Maternal history of angioma is associated with infantile hemangioma and port-wine stain in children: a population-based, cohort study of mother-child pairs from the United Kingdom.

The two most prevalent childhood vascular abnormalities are infantile hemangioma (IH) and port-wine stain (PWS). They become apparent shortly after birth but have distinct pathophysiology and clinical manifestations. The goal of this study was to determine if mother's history of angioma or PWS is associated with these vascular abnormalities. We evaluated an UK anonymized electronic medical records database with medical records that were linked between children and their mothers. Cox proportional hazards models were used to evaluate the association between maternal factors and the time of onset of either IH or PWS in children. Between 2004 and 2021, 639,085 children were linked to their mom's medical data with a total of 4,270,773 person-years of follow up. Children born to mothers with an angioma as compared to a mother without an angioma were more than 60% more likely to have an IH (HR: 1.64 [1.07, 2.52]). Children born to mothers with a PWS as compared to children born to mothers without a PWS were nearly 20 times more likely to have a PWS (18.95 [4.71,76.26]). Mothers with angiomas were not more likely to have children with PWS and mothers with PWS were not more likely to have children with IH. The effect estimates were minimally changed after adjustment. We demonstrated that children born to mothers with angiomas or PWS were at increased risk of IH or PWS, respectively.

Challenges in designing a randomized, double-blind noninferiority trial for treatment of acne: The SD-ACNE trial.

BACKGROUND/AIMS: Excessive use of antibiotics has led to development of antibiotic resistance and other antibiotic-associated complications. Dermatologists prescribe more antibiotics per clinician than any other major specialty, with much of this use for acne. Alternative acne treatments are available but are used much less often than antibiotics, at least partially because dermatologists feel that they are less effective. Spironolactone, a hormonal therapy with antiandrogen effects that can address the hormonal pathogenesis of acne, may represent a therapeutic alternative to oral antibiotics for women with acne. However, the comparative effects of spironolactone and oral antibiotics in the treatment of acne have not been definitively studied. The Spironolactone versus Doxycycline for Acne: A Comparative Effectiveness, Noninferiority Evaluation (SD-ACNE) trial aims to answer whether spironolactone, in addition to standard topical therapy, is noninferior to doxycycline (an oral antibiotic) for women with acne. Several interesting challenges arose in the development of this study, including determining acceptability of the comparative regimens to participating dermatologists, identifying data to support a noninferiority margin, and establishing a process for unblinding participants after they completed the study while maintaining the blind for study investigators. METHODS: We present the scientific and clinical rationale for the decisions made in the design of the trial, including input from key stakeholders through a Delphi consensus process. RESULTS: The Spironolactone versus Doxycycline for Acne: A Comparative Effectiveness, Noninferiority Evaluation trial (NCT04582383) is being conducted at a range of community and academic sites in the United States. To maximize external validity and inform clinical practice, the study is designed with broad eligibility criteria and no prohibition of use of topical medications. Participants in the trial will be randomized to receive either spironolactone 100 mg/day or doxycycline hyclate 100 mg/day for 16 weeks. The primary outcome is the absolute decrease in inflammatory lesion count, and we have established a noninferiority margin of four inflammatory lesions. Secondary outcomes include the percentage of participants achieving Investigator Global Assessment success, change in quality of life, and microbiome changes and diversity. CONCLUSIONS: The Spironolactone versus Doxycycline for Acne: A Comparative Effectiveness, Noninferiority Evaluation trial will have substantial implications for the treatment of acne and antibiotic stewardship. In addition, this study will provide important information on the effect of these systemic agents on the development of changes to the microbiome and antibiotic resistance in a healthy population of patients.

Adult and infantile seborrheic dermatitis: update on current state of evidence and potential research frontiers.

Seborrheic dermatitis (SD) is a highly prevalent dermatological condition globally. The condition demonstrates bimodal presentation with what is commonly thought to be two subtypes: adult/adolescent seborrheic dermatitis (ASD) and infantile seborrheic dermatitis (ISD). Despite the common prevalence of ASD and ISD, there remains uncertainty around the underlying pathogenetic mechanisms, risk factors, and appropriate classification of the disease(s). This narrative review summarizes the current understanding of the epidemiology, presentation, and pathogenetic factors like epidermal barrier dysfunction, lipid abnormalities, and cutaneous microbiome for ASD and ISD. Elements such as immune responsiveness, neuroendocrine factors, and genetics in these disease states are also investigated. Throughout our review, we highlight shared features and discrepancies between ASD and ISD that are present in the literature and discuss potential avenues for future research that explore these disease states. We aim to contribute to the medical discourse on ASD and ISD and increase awareness of the need for additional research around these conditions, ultimately informing better targeting of therapeutics moving forward.

Antihypertensive Medications and Eczematous Dermatitis in Older Adults.

Importance: Rates of physician-diagnosed eczema have been increasing among older adults, but little is known regarding the pathophysiologic processes and best treatments in this subgroup. Preliminary data suggest that medications-antihypertensive medications in particular-may contribute to eczematous dermatitis; however, there are limited population-based data on the proportion of eczematous dermatitis diagnoses among older adults that may be attributed to antihypertensive drugs. Objectives: To determine whether antihypertensive drug use is associated with eczematous dermatitis in older adults. Design, Settings, and Participants: This was a longitudinal cohort study of a population-based sample of individuals 60 years and older without a diagnosis of eczematous dermatitis at baseline. It was conducted at primary care practices participating in The Health Improvement Network in the United Kingdom from January 1, 1994, to January 1, 2015. Data analyses were performed from January 6, 2020, to February 6, 2024. Exposure: Exposure date by first prescription for an antihypertensive drug within each drug class. Main outcome measures: Newly active eczematous dermatitis was based on the first date for 1 of the 5 most common eczema codes used in a previously validated algorithm. Results: Among the total study sample of 1 561 358 older adults (mean [SD] age, 67 [9] years; 54% female), the overall prevalence of eczematous dermatitis was 6.7% during a median (IQR) follow-up duration of 6 (3-11) years. Eczematous dermatitis incidence was higher among participants receiving antihypertensive drugs than those who did not (12 vs 9 of 1000 person-years of follow-up). Adjusted Cox proportional hazard models found that participants who received any antihypertensive drugs had a 29% increased hazard rate of any eczematous dermatitis (hazard ratio [HR], 1.29; 95% CI, 1.26-1.31). When assessing each antihypertensive drug class individually, the largest effect size was observed for diuretic drugs (HR, 1.21; 95% CI, 1.19-1.24) and calcium channel blockers (HR, 1.16; 95% CI, 1.14-1.18), and the smallest effect sizes were for angiotensin-converting enzyme inhibitors (HR, 1.02; 95% CI, 1.00-1.04) and ß-blockers (HR, 1.04; 95% CI, 1.02-1.06). Conclusions and Relevance: This cohort study found that antihypertensive drugs were associated with a small increased rate of eczematous dermatitis, with effect sizes largest for calcium channel blockers and diuretic drugs, and smallest for angiotensin-converting enzyme inhibitors and ß-blockers. Although additional research is needed to understand the mechanisms underlying the association, these data could be helpful to clinicians to guide management when a patient presents with eczematous dermatitis in older age.

Imaging the large-scale and cellular response to focal traumatic brain injury in mouse neocortex.

Traumatic brain injury (TBI) affects neural function at the local injury site and also at distant, connected brain areas. However, the real-time neural dynamics in response to injury and subsequent effects on sensory processing and behavior are not fully resolved, especially across a range of spatial scales. We used in vivo calcium imaging in awake, head-restrained male and female mice to measure large-scale and cellular resolution neuronal activation, respectively, in response to a mild TBI induced by focal controlled cortical impact (CCI) injury of the motor cortex (M1). Widefield imaging revealed an immediate CCI-induced activation at the injury site, followed by a massive slow wave of calcium signal activation that traveled across the majority of the dorsal cortex within approximately 30 s. Correspondingly, two-photon calcium imaging in primary somatosensory cortex (S1) found strong activation of neuropil and neuronal populations during the CCI-induced traveling wave. A depression of calcium signals followed the wave, during which we observed atypical activity of a sparse population of S1 neurons. Longitudinal imaging in the hours and days after CCI revealed increases in the area of whisker-evoked sensory maps at early time points, in parallel to decreases in cortical functional connectivity and behavioral measures. Neural and behavioral changes mostly recovered over hours to days in our mild-TBI model, with a more lasting decrease in the number of active S1 neurons. Our results provide novel spatial and temporal views of neural adaptations that occur at cortical sites remote to a focal brain injury.

Antihypertensive Medications and Risk of Melanoma and Keratinocyte Carcinomas: A Systematic Review and Meta-Analysis.

Some antihypertensive medications are photosensitizing. The implications for skin cancer risk remain unclear because results from prior studies are inconsistent and as new evidence is published. We performed a systematic review and meta-analysis to evaluate the association between antihypertensives and common skin cancers (cutaneous squamous cell carcinoma, basal cell carcinoma, and melanoma) and to evaluate dose-response relationships. Forty-four articles met inclusion criteria, and 42 could be meta analyzed. Increased risks were seen for basal cell carcinoma with calcium channel blockers (relative risk [RR] = 1.17, 95% confidence interval [CI] = 1.11-1.22), diuretics (RR = 1.06, 95% CI = 1.03-1.10), and thiazides (RR = 1.10, 95% CI = 1.04-1.16); for squamous cell carcinoma with calcium channel blockers (RR = 1.08, 95% CI = 1.01-1.14), diuretics (RR = 1.29, 95% CI = 1.17-1.43), and thiazides (RR = 1.36, 95% CI = 1.15-1.61); and for melanoma in angiotensin-converting enzyme inhibitors (RR = 1.09, 95% CI = 1.03-1.14), calcium channel blockers (RR = 1.08, 95% CI = 1.03-1.12), and thiazides (RR = 1.09, 95% CI = 1.02-1.17). The quality of evidence was low or very low. We observed evidence for dose-response for thiazides with basal cell carcinoma; angiotensin-converting enzyme inhibitors, diuretics, and thiazides with squamous cell carcinoma; and angiotensin-converting enzyme inhibitors, diuretics, and thiazides with melanoma. Our meta-analysis supports a potential causal association between some antihypertensives, particularly diuretics, and skin cancer risk.

Role of Posterior Medial Thalamus in the Modulation of Striatal Circuitry and Choice Behavior.

The posterior medial (POm) thalamus is heavily interconnected with sensory and motor circuitry and is likely involved in behavioral modulation and sensorimotor integration. POm provides axonal projections to the dorsal striatum, a hotspot of sensorimotor processing, yet the role of POm-striatal projections has remained undetermined. Using optogenetics with slice electrophysiology, we found that POm provides robust synaptic input to direct and indirect pathway striatal spiny projection neurons (D1- and D2-SPNs, respectively) and parvalbumin-expressing fast spiking interneurons (PVs). During the performance of a whisker-based tactile discrimination task, POm-striatal projections displayed learning-related activation correlating with anticipatory, but not reward-related, pupil dilation. Inhibition of POm-striatal axons across learning caused slower reaction times and an increase in the number of training sessions for expert performance. Our data indicate that POm-striatal inputs provide a behaviorally relevant arousal-related signal, which may prime striatal circuitry for efficient integration of subsequent choice-related inputs.

Efficacy and safety of crisaborole ointment, 2%, in participants aged ≥45 years with stasis dermatitis: Results from a fully decentralized, randomized, proof-of-concept phase 2a study.

BACKGROUND: Crisaborole ointment, 2%, is a nonsteroidal topical phosphodiesterase 4 inhibitor approved for the treatment of mild-to-moderate atopic dermatitis. OBJECTIVE: To evaluate the efficacy and safety of crisaborole in stasis dermatitis (SD). METHODS: In this randomized, double-blind, vehicle-controlled, decentralized phase 2a study (NCT04091087), 65 participants aged ≥45 years with SD without active ulceration received crisaborole or vehicle (1:1) twice-daily for 6 weeks. The primary end point was percentage change from baseline in total sign score at week 6 based on in-person assessment. RESULTS: Crisaborole-treated participants had significantly reduced total sign score from baseline versus vehicle based on in-person (nondermatologist) assessment (-32.4% vs -18.1%, P = .0299) and central reader (dermatologists) assessment of photographs (-52.5% vs -10.3%, P = .0004). Efficacy according to success and improvement per Investigator's Global Assessment score and lesional percentage body surface area reached statistical significance based on central reader but not in-person assessments. Skin and subcutaneous tissue disorders were common all-causality treatment-emergent adverse events with crisaborole. LIMITATIONS: Small sample size and short treatment duration were key limitations. In-person assessment was not conducted by dermatologists. CONCLUSION: Crisaborole improved signs and symptoms of SD and was well tolerated. Central reader assessment represents a promising approach for siteless clinical research.

Identifying Core Outcome Domains in Chronic Skin Disease Using the Best-Worst Scaling Method.

Importance: The use of patient-reported outcome measures (PROMs) potentially holds promise as an opportunity to improve outcomes and quality of care for patients with skin disease, but the routine use of PROMs remains limited. While the Patient-Reported Outcomes Measurement Information System (PROMIS) has several strengths and domains relevant to those with chronic skin disease, it is not clear which are most useful. Objective: To determine which PROMIS domains are most meaningful to those with chronic skin disease to develop a PROMIS profile that effectively captures the experience of living with these skin diseases. Design, Setting, and Participants: This cross-sectional study was based on data gathered from an internet survey that was administered to a sample of adult respondents in the US on the Prolific Platform and ResearchMatch and through the National Psoriasis Foundation. A list of PROMIS domains relevant to chronic skin disease was developed through literature review. These domains were included in a best-worst scaling exercise, in which participants were shown 12 sets of 4 domains and asked to choose which domain in each set was the most important and least important to their experience. Participants completed the survey between December 2022 and June 2023. Data were analyzed in June 2023. Main Outcomes and Measures: Ratio-scaled preference score for each of the domains. Results: Of 939 total participants, 559 (59.5%) were female, 20 (2.1%) gender nonconforming, 7 (0.7%) transgender men, and 1 (0.1%) transgender women; there were 4 American Indian/Alaska Native (0.4%), 50 Asian (5.3%), 63 Black (6.7%), 66 Hispanic or Latino/a/x (7.0%), 2 Native Hawaiian/Pacific Islander (0.2%), 749 White (79.8%), and 42 multiracial individuals (4.5%). The survey was completed by 200 participants with acne, 316 with psoriasis, 199 with atopic dermatitis, and 224 with various chronic skin diseases. For those with acne, the highest-scored domains were body image (15.66), appearance (14.96), life satisfaction (11.29), depression (9.25), and anxiety (9.18). For those with psoriasis, the highest-scored domains were life satisfaction (11.31), appearance (11.05), itch (10.98), pain (9.97), and body image (8.75). For those with atopic dermatitis, the highest-scored domains were itch (12.60), life satisfaction (11.65), appearance (11.40), body image (11.25), and pain (10.03). Conclusion and Relevance: The results of this study suggest that body image, appearance, life satisfaction, itch, pain, anxiety, and depression were highly rated across the surveys. By identifying the PROMIS domains most important to individuals with chronic skin disease, clinicians can choose the domains that are most relevant to patients. In addition, this may guide the construction of a PROMIS profile that effectively captures the experience of living with these skin diseases and can serve as a patient-reported measure of disease severity and treatment effectiveness.

An Improved Clinical and Genetics-Based Prediction Model for Diabetic Foot Ulcer Healing.

Objective: The goal of this investigation was to use comprehensive prediction modeling tools and available genetic information to try to improve upon the performance of simple clinical models in predicting whether a diabetic foot ulcer (DFU) will heal. Approach: We utilized a cohort study (n = 206) that included clinical factors, measurements of circulating endothelial precursor cells (CEPCs), and fine sequencing of the NOS1AP gene. We derived and selected relevant predictive features from this patient-level information using statistical and machine learning techniques. We then developed prognostic models using machine learning approaches and assessed predictive performance. The presentation is consistent with TRIPOD requirements. Results: Models using baseline clinical and CEPC data had an area under the receiver operating characteristic curve (AUC) of 0.73 (0.66-0.80). Models using only single nucleotide polymorphisms (SNPs) of the NOS1AP gene had an AUC of 0.67 (95% confidence interval, CI: [0.59-0.75]). However, models incorporating baseline and SNP information resulted in improved AUC (0.80, 95% CI [0.73-0.87]). Innovation: We provide a rigorous analysis demonstrating the predictive potential of genetic information in DFU healing. In this process, we present a framework for using advanced statistical and bioinformatics techniques for creating superior prognostic models and identify potentially predictive SNPs for future research. Conclusion: We have developed a new benchmark for which future predictive models can be compared against. Such models will enable wound care experts to more accurately predict whether a patient will heal and aid clinical trialists in designing studies to evaluate therapies for subjects likely or unlikely to heal.

Cell-Type Specific Connectivity of Whisker-Related Sensory and Motor Cortical Input to Dorsal Striatum.

The anterior dorsolateral striatum (DLS) is heavily innervated by convergent excitatory projections from the primary motor (M1) and sensory cortex (S1) and considered an important site of sensorimotor integration. M1 and S1 corticostriatal synapses have functional differences in their connection strength with striatal spiny projection neurons (SPNs) and fast-spiking interneurons (FSIs) in the DLS and, as a result, exert distinct influences on sensory-guided behaviors. In the present study, we tested whether M1 and S1 inputs exhibit differences in the subcellular anatomical distribution of striatal neurons. We injected adeno-associated viral vectors encoding spaghetti monster fluorescent proteins (sm.FPs) into M1 and S1 in male and female mice and used confocal microscopy to generate 3D reconstructions of corticostriatal inputs to single identified SPNs and FSIs obtained through ex vivo patch clamp electrophysiology. We found that M1 and S1 dually innervate SPNs and FSIs; however, there is a consistent bias towards the M1 input in SPNs that is not found in FSIs. In addition, M1 and S1 inputs were distributed similarly across the proximal, medial, and distal regions of SPN and FSI dendrites. Notably, closely localized M1 and S1 clusters of inputs were more prevalent in SPNs than FSIs, suggesting that cortical inputs are integrated through cell-type specific mechanisms. Our results suggest that the stronger functional connectivity from M1 to SPNs compared to S1, as previously observed, is due to a higher quantity of synaptic inputs. Our results have implications for how sensorimotor integration is performed in the striatum through cell-specific differences in corticostriatal connections.

Patient Phenotyping for Atopic Dermatitis With Transformers and Machine Learning: Algorithm Development and Validation Study.

BACKGROUND: Atopic dermatitis (AD) is a chronic skin condition that millions of people around the world live with each day. Performing research into identifying the causes and treatment for this disease has great potential to provide benefits for these individuals. However, AD clinical trial recruitment is not a trivial task due to the variance in diagnostic precision and phenotypic definitions leveraged by different clinicians, as well as the time spent finding, recruiting, and enrolling patients by clinicians to become study participants. Thus, there is a need for automatic and effective patient phenotyping for cohort recruitment. OBJECTIVE: This study aims to present an approach for identifying patients whose electronic health records suggest that they may have AD. METHODS: We created a vectorized representation of each patient and trained various supervised machine learning methods to classify when a patient has AD. Each patient is represented by a vector of either probabilities or binary values, where each value indicates whether they meet a different criteria for AD diagnosis. RESULTS: The most accurate AD classifier performed with a class-balanced accuracy of 0.8036, a precision of 0.8400, and a recall of 0.7500 when using XGBoost (Extreme Gradient Boosting). CONCLUSIONS: Creating an automated approach for identifying patient cohorts has the potential to accelerate, standardize, and automate the process of patient recruitment for AD studies; therefore, reducing clinician burden and informing the discovery of better treatment options for AD.

Keratinocyte Carcinoma Incidence by Race and Ethnicity in Older Adults With Medicare Coverage.

This cohort study examines raw and age-adjusted differences in the incidence of keratinocyte carcinoma among Medicare beneficiaries by race and ethnicity.

Risk of atopic dermatitis and the atopic march paradigm in children of mothers with atopic illnesses: A birth cohort study from the United Kingdom.

BACKGROUND: Atopic dermatitis (AD) is thought to precede the onset of other allergic illness (OAI) in a temporal progression (ie, atopic march), yet the timing and progression has been questioned. It is also unclear how parental allergic illness impacts the development of these illnesses in offspring. OBJECTIVE: (1) Explore risk of incident AD and (2) timing of allergic disease onset in children of mothers with AD compared with mothers without AD from the United Kingdom. METHODS: We created a birth cohort of mother-child pairs using IQVIA Medical Research Data database and developed Cox proportional models to examine the above associations (hazard ratio, HR [95% confidence interval, CI]). RESULTS: Among 1,224,243 child-mother pairs, mean child (standard deviation) follow-up time was 10.8 (8.3) years and 50.1% were males (N = 600,905). Children were 59% (HR = 1.59 [1.57, 1.60]) more likely to have AD if their mothers had AD compared with no AD with mean age of first AD diagnosis at 3.3 (4.8) years. Most children with any diagnosis of AD present with AD first (91.0%); however, in those with asthma, only 67.8% developed AD first. CONCLUSION: Children born to mothers with AD are more prone to develop AD and some develop OAI first, suggesting that not all follow the same sequential pathway.

Skin Cancers in Medicare Beneficiaries With Actinic Keratoses.

Importance: Actinic keratoses (AK) are common premalignant skin lesions with a small risk of progressing to cutaneous squamous cell carcinoma (SCC). There is some evidence that patients with AKs also have increased risks of other skin cancers beyond SCC. However, the absolute risks of skin cancer in patients with AKs are unknown. Objective: To calculate the absolute and relative risks of future skin cancer in Medicare beneficiaries with AKs. Design, Setting, and Participants: This retrospective cohort study was performed using a deidentified, random sample of 4 999 999 fee-for-service Medicare beneficiaries from 2009 through 2018. Patients with treated AKs were included, and patients with seborrheic keratoses (SKs) were included as a comparator group. All patients were required to have at least 1 year between data set entry and first AK or SK. Patients with a history of skin cancer were excluded. Data were analyzed from September 2022 to March 2023. Main Outcomes and Measures: Outcomes were first surgically treated skin cancer, including keratinocyte carcinoma (including SCC and basal cell carcinoma [BCC]) and melanoma. The absolute risks of skin cancer in patients with AKs were evaluated. Skin cancer risks in patients with AKs were compared with patients with SKs using adjusted competing risks regression. Results: A total of 555 945 patients with AKs (mean [SD] age, 74.0 [7.4] years; 55.4% female) and 481 024 patients with SKs (mean [SD] age, 73.3 [7.3] years; 72.4% female) were included. The absolute risk of skin cancer after a first AK was 6.3% (95% CI, 6.3%-6.4%) at 1 year, 18.4% (95% CI, 18.3%-18.5%) at 3 years, and 28.5% (95% CI, 28.4%-28.7%) at 5 years. Patients with AKs had increased risk of skin cancer compared with patients with SKs (any skin cancer: adjusted hazard ratio [aHR], 2.17; 95% CI, 2.15-2.19; keratinocyte carcinoma: aHR, 2.20; 95% CI, 2.18-2.22; SCC: aHR, 2.63; 95% CI, 2.59-2.66; BCC: aHR, 1.85; 95% CI, 1.82-1.87; and melanoma: aHR, 1.67; 95% CI, 1.60-1.73). Conclusions and Relevance: In this cohort study, older patients with AKs had substantial absolute risks, as well as elevated relative risks, of skin cancer. AKs may be clinical markers of UV exposure and increased skin cancer risk, including SCC, BCC, and melanoma. However, guidelines are lacking for follow-up skin cancer surveillance in patients with AKs. Efforts to develop evidence-based recommendations for skin cancer surveillance in patients with AKs are paramount.

In utero or early in life exposure to antibiotics and the risk of childhood atopic dermatitis, a population-based cohort study.

BACKGROUND: Atopic dermatitis (AD) is a common inflammatory disease of the skin that begins early in life and can be lifelong. The purpose of our study was to evaluate whether fetal exposure and/or early life exposure of a child to antibiotics increases the risk of early onset AD. OBJECTIVE: We hypothesize that antibiotic exposure in utero or early in life (e.g., first 90 days) increases the likelihood that children develop AD. METHODS: Utilizing a large prospectively collected electronic medical records database, we studied the association of antibiotic exposure received in utero or very early in life and the relative risk of onset of AD in a population-based cohort study. Associations were estimated using proportional hazards models as hazard ratios (HR) with 95% confidence intervals (CI). RESULTS: The risk of AD in childhood was increased after in utero or early life antibiotic exposure. For any in utero AB exposure the HR was 1.38 (1.36,1.39). However, penicillin demonstrated the strongest association with AD for both in utero exposure, 1.43 (1.41,1.44), and for childhood exposure, 1.81(1.79,1.82). HRs were higher in children born to mothers without AD than those with AD pointing to effect modification by maternal AD status. CONCLUSION: Children born to mothers exposed to antibiotics while in utero had, depending on the mother's history of AD, approximately a 20 to 40% increased risk of developing AD. Depending on the antibiotic, children who received antibiotics early-in-life had a 40 to 80% increased risk of developing AD. Our study, supports and refines the association between incident AD and antibiotic administration. It also adds population-based support to therapeutic attempts to treat AD by modifying skin microbiome.

Patient Phenotyping for Atopic Dermatitis with Transformers and Machine Learning.

Background: Atopic dermatitis (AD) is a chronic skin condition that millions of people around the world live with each day. Performing research studies into identifying the causes and treatment for this disease has great potential to provide benefit for these individuals. However, AD clinical trial recruitment is a non-trivial task due to variance in diagnostic precision and phenotypic definitions leveraged by different clinicians as well as time spent finding, recruiting, and enrolling patients by clinicians to become study subjects. Thus, there is a need for automatic and effective patient phenotyping for cohort recruitment. Objective: Our study aims to present an approach for identifying patients whose electronic health records suggest that they may have AD. Methods: We created a vectorized representation of each patient and trained various supervised machine learning methods to classify when a patient has AD. Each patient is represented by a vector of either probabilities or binary values where each value indicates whether they meet a different criteria for AD diagnosis. Results: The most accurate AD classifier performed with a class-balanced accuracy of 0.8036, a precision of 0.8400, and a recall of 0.7500 when using XGBoost (Extreme Gradient Boosting). Conclusions: Creating an automated approach for identifying patient cohorts has the potential to accelerate, standardize, and automate the process of patient recruitment for AD studies; therefore, reducing clinician burden and informing knowledge discovery of better treatment options for AD.