists (n=5) and patients (n=10, age 21-54years) participated in the development of the eyebrow, eyelash and nail photoguides and confirmed that they included photos that appropriately represented different severity levels and were helpful to derive and standardize ratings across raters.The ClinRO and PRO measures for eyebrow, eyelash and nail appearance, with their accompanying photoguides and the PRO Measure for Eye Irritation provide clear and meaningful assessments of outcomes important to patients with AA.

View details for DOI 10.1007/s40257-020-00545-9

View details for PubMedID 32803546

"'You lose your hair, what's the big deal?' I was so embarrassed, I was so self-conscious, I was so depressed:" a qualitative interview study to understand the psychosocial burden of alopecia areata. Journal of patient-reported outcomes Aldhouse, N. V., Kitchen, H. n., Knight, S. n., Macey, J. n., Nunes, F. P., Dutronc, Y. n., Mesinkovska, N. n., Ko, J. M., King, B. A., Wyrwich, K. W. 2020; 4 (1): 76


Alopecia areata (AA) is characterized by hair loss that can affect the scalp and body. This study describes the psychosocial burden of AA.Participants diagnosed with AA who had experienced 50% scalp hair loss according to the Severity of Alopecia Tool (SALT) were identified by clinicians. A semi-structured interview guide, developed with expert clinician input, included open-ended questions to explore patients' experiences of living with AA. Data were thematically analyzed to identify concepts and relationships.Participants (n=45, 58% female, mean age 33.3years [range 15-72], mean SALT 67.2 [range 0-100]) described the AA diagnosis as "devastating". Both males and females reported emotional and psychological impacts of AA including feeling sad/depressed (n=21), embarrassed/ashamed (n=10) and angry/frustrated (n=3). Patients felt helpless (n=5) due to the unpredictability of disease recurrence, and anxious (n=19) about judgement from others. Many patients avoided social situations (n=18), which impaired relationships and increased isolation. Coping strategies included concealment of hair loss through wigs or make-up, although fear of the displacement of these coverings also caused anxiety and the avoidance of activities that could result in scalp exposure (n=22). Some patients became more accepting of AA over time, which lessened the emotional impact, though efficacious treatment was still desired. A conceptual framework was developed, and a conceptual model was created to depict the relationship between the physical signs/symptoms and the associated psychosocial effects of AA.AA impairs patients' emotional and psychological wellbeing, relationships and lifestyles. Greater disease awareness and effective treatments are needed.

View details for DOI 10.1186/s41687-020-00240-7

View details for PubMedID 32914253

Inflammatory alopecia in patients on dupilumab: a retrospective cohort study at an academic institution. Journal of the European Academy of Dermatology and Venereology : JEADV Zhu, G. A., Kang, K. J., Chen, J. K., Novoa, R. A., Brown, R. A., Chiou, A. S., Ko, J. M., Honari, G. 2019


Dupilumab targets IL-4Ralpha and is used for moderate-to-severe atopic dermatitis (AD). Prior reports have described new alopecia areata (AA),1 flaring of prior AA,2 as well as improvement or resolution of AA3 in patients treated with dupilumab. We conducted a retrospective cohort study to describe the natural history of prior or new inflammatory alopecia in patients on dupilumab.

View details for DOI 10.1111/jdv.16094

View details for PubMedID 31737955

The Alopecia Areata Investigator's Global Assessment (AA-IGA) scale: A measure for evaluating clinically meaningful success in clinical trials Wyrwich, K. W., Kitchen, H., Knight, S., Aldhouse, N. J., Macey, J., Nunes, F. P., Dutronc, Y., Mesinkovska, N. A., Ko, J. M., King, B. A. MOSBY-ELSEVIER. 2019: AB283
Marking the Path Toward Artificial Intelligence-Based Image Classification in Dermatology. JAMA dermatology Novoa, R. A., Gevaert, O., Ko, J. M. 2019

View details for DOI 10.1001/jamadermatol.2019.1633

View details for PubMedID 31411643

Assessment of the Development of New Regional Dermatoses in Patients Treated for Atopic Dermatitis With Dupilumab JAMA DERMATOLOGY Zhu, G., Chen, J. K., Chiou, A., Ko, J., Honari, G. 2019; 155 (7): 85052
Repeat patch testing in a patient with allergic contact dermatitis improved on dupilumab. JAAD case reports Zhu, G. A., Chen, J. K., Chiou, A., Ko, J., Honari, G. 2019; 5 (4): 33638

View details for PubMedID 30989102

Artificial intelligence and dermatology: opportunities, challenges, and future directions. Seminars in cutaneous medicine and surgery Schlessinger, D. I., Chhor, G., Gevaert, O., Swetter, S. M., Ko, J., Novoa, R. A. 2019; 38 (1): E3137


The application of artificial intelligence (AI) to medicine has considerable potential within dermatology, where the majority of diagnoses are based on visual pattern recognition. Opportunities for AI in dermatology include the potential to automate repetitive tasks; optimize time-consuming tasks; extend limited medical resources; improve interobserver reliability issues; and expand the diagnostic toolbox of dermatologists. To achieve the full potential of AI, however, developers must aim to create algorithms representing diverse patient populations; ensure algorithm output is ultimately interpretable; validate algorithm performance prospectively; preserve human-patient interaction when necessary; and demonstrate validity in the eyes of regulatory bodies.

View details for PubMedID 31051021

Artificial intelligence and dermatology: opportunities, challenges, and future directions SEMINARS IN CUTANEOUS MEDICINE AND SURGERY Schlessinger, D. I., Chhor, G., Gevaert, O., Swetter, S. M., Ko, J., Novoa, R. A. 2019; 38 (1): E31E37
Commentary: Position Statement on Augmented Intelligence (AuI). Journal of the American Academy of Dermatology Kovarik, C. n., Lee, I. n., Ko, J. n. 2019

View details for DOI 10.1016/j.jaad.2019.06.032

View details for PubMedID 31247221

Assessment of the Development of New Regional Dermatoses in Patients Treated for Atopic Dermatitis With Dupilumab. JAMA dermatology Zhu, G. A., Chen, J. K., Chiou, A. n., Ko, J. n., Honari, G. n. 2019

View details for PubMedID 31042259

Rebound effect associated with JAK inhibitor use in the treatment of alopecia areata. Journal of the European Academy of Dermatology and Venereology : JEADV Gordon, S. C., Abudu, M., Zancanaro, P., Ko, J. M., Rosmarin, D. 2018


Alopecia areata (AA) is a common autoimmune disease driven by Th1 cytokines characterized by non-scarring hair loss.1,2 Mouse models have demonstrated that IFN-gamma-producing NKG2D+ CD8+ cytotoxic T lymphocytes (CTLs) are essential for disease pathogenesis, along with JAK-STAT dependent cytokines IFN-gamma and IL-15, which induce autoreactive T cell activation.1,3 This article is protected by copyright. All rights reserved.

View details for DOI 10.1111/jdv.15383

View details for PubMedID 30520145

Implementation and evaluation of Stanford Health Care store-and-forward teledermatology consultation workflow built within an existing electronic health record system. Journal of telemedicine and telecare Kim, G. E., Afanasiev, O. K., O'Dell, C., Sharp, C., Ko, J. M. 2018: 1357633X18799805


Introduction Teledermatology services that function separately from patients' primary electronic health record (EHR) can lead to fragmented care, poor provider communication, privacy concerns and billing challenges. This study addresses these challenges by developing PhotoCareMD, a store-and-forward (SAF) teledermatology consultation workflow built entirely within an existing Epic-based EHR. Methods Thirty-six primary care physicians (PCPs) from eight outpatient clinics submitted 215 electronic consults (eConsults) for 211 patients to a Stanford Health Care dermatologist via PhotoCareMD. Comparisons were made with in-person referrals for this same dermatologist prior to initiation of PhotoCareMD. Results Compared to traditional in-person dermatology clinic visits, eConsults decreased the time to diagnosis and treatment from 23 days to 16 hours. The majority (73%) of eConsults were resolved electronically. In-person referrals from PhotoCareMD (27%) had a 50% lower cancellation rate compared with traditional referrals (11% versus 22%). The average in-person visit and documentation was 25 minutes compared with 8 minutes for an eConsult. PhotoCareMD saved 13 additional clinic hours to be made available to the dermatologist over the course of the pilot. At four patients per hour, this opens 52 dermatology clinic slots. Over 96% of patients had a favourable experience and 95% felt this service saved them time. Among PCPs, 100% would recommend PhotoCareMD to their colleagues and 95% said PhotoCareMD was a helpful educational tool. Discussion An internal SAF teledermatology workflow can be effectively implemented to increase access to and quality of dermatologic care. Our workflow can serve as a successful model for other hospitals and specialties.

View details for DOI 10.1177/1357633X18799805

View details for PubMedID 30301409

Automated Classification of Skin Lesions: From Pixels to Practice. The Journal of investigative dermatology Narla, A., Kuprel, B., Sarin, K., Novoa, R., Ko, J. 2018; 138 (10): 210810


The letters "Interpretation of the Outputs of Deep Learning Model trained with Skin Cancer Dataset" and "Automated Dermatological Diagnosis: Hype or Reality?" highlight the opportunities, hurdles, and possible pitfalls with the development of tools that allow for automated skin lesion classification. The potential clinical impact of these advances relies on their scalability, accuracy, and generalizability across a range of diagnostic scenarios.

View details for PubMedID 30244720

The importance of eyebrows in the treatment of alopecia areata: An online questionnaire Liu, L., King, B., Ko, J. MOSBY-ELSEVIER. 2018: AB288
Challenges and recommendations for epigenomics in precision health NATURE BIOTECHNOLOGY Carter, A. C., Chang, H. Y., Church, G., Dombkowski, A., Ecker, J. R., Gil, E., Giresi, P. G., Greely, H., Greenleaf, W. J., Hacohen, N., He, C., Hill, D., Ko, J., Kohane, I., Kundaje, A., Palmer, M., Snyder, M. P., Tung, J., Urban, A., Vidal, M., Wong, W. 2017; 35 (12): 112832

View details for PubMedID 29220033

Dermatologist-level classification of skin cancer with deep neural networks. Nature Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., Thrun, S. 2017; 542 (7639): 115-118


Skin cancer, the most common human malignancy, is primarily diagnosed visually, beginning with an initial clinical screening and followed potentially by dermoscopic analysis, a biopsy and histopathological examination. Automated classification of skin lesions using images is a challenging task owing to the fine-grained variability in the appearance of skin lesions. Deep convolutional neural networks (CNNs) show potential for general and highly variable tasks across many fine-grained object categories. Here we demonstrate classification of skin lesions using a single CNN, trained end-to-end from images directly, using only pixels and disease labels as inputs. We train a CNN using a dataset of 129,450 clinical images-two orders of magnitude larger than previous datasets-consisting of 2,032 different diseases. We test its performance against 21 board-certified dermatologists on biopsy-proven clinical images with two critical binary classification use cases: keratinocyte carcinomas versus benign seborrheic keratoses; and malignant melanomas versus benign nevi. The first case represents the identification of the most common cancers, the second represents the identification of the deadliest skin cancer. The CNN achieves performance on par with all tested experts across both tasks, demonstrating an artificial intelligence capable of classifying skin cancer with a level of competence comparable to dermatologists. Outfitted with deep neural networks, mobile devices can potentially extend the reach of dermatologists outside of the clinic. It is projected that 6.3 billion smartphone subscriptions will exist by the year 2021 (ref. 13) and can therefore potentially provide low-cost universal access to vital diagnostic care.

View details for DOI 10.1038/nature21056

View details for PubMedID 28117445

Crowdsourcing dermatology: DataDerm, big data analytics, and machine learning technology. Journal of the American Academy of Dermatology Park, A. J., Ko, J. M., Swerlick, R. A. 2017

View details for PubMedID 29042152

A case and review of congenital leukonychia. Dermatology online journal Pathipati, A. S., Ko, J. M., Yost, J. M. 2016; 22 (10)


Leukonychia refers to a white discoloration of the nails. Although several conditions may cause white nails, a rare, isolated, congenital form of the disease is hypothesized to stem from disordered keratinization of the nail plate. Herein, we report a case of a 41-year-old woman with congenital leukonychia and review prior cases.

View details for PubMedID 28329587

Safety and efficacy of the JAK inhibitor tofacitinib citrate in patients with alopecia areata. JCI insight Kennedy Crispin, M., Ko, J. M., Craiglow, B. G., Li, S., Shankar, G., Urban, J. R., Chen, J. C., Cerise, J. E., Jabbari, A., Winge, M. C., Marinkovich, M. P., Christiano, A. M., Oro, A. E., King, B. A. 2016; 1 (15)


Alopecia areata (AA) is an autoimmune disease characterized by hair loss mediated by CD8(+) T cells. There are no reliably effective therapies for AA. Based on recent developments in the understanding of the pathomechanism of AA, JAK inhibitors appear to be a therapeutic option; however, their efficacy for the treatment of AA has not been systematically examined.This was a 2-center, open-label, single-arm trial using the pan-JAK inhibitor, tofacitinib citrate, for AA with >50% scalp hair loss, alopecia totalis (AT), and alopecia universalis (AU). Tofacitinib (5 mg) was given twice daily for 3 months. Endpoints included regrowth of scalp hair, as assessed by the severity of alopecia tool (SALT), duration of hair growth after completion of therapy, and disease transcriptome.Of 66 subjects treated, 32% experienced 50% or greater improvement in SALT score. AA and ophiasis subtypes were more responsive than AT and AU subtypes. Shorter duration of disease and histological peribulbar inflammation on pretreatment scalp biopsies were associated with improvement in SALT score. Drug cessation resulted in disease relapse in 8.5 weeks. Adverse events were limited to grade I and II infections. An AA responsiveness to JAK/STAT inhibitors score was developed to segregate responders and nonresponders, and the previously developed AA disease activity index score tracked response to treatment.At the dose and duration studied, tofacitinib is a safe and effective treatment for severe AA, though it does not result in a durable response. Transcriptome changes reveal unexpected molecular complexity within the NCT02197455 and NCT02312882.This work was supported by the US Department of Veterans Affairs Office of Research and Development, National Institute of Arthritis and Musculoskeletal and Skin Diseases National Institutes of Health grant R01 AR47223 and U01 AR67173, the National Psoriasis Foundation, the Swedish Society of Medicine, the Fernstrm Foundation, the Locks of Love Foundation, the National Alopecia Areata Foundation, and the Ranjini and Ajay Poddar Resource Fund for Dermatologic Diseases Research.

View details for PubMedID 27699252

Implementation and evaluation of Stanford Health Care direct-care teledermatology program. SAGE open medicine Pathipati, A. S., Ko, J. M. 2016; 4: 2050312116659089-?


Teledermatology has proven to be an effective means of providing dermatologic care. The existing research has primarily evaluated its usefulness in a consultative model. Few academic centers have evaluated a patient-initiated model, and direct-to-consumer services remain the subject of controversy. Stanford Health Care recently launched a direct-care, patient-initiated teledermatology pilot program. This article evaluates the viability and patient satisfaction with this service.During the pilot period, patients were able to seek remote dermatologic care using an eVisit tool in their MyHealth account. Patients initiated the consultation, answered questions regarding their complaint, and uploaded a picture if relevant. A Stanford dermatologist reviewed each eVisit and responded with an assessment and plan. The dermatologist noted whether they were able to make a diagnosis and their level of confidence in it. After the study, 10 patients participated in a focus group to provide feedback on the service.In all, 38 patients sought care during the pilot period. A dermatologist was able to make a diagnosis in 36 of 38 (95%) cases, with an average confidence level of 7.9 of 10. The average time to consultation was 0.8days. Patients indicated high levels of satisfaction with the service although they had suggestions for improvement.Patients provided clinically useful images and information in a direct-care teledermatology model. Such services allow dermatology providers to increase access while maintaining high-quality care in an academic medical center. Further research is needed on standalone services that cannot integrate encounters with the patient's existing medical record.

View details for DOI 10.1177/2050312116659089

View details for PubMedID 27493756

View details for PubMedCentralID PMC4959300

Validation of a Skin-Lesion Image-Matching Algorithm Based on Computer Vision Technology TELEMEDICINE AND E-HEALTH Chen, R. H., Snorrason, M., Enger, S. M., Mostafa, E., Ko, J. M., Aoki, V., Bowling, J. 2016; 22 (1): 45-50
Randomized Controlled Trial of Cryotherapy With Liquid Nitrogen vs Topical Salicylic Acid vs Wait-and-See for Cutaneous Warts ARCHIVES OF DERMATOLOGY Ko, J., Bigby, M. 2012; 148 (7): 840-842

View details for Web of Science ID 000306417100014

View details for PubMedID 22801618

A Randomized, Prospective Trial Evaluating Surgeon Preference in Selection of Absorbable Suture Material JOURNAL OF DRUGS IN DERMATOLOGY Lu, L. K., Ko, J. M., Lee, J., Krum, D. M., Price, L. L., Finn, D., Lee, D., Rogers, G. S. 2012; 11 (2): 196-201


This study is the first double-blinded, randomized comparison of two absorbable sutures. To better understand product characteristics and surgeon preference, we conducted a study of two similar-appearing FDA-approved sutures, glyconate and poliglecaprone 25. Four dermatologic surgeons were enlisted. A total of 48 patients with 53 surgical sites were examined. One half of each surgical wound was closed with one type of suture and the other half with the other type. Each half was evaluated for product characteristics. There was no statistically significant difference in surgeon preference for glyconate versus poliglecaprone 25 (P=0.64). Of the cohort preferring poliglecaprone 25, there was a correlation with speed of closure (P=0.06). Of the surgeons that preferred glyconate, we found significantly better visibility (P=0.03), reduced suture breakage during knot tying (P=0.05), and correlation with better handling properties (P=0.06) associated with that preference. The data from this study will enable products to be designed towards these needs and allow surgeons to select sutures that more precisely fit their particular requirements.

View details for Web of Science ID 000299965700009

View details for PubMedID 22270202

A new era: melanoma genetics and therapeutics JOURNAL OF PATHOLOGY Ko, J. M., Fisher, D. E. 2011; 223 (2): 241-250


We have recently witnessed an explosion in our understanding of melanoma. Knowledge of the molecular basis of melanoma and the successes of targeted therapies have pushed melanoma care to the precipice of a new era. Identification of significant pathways and oncogenes has translated to the development of targeted therapies, some of which have produced major clinical responses. In this review, we provide an overview of selected key pathways and melanoma oncogenes as well as the targeted agents and therapeutic approaches whose successes suggest the promise of a new era in melanoma and cancer therapy. Despite these advances, the conversion of transient remissions to stable cures remains a vital challenge. Continued progress towards a better understanding about the complexity and redundancy responsible for melanoma progression may provide direction for anti-cancer drug development.

View details for DOI 10.1002/path.2804

View details for Web of Science ID 000285554600013

View details for PubMedID 21125678

Pathways to Melanoma SEMINARS IN CUTANEOUS MEDICINE AND SURGERY Ko, J. M., Velez, N. F., Tsao, H. 2010; 29 (4): 210-217


Melanoma is one of the most aggressive and yet poorly understood of human malignancies. Advances in genomics has allowed a more nuanced understanding of the disease, moving beyond the traditional dysplastic nevus-to-melanoma model and identifying multiple divergent oncogenic pathways leading to melanoma. An understanding of the molecular mechanisms driving melanoma has opened the doors for the development of targeted therapeutic approaches. As we enter the era of personalized medicine, it will be critical for clinicians to both appreciate and be able to determine the molecular profile of their patients' melanoma because this profile will guide risk stratification, genetic counseling, and treatment customization. A review of the divergent pathways of melanoma development is presented here, with a particular emphasis on recently identified mutations, and their implications for patient care.

View details for DOI 10.1016/j.sder.2010.10.004

View details for Web of Science ID 000287382200003

View details for PubMedID 21277534

Skin and bone: the pathogenetic relationship between psoriasis and psoriatic arthritis GIORNALE ITALIANO DI DERMATOLOGIA E VENEREOLOGIA Ko, J. M., QURESHI, A. W. 2010; 145 (3): 393-406


Our current understanding of the relationship between psoriasis and psoriatic arthritis remains incomplete, though the evidence from the clinical setting, response to therapeutics, epidemiology, genetics, imaging, and immunopathologic models suggest that they make likely share a common pathogenesis. Psoriatic disease can no longer be thought of as a condition limited to skin and joints. Rather, it must be considered a multi-faceted disorder in which systemic inflammation plays a central role. There is now convincing evidence that individuals with psoriasis have a higher prevalence of co-morbid disease, particularly cardiovascular risk factors, metabolic disorders, and other immune-mediated inflammatory diseases. The cutaneous manifestations of psoriasis place dermatologists in a crucial and privileged role--one that affords us the potential for early detection of associated co-morbid conditions through screening and perhaps impact disease course and clinical outcomes.

View details for Web of Science ID 000279937700007

View details for PubMedID 20461047

Paying for Enhanced Service Comparing Patients' Experiences in a Concierge and General Medicine Practice PATIENT-PATIENT CENTERED OUTCOMES RESEARCH Ko, J. M., Rodriguez, H. P., Fairchild, D. G., Rodday, A. M., Safran, D. G. 2009; 2 (2): 95-103


Concierge medical practice is a relatively new and somewhat controversial development in primary-care practice. These practices promise patients more personalized care and dedicated service, in exchange for an annual membership fee paid by patients. The experiences of patients using these practices remain largely undocumented.To assess the experiences of patients in a concierge medicine practice compared with those in a general medicine practice.Stratified random samples of patients empanelled to each of the four doctors who practice at both a general medicine and a concierge medicine practice separately situated at an academic medical center were drawn. Patients were eligible for the study if they had a visit with the physician between January and May 2006. The study questionnaire (Consumer Assessment of Healthcare Providers and Systems Clinician and Group Survey, supplemented with items from the Ambulatory Care Experiences Survey) was administered by mail to 100 general medicine patients per physician (n=400) and all eligible concierge medicine patients (n=201). Patients who completed the survey and affirmed the study physician as their primary-care physician formed the analytic sample (n=344) that was used to compare the experiences of concierge medicine and general medicine patients. Models controlled for respondent characteristics and accounted for patient clustering within physicians using physician fixed effects.Patients' experiences with organizational features of care, comprising care co-ordination (p<0.01), access to care (p<0.001) and interactions with office staff (p<0.001), favored concierge medicine over general medicine practice. The quality of physician-patient interactions did not differ significantly between the two groups. However, the patients of the concierge medicine practice were more likely to report that their physician spends sufficient time in clinical encounters than patients of the general medicine practice (p<0.003).The results suggest patients of the concierge medicine practice experienced and reported enhanced service, greater access to care, and better care co-ordination than those of the general medicine practice. This suggests that further study to understand the etiology of these differences may be beneficial in enhancing patients' experience in traditional primary-care practices.

View details for DOI 10.2165/01312067-200902020-00005

View details for Web of Science ID 000208001400005

View details for PubMedID 22273085

Induction and exacerbation of psoriasis with TNF-blockade therapy: A review and analysis of 127 cases JOURNAL OF DERMATOLOGICAL TREATMENT Ko, J. M., Gottlieb, A. B., Kerbleski, J. F. 2009; 20 (2): 100-108


There are reports of rare adverse effects of tumor necrosis factor (TNF) inhibitors, including infections, malignancies, and induction of autoimmune conditions. Intriguing, are cases of induction or exacerbation of psoriasis in conjunction with TNF inhibitor therapy, given that they are approved for treatment of the same condition. Objective: Published cases of psoriasis occurring during anti-TNF therapy were analyzed, including overviews of proposed etiologies and treatment recommendations.A literature search using Ovid MEDLINE and PubMed was performed for articles published between January 1990 and September 2007 to collect reported cases of psoriasis in patients receiving therapy with TNF blocking agents.A total of 127 cases were identified: 70 in patients on infliximab (55.1%), 35 with etanercept (27.6%), and 22 with adalimumab (17.3%). Females comprised 58% of cases; mean age of reported patients was 45.8 years, and the time from initiation of treatment to onset of lesions averaged 10.5 months. These patients suffered from a number of primary conditions, with rheumatoid arthritis, ankylosing spondylitis, and Crohn's disease accounting for the vast majority. Palmoplantar pustular psoriasis was observed in 40.5% of the cases, with plaque-type psoriasis in 33.1%, and other types comprising the remainder. Topical corticosteroids were the most commonly employed treatment modality but led to resolution in only 26.8% of cases in which they were employed solely. Switching to a different anti-TNF agent led to resolution in 15.4% of cases. Cessation of anti-TNF therapy with systemic therapy led to resolution in 64.3% of cases.More information and cases are needed. Biopsies of TNF-blockade-induced lesions may reveal what cytokines and cell types drive the development of these lesions. Additionally, there is a need to develop an algorithm to treat this paradoxical side effect of therapy with TNF-blockers.

View details for DOI 10.1080/09546630802441234

View details for Web of Science ID 000264554200008

View details for PubMedID 18923992

Prospective assessment of computer-aided detection in interpretation of screening mammography AMERICAN JOURNAL OF ROENTGENOLOGY Ko, J. M., Nicholas, M. J., Mendel, J. B., Slanetz, P. J. 2006; 187 (6): 1483-1491


The purpose of this study was to prospectively assess the usefulness of computer-aided detection (CAD) in the interpretation of screening mammography and to provide the true sensitivity and specificity of this technique in a clinical setting.Over a 26-month period, 5,016 screening mammograms were interpreted without, and subsequently with, the assistance of the iCAD MammoReader detection system. Data collected for actionable findings included dominant feature (calcification, mass, asymmetry, architectural distortion), detection method (radiologist only, CAD only, or both radiologist and CAD), BI-RADS assessment code, associated histopathology for those undergoing biopsy, and tumor stage for malignant lesions. The study population was cross-checked against an independent reference standard to identify false-negative cases.Of the 5,016 cases, the recall rate increased from 12% to 14% with the addition of CAD. Of the 107 (2%) patients who underwent biopsy, 101 (94%) were prompted by the radiologist and six (6%) were prompted by CAD. Of the 124 biopsies performed on actionable findings in the 107 patients, findings in 79 (64%) were benign and in 45 (36%) were in situ or invasive carcinoma. Three study participants who were not recalled by the radiologist with the assistance of CAD developed cancer within 1 year of the screening mammogram and were considered to be false-negative cases. The radiologist detected 43 (90%) of the 48 total malignancies and 45 (94%) of the 48 malignancies with the assistance of CAD. CAD missed eight cancers that were detected by the radiologist, which presented as architectural distortions (n = 3), irregular masses (n = 4), and a circumscribed mass (n = 1). CAD detected two in situ cancers as a faint cluster of calcifications that had not been perceived by the radiologist and one mass that was dismissed by the radiologist, accounting for at least a 4.7% increase in cancer detection rate. Sensitivity of screening mammography with the use of CAD (94%) represented an absolute and relative 4% increase over the sensitivity of the radiologist alone (90%). Specificity of screening mammography with and without the use of CAD was 99%.Routine use of CAD while interpreting screening mammograms significantly increases recall rates, has no significant effect on positive predictive value for biopsy, and can increase cancer detection rate by at least 4.7% and sensitivity by at least 4%. This study provides "true" values for sensitivity and specificity for use of CAD in interpretation of screening mammography as measured prospectively in the context of a working clinical setting.

View details for DOI 10.2214/AJR.05.1582

View details for Web of Science ID 000242289200017

View details for PubMedID 17114541