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.

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.

No Association of filaggrin copy number variation and atopic dermatitis risk in White and Black Americans.

Atopic dermatitis (AD) is a chronic, inflammatory skin condition with a multifactorial pathophysiology. The filaggrin gene (FLG) has particularly been implicated given loss of function (LoF) mutations in this gene lead to skin barrier dysfunction and such mutations can increase a patient's likelihood of developing AD. FLG has intragenic copy number variation (CNV), which impacts the total amount of filaggrin produced. Previous research reported a dose-dependent effect such that as amount of FLG increases, risk of AD decreases. To gain a better understanding, we evaluated FLG CNV in a large case-control study of Whites and Blacks with and without AD. The goal of our study was to determine whether FLG CNV has a dose-dependent effect on the risk of developing AD and to determine whether FLG CNV varies by race. The frequencies and odds ratios comparing a given CNV by race or race within those with AD did not significantly vary. It had been thought that FLG CNV might vary by race and represent an important association with AD in Black AD subjects. However, our work suggests that while there are racial differences with respect to CNV, these differences do not appear to explain AD risk.

Untapping the potential of utilizing electronic medical records to identify patients with atopic dermatitis: an algorithm using ICD-10 codes.

Atopic Dermatitis (AD) is a chronic, inflammatory skin condition that imposes an enormous personal and economic burden in the United States. Due to the ubiquity of the use of electronic medical records (EMR) in the United States, utilizing such data is critically important to studying common dermatologic diseases, such as AD. Our goal was to create a simple-to-use algorithm applied to EMR data to accurately identify AD patients thereby making it possible to efficiently use EMR data to ascertain and then study individuals with AD. Our results suggest that the algorithm that is most likely to accurately identify AD patients from the EMR based on PPV utilizes ICD-10 code for L20.89, L20.9, or L20.84 in conjunction with a diagnosis code for asthma or allergic rhinitis, treatment code, and dermatology consult code. This approach yields a PPV of 95.00% in our training cohort and 100.00% in our validation cohort. Therefore, future studies can use this algorithm to better assure that a subject has AD for studies of the pathogenesis and/or potential treatment targets of AD.

Prophylactic Postoperative High Flow Nasal Oxygen Versus Conventional Oxygen Therapy in Obese Patients Undergoing Bariatric Surgery (OXYBAR Study): a Pilot Randomised Controlled Trial.

BACKGROUND: Patients with obesity are predisposed to a reduction in end-expiratory lung volume (EELV) and atelectasis after anaesthesia. High flow nasal oxygen (HFNO) may increase EELV, reducing the likelihood of postoperative pulmonary complications (PPC). We conducted a pilot randomised controlled trial (RCT) of conventional oxygen therapy versus HFNO after bariatric surgery. The aim was to investigate the feasibility of using electrical impedance tomography (EIT) as a means of assessing respiratory mechanics and to inform the design of a definitive RCT. METHODS: We performed a single-centre, parallel-group, pilot RCT. Adult patients with obesity undergoing elective bariatric surgery were eligible for inclusion. We excluded patients with a known contraindication to HFNO or with chronic lung disease. RESULTS: Fifty patients were randomised in equal proportions. One patient crossed over from conventional O2 to HFNO. Delta EELI was higher at 1 hour in patients receiving HFNO (mean difference = 831 Au (95% CI - 1636-3298), p = 0.5). Continuous EIT beyond 1 hour was poorly tolerated. At 6 hours, there were no differences in PaO2/FiO2 ratio or PaCO2. Only one patient developed a PPC (in the HFNO group) by 6 weeks. CONCLUSIONS: These data suggest that a large-scale RCT of HFNO after bariatric surgery in an 'all-comers' population is likely infeasible. While EIT was an effective means of assessing respiratory mechanics, it was impractical over time. Similarly, the infrequency of PPC precludes its use as a primary outcome. Future studies should focus on identifying patients at the greatest risk of PPC.

Patient Perspectives on the Lived Experience of Acne and Its Treatment Among Adult Women With Acne: A Qualitative Study.

INTRODUCTION: Acne often persists into adulthood in women. However, few studies have specifically explored the lived experience of acne in adult populations. OBJECTIVE: To examine the lived experience of acne and its treatment among a cohort of adult women. DESIGN, SETTING, AND PARTICIPANTS: A qualitative analysis was conducted from free listing and open-ended, semistructured interviews of patients at a large academic health care system (University of Pennsylvania Health System) and a private practice (Dermatologists of Southwest Ohio). Fifty women 18 to 40 years of age with moderate to severe acne participated in interviews conducted between August 30, 2019, and December 31, 2020. MAIN OUTCOMES AND MEASURES: Free-listing data from interviews were used to calculate the Smith S, a measure of saliency for each list item. Semistructured interviews were examined to detect themes about patient perspectives regarding their acne and its treatment. RESULTS: Fifty participants (mean [SD] age, 28 [5.38] years; 24 [48%] White) described acne-related concerns about their appearance that affected their social, professional, and personal lives, with many altering their behavior because of their acne. Depression, anxiety, and social isolation were commonly reported. Participants described successful treatment as having completely clear skin over time or a manageable number of blemishes. Many participants described frustration with finding a dermatologist with whom they were comfortable and with identifying effective treatments for their acne. CONCLUSIONS AND RELEVANCE: The results of this qualitative study suggest that women with acne have strong concerns about appearance and experience mental and emotional health consequences and disruption of their personal and professional lives. In addition, many patients describe challenges finding effective treatments and accessing care. Future trials to understand the optimal treatment approaches for women with acne are needed to improve outcomes in this population.

High flow nasal oxygen after bariatric surgery (OXYBAR), prophylactic post-operative high flow nasal oxygen versus conventional oxygen therapy in obese patients undergoing bariatric surgery: study protocol for a randomised controlled pilot trial.

BACKGROUND: The incidence of obesity is increasing worldwide. In selected individuals, bariatric surgery may offer a means of achieving long-term weight loss, improved health, and healthcare cost reduction. Physiological changes that occur because of obesity and general anaesthesia predispose to respiratory complications following bariatric surgery. The aim of this study is to determine whether post-operative high flow nasal oxygen therapy (HFNO2) improves respiratory function and reduces the incidence of post-operative pulmonary complications (PPCs) in comparison to conventional oxygen therapy in these patients. METHOD: The OXYBAR study is a prospective, un-blinded, single centre, randomised, controlled pilot study. Patients with body mass index (BMI) > 30 kg/m2, undergoing laparoscopic bariatric surgery, will be randomised to receive either standard low flow oxygen therapy or HFNO2 in the post-operative period. The primary outcome measure is the change in end expiratory lung impedance (∆EELI) as measured by electrical impedance tomography (EIT). Secondary outcome measures include change in tidal volume (∆Vt), partial arterial pressure of oxygen/fraction of inspired oxygen (PaO2/FiO2) ratio, incidence of PPCs, hospital length of stay and measures of patient comfort. DISCUSSION: We hypothesise that the post-operative administration of HFNO2 will increase EELI and therefore end expiratory lung volume (EELV) in obese patients. To our knowledge this is the first trial designed to assess the effects of HFNO2 on EELV in this population. We anticipate that data collected during this pilot study will inform a larger multicentre trial. TRIAL REGISTRATION: Australian New Zealand Clinical Trials Registry (ANZCTR), ACTRN12617000694314 . Registered on 15 May 2017.

Pre-operative chemoradiation for non-metastatic locally advanced rectal cancer.

BACKGROUND: This review sets out to assess the efficacy of pre-operative chemoradiation when compared to radiotherapy alone before surgery in the treatment of advanced non metastatic rectal surgery. OBJECTIVES: To determine the efficacy of pre-operative chemoradiation (CRT) compared with radiation (RT) alone, in locally advanced rectal cancer with respect to overall survival, local recurrence and 30 day mortality, sphincter preservation and toxicity of treatment (both acute and late). SEARCH METHODS: In September 2011, we searched clinical trial registers, the Cochrane Central Register of Controlled Trials, Web of Science, EMBASE and MEDLINE and reviewed reference lists. Further hand searches were conducted of relevant journal proceedings. No language constraints were applied.The following search terms were used: colorectal, rectal, rectum, cancer, carcinoma, tumour, radiotherapy, chemotherapy, chemoradiotherapy, chemoradiation, 5-Fluorouracil, 5-FU, neo-adjuvant, preoperative, surgery, anterior resection, abdominoperineal resection, total mesorectal excision. SELECTION CRITERIA: Male and female patients aged over 18 years undergoing preoperative chemoradiation or radiotherapy followed by surgery for locally advanced non-metastatic rectal cancer. There was no upper age limit for participants. Locally advanced non-metastatic cancer was defined as stage 3 rectal tumours. These are tumours of any T stage with nodal involvement, without evidence of distant metastases. DATA COLLECTION AND ANALYSIS: Primary outcome parameters included overall survival and local recurrence rate. Secondary outcome parameters included 30 day mortality, sphincter preservation, pathological response of tumour, acute and late toxicity of treatment. The outcome parameters were summarized using the odds ratio and 95% confidence intervals (CI). MAIN RESULTS: There were 6 randomised controlled trials eligible for inclusion. A reduction in local recurrence was seen in the CRT group in comparison to the RT group (OR 0.56, 95% CI 0.42-0.75, P<0.0001). The results for overall survival were (OR=1.01 95%CI 0.85-1.20, P=0.88).The 30 day mortality was the same for both groups, CRT vs RT (OR 1.73, 95% CI 0.88-3.38). Sphincter preservation (stoma rate) was also similar for the two interventions (OR 1.02, 95% CI 0.85-1.21, P=0.64). An increase in acute grade 3/4 treatment related toxicity was seen in the CRT group versus the RT group (OR 3.96, 95% CI 3.03, 5.17, P<0.00001), although this result did display heterogeneity P=0.0005. Late toxicity events were similar between the two groups (OR 0.88, 95% CI 0.50, 1.54, P=0.65). AUTHORS' CONCLUSIONS: RT was compared to the more intensive CRT in the treatment of T3-4, node positive (locally advanced) rectal cancer. While there was no difference in overall survival between RT and CRT, CRT was associated with less local recurrence.