Three Epochs of Artificial Intelligence in Health Care

Importance

Interest in artificial intelligence (AI) has reached an all-time high, and health care leaders across the ecosystem are faced with questions about where, when, and how to deploy AI and how to understand its risks, problems, and possibilities.

Observations

While AI as a concept has existed since the 1950s, all AI is not the same. Capabilities and risks of various kinds of AI differ markedly, and on examination 3 epochs of AI emerge. AI 1.0 includes symbolic AI, which attempts to encode human knowledge into computational rules, as well as probabilistic models. The era of AI 2.0 began with deep learning, in which models learn from examples labeled with ground truth. This era brought about many advances both in people's daily lives and in health care. Deep learning models are task-specific, meaning they do one thing at a time, and they primarily focus on classification and prediction. AI 3.0 is the era of foundation models and generative AI. Models in AI 3.0 have fundamentally new (and potentially transformative) capabilities, as well as new kinds of risks, such as hallucinations. These models can do many different kinds of tasks without being retrained on a new dataset. For example, a simple text instruction will change the model's behavior. Prompts such as "Write this note for a specialist consultant" and "Write this note for the patient's mother" will produce markedly different content.

Conclusions and Relevance

Foundation models and generative AI represent a major revolution in AI's capabilities, ffering tremendous potential to improve care. Health care leaders are making decisions about AI today. While any heuristic omits details and loses nuance, the framework of AI 1.0, 2.0, and 3.0 may be helpful to decision-makers because each epoch has fundamentally different capabilities and risks.

Baseline Levels of Circulating Inflammatory Biomarkers Stratify Patients with Vitiligo Who Significantly Repigment after Treatment with Ruxolitinib Cream

BACKGROUND

Efficacy of ruxolitinib cream, a topical Jak1/Jak2 inhibitor, was demonstrated in a phase 2 trial in patients with vitiligo.

OBJECTIVE

This study aimed to characterize circulating inflammatory biomarker profiles in patients who demonstrated ≥50% improvement in facial Vitiligo Area Scoring Index scores by week 24 (group 1) and those who did not (group 2).

DESIGN

This was a posthoc analysis of a multicenter, randomized, double-blind, vehicle-controlled, phase 2 study in which screening was conducted between June 7, 2017 and March 21, 2018.

POPULATION

Patients aged between 18 and 75 years with vitiligo, including depigmentation affecting ≥0.5% of body surface area on the face and ≥3% of body surface area on nonfacial areas, were eligible.

INTERVENTION

Patients applied 1.5% ruxolitinib cream to lesions once or twice daily for 52 weeks.

MAIN OUTCOMES AND MEASURES

Patients were grouped by achievement of ≥50% improvement in facial Vitiligo Area Scoring Index at week 24. Proteomic analysis was performed on baseline serum samples.

RESULTS

Mean ± standard error facial Vitiligo Area Scoring Index in group 1 (n = 30) versus group 2 (n = 27) improved by 79.9 ± 4.0% versus 1.1 ± 7.3% and 91.9 ± 1.5% versus 25.1 ± 13.4% at weeks 24 and 52, respectively. Broad proteomic analysis revealed 76 proteins (of 1,104 tested) that were differentially expressed between groups 1 and 2 at baseline (P < 0.05). Ten distinct proteins were upregulated in group 1; 64 were elevated in group 2.

CONCLUSION

This analysis identified potential differences between patients who achieved ≥50% improvement in facial Vitiligo Area Scoring Index at 24 weeks and those who did not that require deeper scientific interrogation and may be important in stratifying therapeutic benefit for patients with vitiligo.

TRIAL REGISTRATION

The original study was registered at ClinicalTrials.gov, NCT03099304.

A biomarker signature to predict complete response to itacitinib and corticosteroids in acute graft-versus-host disease

A broad proteomic analysis was conducted to identify and evaluate candidate biomarkers potentially predictive of response to treatment with an oral selective Janus kinase 1 (JAK1) inhibitor, itacitinib, in acute graft‐versus‐host disease (GVHD). Plasma samples from 25 participants (identification cohort; NCT02614612) were used to identify novel biomarkers that were tested in a validation cohort from a placebo‐controlled, randomised trial (n = 210; NCT03139604). The identification cohort received corticosteroids plus 200 or 300 mg itacitinib once daily. The validation cohort received corticosteroids plus 200 mg itacitinib once daily or placebo. A broad proteomic analysis was conducted using a proximity extension assay. Baseline and longitudinal comparisons were performed with unpaired t‐test and one‐way analysis of variance used to evaluate biomarker level changes. Seven candidate biomarkers were identified. Monocyte‐chemotactic protein (MCP)3, pro‐calcitonin/calcitonin (ProCALCA/CALCA), together with a previously identified prognostic acute GVHD biomarker, regenerating islet‐derived protein (REG)3A, stratified complete responders from non‐responders (participants with progressive disease) to itacitinib, but not placebo, potentially representing predictive biomarkers of itacitinib in acute GVHD. ProCALCA/CALCA, suppressor of tumorigenicity (ST)2, and tumour necrosis factor receptor (TNFR)1 were significantly reduced over time by itacitinib in responders, potentially representing response‐to‐treatment biomarkers. Novel biomarkers have the potential to identify patients with acute GVHD that may respond to itacitinib plus corticosteroid treatment (NCT02614612; NCT03139604).

Patient and Clinician Perceptions of Factors Relevant to Ideal Specialty Consultations

IMPORTANCE

Inpatient subspecialty consultations, a common and expensive practice within inpatient medicine, do not always go well; however, little is known about the failure modes of consultation, thus making it difficult to identify interventions to improve consultation quality.

OBJECTIVE

To understand how stakeholders envision the ideal inpatient consultation and identify how and why consultations commonly fall short of this ideal.

DESIGN, SETTING, AND PARTICIPANTS

This qualitative study used in-depth, semistructured interviews collected from April to October 2017 and analyzed from January 2018 to February 2020 using conventional content analysis. The setting was a single academic medical center in Boston, Massachusetts. Participants were hospitalists and specialists who had requested or performed a consultation for a non-intensive care unit patient in the previous 4 months, patients who had received a consultation while hospitalized at the medical center in the previous 15 months, and family members of such patients.

MAIN OUTCOMES AND MEASURES

Consultation experiences reported by participants. Clinicians were asked about characteristics of the ideal consultation, positive and negative consultation experiences, costs and benefits, and suggested improvements. Patients and family members were asked about their consultation experience, changes in care, communication preferences, and suggested improvements.

RESULTS

The study included 38 participants: 17 specialists, 13 hospitalists, 4 patients, and 4 family members. More than half (21 of 38) of the participants were female. There were 11 key information exchanges identified that occur among the specialist team, primary team, and patient/family during an ideal consultation. These exchanges are time sensitive and primarily carried out through unwritten protocols. We also identified 6 defects (process failures) that commonly derail information exchanges (complete omission, exclusion of a key stakeholder, poor timing, incomplete or inaccurate information, and misinterpretation) and 5 contextual factors (roles and boundaries, professionalism, team hierarchy, availability, and operational know-how) that influence how information exchange unfolds, making some consultations more prone to defects.

CONCLUSIONS AND RELEVANCE

Successful inpatient consultation requires a complicated, sequenced series of time-sensitive information exchanges that are highly vulnerable to failure. Maximizing the benefit of consultations will likely entail not only minimizing low-value consultations but also actively preventing defects, such as information inaccuracies and misinterpretation, that commonly derail the consultation process.

Janus kinase 1 inhibitor INCB054707 for patients with moderate-to-severe hidradenitis suppurativa: results from two phase 2 studies

Background

Janus kinase (JAK)‐mediated cytokine signalling contributes to local and systemic inflammation in hidradenitis suppurativa (HS).

Objectives

To describe the safety and efficacy results from two multicentre phase II trials of the JAK1 inhibitor INCB054707 in patients with moderate‐to‐severe HS.

Methods

Patients received open‐label INCB054707 15 mg once daily (QD; Study 1) or were randomized to INCB054707 30, 60 or 90 mg QD or placebo (3 : 1 within each cohort; Study 2) for 8 weeks. Eligible patients were aged 18–75 years and had moderate‐to‐severe HS (Hurley stage II/III disease), lesions present in at least two anatomical locations, and a total abscess and inflammatory nodule count ≥ 3. The primary endpoint for both studies was safety and tolerability. Secondary endpoints included HS Clinical Response (HiSCR) and other efficacy measures.

Results

Ten patients were enrolled in Study 1 (15 mg INCB054707) and 35 in Study 2 (INCB054707: 30 mg, n = 9; 60 mg, n = 9; 90 mg, n = 8; placebo, n = 9). Overall, 70% of patients in Study 1 and 81% of patients receiving INCB054707 in Study 2 experienced at least one treatment‐emergent adverse event; 30% and 42% of patients, respectively, had at least one treatment‐related adverse event. Among the evaluable patients, three (43%) in Study 1 and 17 (65% overall: 30 mg, 56%; 60 mg, 56%; 90 mg, 88%) receiving INCB054707 vs. 4 patients (57%) receiving placebo in Study 2 achieved HiSCR at week 8.

Conclusions

INCB054707 was well tolerated, with responses observed in patients with moderate‐to‐severe HS. The safety and efficacy findings from these studies demonstrate proof of concept for JAK1 inhibition in HS. The studies are registered on ClinicalTrials.gov (NCT03569371 and NCT03607487).

Privacy-first health research with federated learning

Privacy protection is paramount in conducting health research. However, studies often rely on data stored in a centralized repository, where analysis is done with full access to the sensitive underlying content. Recent advances in federated learning enable building complex machine-learned models that are trained in a distributed fashion. These techniques facilitate the calculation of research study endpoints such that private data never leaves a given device or healthcare system. We show-on a diverse set of single and multi-site health studies-that federated models can achieve similar accuracy, precision, and generalizability, and lead to the same interpretation as standard centralized statistical models while achieving considerably stronger privacy protections and without significantly raising computational costs. This work is the first to apply modern and general federated learning methods that explicitly incorporate differential privacy to clinical and epidemiological research-across a spectrum of units of federation, model architectures, complexity of learning tasks and diseases. As a result, it enables health research participants to remain in control of their data and still contribute to advancing science-aspects that used to be at odds with each other.

Modeling Skin Inflammation Using Human In Vitro Models

Skin is made up of an epidermis and, dermis which serve as a barrier against physical and environmental threats. Keratinocytes make up greater than 95% of the epidermis and form different layers based on their level of differentiation. Millions of individuals suffer from skin diseases, which are characterized by significant barrier disruption and inflammation. Investigators previously relied on animal models to investigate inflammatory skin diseases; however, technological advances have enabled the use of physiologically human skin models to investigate the effects of inflammatory mediators on the structure and function of skin cells. In this article, we describe two protocols using keratinocytes to investigate tumor necrosis factor alpha (TNF-α) and interferon gamma (IFN-γ) driven skin inflammation as a surrogate for psoriasis, vitiligo, and other autoimmune skin diseases driven by these cytokines. © 2021 Wiley Periodicals LLC. Basic Protocol 1: Preparing a HaCaT keratinocyte culture Basic Protocol 2: 3-Dimensional organotypic skin cultures to assess TNF-α and IFN-γ driven skin inflammation.

Interplay between Humoral and CLA+ T Cell Response against Candida albicans in Psoriasis

Candida albicans (CA) infections have been associated with psoriasis onset or disease flares. However, the integrated immune response against this fungus is still poorly characterized in psoriasis. We studied specific immunoglobulins in plasma and the CA response in cocultures of circulating memory CD45RA^- cutaneous lymphocyte antigen (CLA)^+/- T cell with autologous epidermal cells from plaque and guttate psoriasis patients (cohort 1, n = 52), and also healthy individuals (n = 17). A complete proteomic profile was also evaluated in plaque psoriasis patients (cohort 2, n = 114) regarding their anti-CA IgA levels. Increased anti-CA IgA and IgG levels are present in the plasma from plaque but not guttate psoriasis compared to healthy controls. CA cellular response is confined to CLA⁺ T cells and is primarily Th17. The levels of anti-CA IgA are directly associated with CLA⁺ Th17 response in plaque psoriasis. Proteomic analysis revealed distinct profiles in psoriasis patients with high anti-CA IgA. C-C motif chemokine ligand 18, chitinase-3-like protein 1 and azurocidin were significantly elevated in the plasma from plaque psoriasis patients with high anti-CA levels and severe disease. Our results indicate a mechanism by which Candida albicans exposure can trigger a clinically relevant IL-17 response in psoriasis. Assessing anti-CA IgA levels may be useful in order to evaluate chronic psoriasis patients.

Ruxolitinib cream for treatment of vitiligo: a randomised, controlled, phase 2 trial

BACKGROUND

Vitiligo is a chronic autoimmune disease resulting in skin depigmentation and reduced quality of life. There is no approved treatment for vitiligo repigmentation and current off-label therapies have limited efficacy, emphasising the need for improved treatment options. We investigated the therapeutic potential of ruxolitinib cream in patients with vitiligo and report the efficacy and safety results up to 52 weeks of double-blind treatment.

METHODS

We did a multicentre, randomised, double-blind, phase 2 study for adult patients with vitiligo in 26 US hospitals and medical centres in 18 states. Patients with depigmentation of 0·5% or more of their facial body surface area (BSA) and 3% or more of their non-facial BSA were randomly assigned (1:1:1:1:1) by use of an interactive response technology system to receive ruxolitinib cream (1·5% twice daily, 1·5% once daily, 0·5% once daily, or 0·15% once daily) or vehicle (control group) twice daily on lesions constituting 20% or less of their total BSA for 24 weeks. Patients in the control group in addition to patients in the 0·15% once daily group who did not show a 25% or higher improvement from baseline in facial Vitiligo Area Scoring Index (F-VASI) at week 24 were re-randomised to one of three higher ruxolitinib cream doses (0·5% once daily, 1·5% once daily, 1·5% twice daily). Patients in the 0·5% once daily, 1·5% once daily, or 1·5% twice daily groups remained at their original dose up to week 52. Patients, investigators, and the study sponsor (except members of the interim analysis and primary endpoint analysis data monitoring teams) remained masked to treatment assignment throughout the study. The primary endpoint was the proportion of patients achieving a 50% or higher improvement from baseline in F-VASI (F-VASI50) at week 24, assessed in the intention-to-treat population. The study is registered with ClinicalTrials.gov, NCT03099304.

FINDINGS

Between June 7, 2017, and March 21, 2018, 205 patients were screened for eligibility, 48 were excluded and 157 patients (mean age, 48·3 years [SD 12·9]; 73 [46%] male and 84 [54%] female) were randomly assigned to either an intervention group or the control group. 32 (20%) of 157 were assigned to the control group, 31 (20%) to the 0·15% once daily group, 31 (20%) to the 0·5% once daily group, 30 (19%) to the 1·5% once daily group, and 33 (21%) to the 1·5% twice daily group. F-VASI50 at week 24 was reached by significantly more patients given ruxolitinib cream at 1·5% twice daily (15 [45%] of 33) and 1·5% once daily (15 [50%] of 30) than were treated with vehicle (one [3%] of 32). Four patients had serious treatment-emergent adverse events (one patient in the 1·5% twice daily group developed subdural haematoma; one patient in the 1·5% once daily group had a seizure; one patient in the 0·5% once daily group had coronary artery occlusion; and one patient in the 0·5% once daily group had oesophageal achalasia), all of which were unrelated to study treatment. Application site pruritus was the most common treatment-related adverse event among patients given ruxolitinib cream (one [3%] of 33 in the 1·5% twice daily group; three [10%] of 30 in the 1·5% once daily group; three [10%] of 31 in the 0·5% once daily group; and six [19%] of 31 in the 0·15% once daily group)with three [9%] of 32 patients showing application site pruritis in the control group. Acne was noted as a treatment-related adverse event in 13 (10%) of 125 patients who received ruxolitinib cream and one (3%) of 32 patients who received vehicle cream. All treatment-related adverse events were mild or moderate in severity and similar across treatment groups.

INTERPRETATION

Treatment with ruxolitinib cream was associated with substantial repigmentation of vitiligo lesions up to 52 weeks of treatment, and all doses were well tolerated. These data suggest that ruxolitinib cream might be an effective treatment option for patients with vitiligo.

FUNDING

Incyte.

Bundled Consent in US Intensive Care Units

BACKGROUND

Bundled consent, the practice of obtaining anticipatory consent for a predefined set of intensive care unit procedures, increases the rate of informed consent conversations and incorporation of patients' wishes into medical decision-making without sacrificing patients' or surrogates' understanding. However, the adoption rate for this practice in academic and nonacademic centers in the United States is unknown.

OBJECTIVE

To determine the national prevalence of use of bundled consent in adult intensive care units and opinions related to bundled consent.

METHODS

A random sample of US hospitals with medical/surgical intensive care units was selected from the AHA [American Hospital Association] Guide. One intensive care unit provider (bedside nurse, nurse manager, or physician) from each hospital was asked to self-reportuse of per-procedure consent versus bundled consent, consent rate for intensive care unit procedures, and opinions about bundled consent.

RESULTS

Of the 238 hospitals contacted, respondents from 100 (42%) completed the survey; 94% of respondents were nurses. The prevalence of bundled consent use was 15% (95% CI, 9%-24%). Respondents using per-procedure consent were more likely than those using bundled consent to self-report performing invasive procedures without consent. Users of bundled consent unanimously recommended the practice, and 49% of respondents using per-procedure consent reported interest in implementing bundled consent.

RESULTS

Bundled consent use is uncommon in academic and nonacademic intensive care units, most likely because of conflicting evidence about the effect on patients and surrogate decision makers. Future work is needed to determine if patients, family members, and providers prefer bundled consent over per-procedure consent.

Predicting Inpatient Medication Orders From Electronic Health Record Data

In a general inpatient population, we predicted patient‐specific medication orders based on structured information in the electronic health record (EHR). Data on over three million medication orders from an academic medical center were used to train two machine‐learning models: A deep learning sequence model and a logistic regression model. Both were compared with a baseline that ranked the most frequently ordered medications based on a patient’s discharge hospital service and amount of time since admission. Models were trained to predict from 990 possible medications at the time of order entry. Fifty‐five percent of medications ordered by physicians were ranked in the sequence model’s top‐10 predictions (logistic model: 49%) and 75% ranked in the top‐25 (logistic model: 69%). Ninety‐three percent of the sequence model’s top‐10 prediction sets contained at least one medication that physicians ordered within the next day. These findings demonstrate that medication orders can be predicted from information present in the EHR.

Customization scenarios for de-identification of clinical notes

BACKGROUND

Automated machine-learning systems are able to de-identify electronic medical records, including free-text clinical notes. Use of such systems would greatly boost the amount of data available to researchers, yet their deployment has been limited due to uncertainty about their performance when applied to new datasets.

OBJECTIVE

We present practical options for clinical note de-identification, assessing performance of machine learning systems ranging from off-the-shelf to fully customized.

METHODS

We implement a state-of-the-art machine learning de-identification system, training and testing on pairs of datasets that match the deployment scenarios. We use clinical notes from two i2b2 competition corpora, the Physionet Gold Standard corpus, and parts of the MIMIC-III dataset.

RESULTS

Fully customized systems remove 97-99% of personally identifying information. Performance of off-the-shelf systems varies by dataset, with performance mostly above 90%. Providing a small labeled dataset or large unlabeled dataset allows for fine-tuning that improves performance over off-the-shelf systems.

CONCLUSION

Health organizations should be aware of the levels of customization available when selecting a de-identification deployment solution, in order to choose the one that best matches their resources and target performance level.

Targeting the Janus Kinase Family in Autoimmune Skin Diseases

Autoimmune skin diseases are characterized by significant local and systemic inflammation that is largely mediated by the Janus kinase (JAK)-signal transducer and activator of transcription (STAT) pathway. Advanced understanding of this pathway has led to the development of targeted inhibitors of Janus kinases (JAKinibs). As a class, JAK inhibitors effectively treat a multitude of hematologic and inflammatory diseases. Growing evidence suggests that JAK inhibitors are efficacious in atopic dermatitis, alopecia areata, psoriasis, and vitiligo. Additional evidence suggests that JAK inhibition might be broadly useful in dermatology, with early reports of efficacy in several other conditions. JAK inhibitors can be administered orally or used topically and represent a promising new class of medications. Here we review the evolving data on the role of the JAK-STAT pathway in inflammatory dermatoses and the potential therapeutic benefit of JAK-STAT antagonism.

The Practice of Respect in the ICU

Although "respect" and "dignity" are intuitive concepts, little formal work has addressed their systematic application in the ICU setting. After convening a multidisciplinary group of relevant experts, we undertook a review of relevant literature and collaborative discussions focused on the practice of respect in the ICU. We report the output of this process, including a summary of current knowledge, a conceptual framework, and a research program for understanding and improving the practice of respect and dignity in the ICU. We separate our report into findings and proposals. Findings include the following: 1) dignity and respect are interrelated; 2) ICU patients and families are vulnerable to disrespect; 3) violations of respect and dignity appear to be common in the ICU and overlap substantially with dehumanization; 4) disrespect may be associated with both primary and secondary harms; and 5) systemic barriers complicate understanding and the reliable practice of respect in the ICU. Proposals include: 1) initiating and/or expanding a field of research on the practice of respect in the ICU; 2) treating "failures of respect" as analogous to patient safety events and using existing quality and safety mechanisms for improvement; and 3) identifying both benefits and potential unintended consequences of efforts to improve the practice of respect. Respect and dignity are important considerations in the ICU, even as substantial additional research remains to be done.

Measuring the quality of inpatient specialist consultation in the intensive care unit: Nursing and family experiences of communication

Rationale

Critically ill patients in the intensive care unit (ICU) often require the care of specialist physicians for clinical or procedural expertise. The current state of communication between specialist physicians and families and nurses has not been explored.

Objectives

To document the receipt of communication by nurses and family members regarding consultations performed on their patient or loved one, and to quantify how this impacts their overall perceptions of the quality of specialty care.

Methods

Prospective survey of 60 adult family members and 90 nurses of 189 ICU patients who received a specialist consultation between March and October of 2015 in a single academic medical center in the United States. Surveys measured the prevalence of direct communication—defined as communication conducted in person, via telephone, or via text-page in which the specialist team gathered information about the patient from the nurse/family member and/or shared recommendations for care—and perceived quality of care.

Results

In about two-thirds of family surveys (40/60) and one-half of nurse surveys (75/160), respondents had no direct communication with the specialist team that performed the consultation. Compared to nurses who had no direct communication with the specialists, those who did were 1.5 times more likely to rate the consultation as “excellent” (RR 1.48, 95% CI 1.2–1.8, p<0.001). Nearly 40% (22/60) of families knew so little about the consultation that they felt incapable of evaluating it.

Conclusions

Most ICU families and nurses have no interaction with specialist providers. Nurses’ frequent exclusion from conversations about specialty care may pose safety risks and increase the likelihood of mixed messages for patients and families, most of whom desire some interaction with specialists. Future research is needed to identify effective mechanisms for information sharing that keep nurses and families aware of consultation requests, delivery, and outcomes without increasing the risk of mixed messages.

Ensuring Fairness in Machine Learning to Advance Health Equity

Machine learning is used increasingly in clinical care to improve diagnosis, treatment selection, and health system efficiency. Because machine-learning models learn from historically collected data, populations that have experienced human and structural biases in the past-called protected groups-are vulnerable to harm by incorrect predictions or withholding of resources. This article describes how model design, biases in data, and the interactions of model predictions with clinicians and patients may exacerbate health care disparities. Rather than simply guarding against these harms passively, machine-learning systems should be used proactively to advance health equity. For that goal to be achieved, principles of distributive justice must be incorporated into model design, deployment, and evaluation. The article describes several technical implementations of distributive justice-specifically those that ensure equality in patient outcomes, performance, and resource allocation-and guides clinicians as to when they should prioritize each principle. Machine learning is providing increasingly sophisticated decision support and population-level monitoring, and it should encode principles of justice to ensure that models benefit all patients.

Bridging the Gap: Interdepartmental Quality Improvement and Patient Safety Curriculum Created by Hospital Leaders, Faculty, and Trainees

BACKGROUND

The Accreditation Council for Graduate Medical Education Clinical Learning Environment Review recommends that quality improvement/patient safety (QI/PS) experts, program faculty, and trainees collectively develop QI/PS education.

OBJECTIVE

Faculty, hospital leaders, and resident and fellow champions at the University of Chicago designed an interdepartmental curriculum to train postgraduate year 1 (PGY-1) residents on core QI/PS principles, measuring outcomes of knowledge, attitudes, and event reporting.

METHODS

The curriculum consisted of 3 sessions: PS, quality assessment, and QI. Faculty and resident and fellow leaders taught foundational knowledge, and hospital leaders discussed institutional priorities. PGY-1 residents attended during protected conference times, and they completed in-class activities. Knowledge and attitudes were assessed using pretests and posttests; graduating residents (PGY-3-PGY-8) were controls. Event reporting was compared to a concurrent control group of nonparticipating PGY-1 residents.

RESULTS

From 2015 to 2017, 140 interns in internal medicine (49%), pediatrics (33%), and surgery (13%) enrolled, with 112 (80%) participating and completing pretests and posttests. Overall, knowledge scores improved (44% versus 57%, P < .001), and 72% of residents demonstrated increased knowledge. Confidence comprehending quality dashboards increased (13% versus 49%, P < .001). PGY-1 posttest responses were similar to those of 252 graduate controls for accessibility of hospital leaders, filing event reports, and quality dashboards. PGY-1 residents in the QI/PS curriculum reported more patient safety events than PGY-1 residents not exposed to the curriculum (0.39 events per trainee versus 0.10, P < .001).

CONCLUSIONS

An interdepartmental curriculum was acceptable to residents and feasible across 3 specialties, and it was associated with increased event reporting by participating PGY-1 residents.

Failures in the Respectful Care of Critically Ill Patients

BACKGROUND

The emotional toll of critical illness on patients and their families can be profound and is emerging as an important target for value improvement. One source of emotional harm to patients and families may be care perceived as inadequately respectful. The prevalence and risk factors for types of emotional harms is under-studied.

METHODS

This prospective cohort study was conducted in nine ICUs at a tertiary care academic medical center in the United States. Prevalence of inadequate respect for (a) the patient and (b) the family, as well as prevalence of perceived lack of control over the care of their loved ones, was assessed by the Family Satisfaction with Care in the Intensive Care Unit instrument. The relationship between these outcomes with demographic and clinical covariates was assessed. Stratification by patient survivorship was performed in sensitivity analysis.

RESULTS

Of more than 1,500 respondents, 16.9% and 21.8% reported that the patient or the family member, respectively, received inadequate respect. No clinical characteristics of the patients were associated with inadequate respect for either the patient or the family member. By comparison, more than half of respondents reported a lack of control over their loved one's care; this finding was associated with multiple clinical factors. Prevalence and associated factors differed by patient survivorship status.

CONCLUSION

Care that is inadequately respectful to patients and families in the setting of critical illness is prevalent but does not appear to be associated with clinical characteristics. The incidence of such emotional harms is nuanced, difficult to predict, and deserves further investigation.

Predicting Intensive Care Unit Readmission with Machine Learning Using Electronic Health Record Data

RATIONALE

Patients transferred from the intensive care unit to the wards who are later readmitted to the intensive care unit have increased length of stay, healthcare expenditure, and mortality compared with those who are never readmitted. Improving risk stratification for patients transferred to the wards could have important benefits for critically ill hospitalized patients.

OBJECTIVES

We aimed to use a machine-learning technique to derive and validate an intensive care unit readmission prediction model with variables available in the electronic health record in real time and compare it to previously published algorithms.

METHODS

This observational cohort study was conducted at an academic hospital in the United States with approximately 600 inpatient beds. A total of 24,885 intensive care unit transfers to the wards were included, with 14,962 transfers (60%) in the training cohort and 9,923 transfers (40%) in the internal validation cohort. Patient characteristics, nursing assessments, International Classification of Diseases, Ninth Revision codes from prior admissions, medications, intensive care unit interventions, diagnostic tests, vital signs, and laboratory results were extracted from the electronic health record and used as predictor variables in a gradient-boosted machine model. Accuracy for predicting intensive care unit readmission was compared with the Stability and Workload Index for Transfer score and Modified Early Warning Score in the internal validation cohort and also externally using the Medical Information Mart for Intensive Care database (n = 42,303 intensive care unit transfers).

RESULTS

Eleven percent (2,834) of discharges to the wards were later readmitted to the intensive care unit. The machine-learning-derived model had significantly better performance (area under the receiver operating curve, 0.76) than either the Stability and Workload Index for Transfer score (area under the receiver operating curve, 0.65), or Modified Early Warning Score (area under the receiver operating curve, 0.58; P value < 0.0001 for all comparisons). At a specificity of 95%, the derived model had a sensitivity of 28% compared with 15% for Stability and Workload Index for Transfer score and 7% for the Modified Early Warning Score. Accuracy improvements with the derived model over Modified Early Warning Score and Stability and Workload Index for Transfer were similar in the Medical Information Mart for Intensive Care-III cohort.

CONCLUSIONS

A machine learning approach to predicting intensive care unit readmission was significantly more accurate than previously published algorithms in both our internal validation and the Medical Information Mart for Intensive Care-III cohort. Implementation of this approach could target patients who may benefit from additional time in the intensive care unit or more frequent monitoring after transfer to the hospital ward.

Prevalence of Dyspnea Among Hospitalized Patients at the Time of Admission

CONTEXT

Dyspnea is an uncomfortable and distressing sensation experienced by hospitalized patients.

OBJECTIVES

There is no large-scale study of the prevalence and intensity of patient-reported dyspnea at the time of admission to the hospital.

METHODS

Between March 2014 and September 2016, we conducted a prospective cohort study among all consecutive hospitalized patients at a single tertiary care center in Boston, MA. During the first 12 hours of admission to medical-surgical and obstetric units, nurses at our institution routinely collect a patient's 1) current level of dyspnea on a 0-10 scale with 10 anchored at "unbearable," 2) worst dyspnea in the past 24 hours before arrival at the hospital on the same 0-10 scale, and 3) activities that were associated with dyspnea before admission. The prevalence of dyspnea was identified, and tests of difference were performed across patient characteristics.

RESULTS

We analyzed 67,362 patients, 12% of whom were obstetric patients. Fifty percent of patients were admitted to a medical-surgical unit after treatment in the emergency department. Among all noncritically ill inpatients, 16% of patients experienced dyspnea in the 24 hours before the admission. Twenty-three percent of patients admitted through the emergency department reported any dyspnea in the past 24 hours. Eleven percent experienced some current dyspnea when interviewed within 12 hours of admission with 4% of patients experiencing dyspnea that was rated 4 or greater. Dyspnea of 4 or more was present in 43% of patients admitted with respiratory diagnoses and 25% of patients with cardiovascular diagnoses. After multivariable adjustment for severity of illness and patient comorbidities, patients admitted on the weekend or during the overnight nursing shift were more likely to report dyspnea on admission.

CONCLUSION

Dyspnea is a common symptom among all hospitalized patients. Routine documentation of dyspnea is feasible in a large tertiary care center.

Treatment of atopic dermatitis with tralokinumab, an anti-IL-13 mAb

BACKGROUND

IL-13 has an important role in atopic dermatitis (AD) pathogenesis. Tralokinumab is a fully human mAb that potently and specifically neutralizes IL-13.

OBJECTIVE

We sought to evaluate the efficacy and safety of tralokinumab in adults with moderate-to-severe AD.

METHODS

In this phase 2b study (NCT02347176), 204 adults were randomized 1:1:1:1 to receive 45, 150, or 300 mg of subcutaneous tralokinumab, or placebo, every 2 weeks for 12 weeks with concomitant topical glucocorticoids. Coprimary end points were change from baseline in Eczema Area Severity Index score and percentage of participants with an Investigator's Global Assessment response (0/1 score and reduction of ≥2 grades from baseline) at week 12.

RESULTS

At week 12, 300 mg of tralokinumab significantly improved change from baseline in Eczema Area Severity Index score versus placebo (adjusted mean difference, -4.94; 95% CI, -8.76 to -1.13; P = .01), and a greater percentage of participants achieved an Investigator's Global Assessment response (26.7% vs 11.8%). Greater responses were found in participants with greater concentrations of biomarkers of increased IL-13 activity. Participants treated with 300 mg of tralokinumab demonstrated improvements in SCORAD, Dermatology Life Quality Index, and pruritus numeric rating scale (7-day mean) scores versus placebo. Upper respiratory tract infection was the most frequent treatment-emergent adverse event reported as related to study drug in the placebo (3.9%) and pooled tralokinumab (3.9%) groups.

CONCLUSIONS

Tralokinumab treatment was associated with early and sustained improvements in AD symptoms and an acceptable safety and tolerability profile, thereby providing evidence for targeting IL-13 in patients with AD.

Implications of Centers for Medicare & Medicaid Services Severe Sepsis and Septic Shock Early Management Bundle and Initial Lactate Measurement on the Management of Sepsis

BACKGROUND

Sepsis remains a significant cause of morbidity and mortality in the United States, leading to the implementation of the Severe Sepsis and Septic Shock Early Management Bundle (SEP-1). SEP-1 identifies patients with "severe sepsis" via clinical and laboratory criteria and mandates interventions, including lactate draws and antibiotics, within a specific time window. We sought to characterize the patients affected and to study the implications of SEP-1 on patient care and outcomes.

METHODS

All adults admitted to the University of Chicago from November 2008 to January 2016 were eligible. Modified SEP-1 criteria were used to identify appropriate patients. Time to lactate draw and antibiotic and IV fluid administration were calculated. In-hospital mortality was examined.

RESULTS

Lactates were measured within the mandated window 32% of the time on the ward (n = 505) compared with 55% (n = 818) in the ICU and 79% (n = 2,144) in the ED. Patients with delayed lactate measurements demonstrated the highest in-hospital mortality at 29%, with increased time to antibiotic administration (median time, 3.9 vs 2.0 h). Patients with initial lactates > 2.0 mmol/L demonstrated an increase in the odds of death with hourly delay in lactate measurement (OR, 1.02; 95% CI, 1.0003-1.05; P = .04).

CONCLUSIONS

Delays in lactate measurement are associated with delayed antibiotics and increased mortality in patients with initial intermediate or elevated lactate levels. Systematic early lactate measurement for all patients with sepsis will lead to a significant increase in lactate draws that may prompt more rapid physician intervention for patients with abnormal initial values.

Scalable and accurate deep learning with electronic health records

Predictive modeling with electronic health record (EHR) data is anticipated to drive personalized medicine and improve healthcare quality. Constructing predictive statistical models typically requires extraction of curated predictor variables from normalized EHR data, a labor-intensive process that discards the vast majority of information in each patient's record. We propose a representation of patients' entire raw EHR records based on the Fast Healthcare Interoperability Resources (FHIR) format. We demonstrate that deep learning methods using this representation are capable of accurately predicting multiple medical events from multiple centers without site-specific data harmonization. We validated our approach using de-identified EHR data from two US academic medical centers with 216,221 adult patients hospitalized for at least 24 h. In the sequential format we propose, this volume of EHR data unrolled into a total of 46,864,534,945 data points, including clinical notes. Deep learning models achieved high accuracy for tasks such as predicting: in-hospital mortality (area under the receiver operator curve [AUROC] across sites 0.93-0.94), 30-day unplanned readmission (AUROC 0.75-0.76), prolonged length of stay (AUROC 0.85-0.86), and all of a patient's final discharge diagnoses (frequency-weighted AUROC 0.90). These models outperformed traditional, clinically-used predictive models in all cases. We believe that this approach can be used to create accurate and scalable predictions for a variety of clinical scenarios. In a case study of a particular prediction, we demonstrate that neural networks can be used to identify relevant information from the patient's chart.

A Phase 2b Dose-Ranging Efficacy and Safety Study of Tralokinumab in Adult Patients with Moderate to Severe Atopic Dermatitis

Abstract not available. Disclosures: Study sponsored by LEO Pharma Copyright 2018 SKIN

Comparison of Hospital Resource Use and Outcomes Among Hospitalists, Primary Care Physicians, and Other Generalists

IMPORTANCE

A physician's prior experience caring for a patient may be associated with patient outcomes and care patterns during and after hospitalization.

OBJECTIVE

To examine differences in the use of health care resources and outcomes among hospitalized patients cared for by hospitalists, their own primary care physicians (PCPs), or other generalists.

DESIGN, SETTING, AND PARTICIPANTS

This retrospective study analyzed admissions for the 20 most common medical diagnoses among elderly fee-for-service Medicare patients from January 1 through December 31, 2013. Patients had at least 1 previous encounter with an outpatient clinician within the 365 days before admission, and diagnoses were restricted to the 20 most common diagnosis related groups. Data were collected from Medicare Parts A and B claims data, and outcomes were analyzed from January 1, 2013, through January 31, 2014.

EXPOSURES

Physician types included hospitalists, PCPs (ie, the physicians who provided a plurality of ambulatory visits in the year preceding admission), or generalists (not the patients' PCPs).

MAIN OUTCOMES AND MEASURES

Number of in-hospital specialist consultations, length of stay, discharge site, all-cause 7- and 30-day readmission rates, and 30-day mortality.

RESULTS

A total of 560 651 admissions were analyzed (41.9% men and 59.1% women; mean [SD] age, 80 [8] years). Patients' physicians were hospitalists in 59.7% of admissions; PCPs, in 14.2%; and other generalists, in 26.1%. Primary care physicians used consultations 3% more (relative risk, 1.03; 95% CI, 1.02-1.05) and other generalists used consultations 6% more (relative risk, 1.06; 95% CI, 1.05-1.07) than hospitalists. Lengths of stay were 12% longer among patients cared for by PCPs (adjusted incidence rate ratio, 1.12; 95% CI, 1.11-1.13) and 6% longer among those cared for by other generalists (adjusted incidence rate ratio, 1.06; 95% CI, 1.05-1.07) compared with patients cared for by hospitalists. However, PCPs were more likely to discharge patients home (adjusted odds ratio [AOR], 1.14; 95% CI, 1.11-1.17), whereas other generalists were less likely to do so (AOR, 0.94; 95% CI, 0.92-0.96). Relative to hospitalists, patients cared for by PCPs had similar readmission rates at 7 days (AOR, 0.98; 95% CI, 0.96-1.01) and 30 days (AOR, 1.02; 95% CI, 0.99-1.04), whereas other generalists' readmission rates were greater than hospitalists' rates at 7 (AOR, 1.05; 95% CI, 1.02-1.07) and 30 (AOR, 1.04; 95% CI, 1.03-1.06) days. Patients cared for by PCPs had lower 30-day mortality than patients of hospitalists (AOR, 0.94; 95% CI, 0.91-0.97), whereas the mortality rate of patients of other generalists was higher (AOR, 1.09; 95% CI, 1.07-1.12).

CONCLUSIONS AND RELEVANCE

A PCP's prior experience with a patient may be associated with inpatient use of resources and patient outcomes. Patients cared for by their own PCP had slightly longer lengths of stay and were more likely to be discharged home but also were less likely to die within 30 days compared with those cared for by hospitalists or other generalists.

No Exit: Identifying Avoidable Terminal Oncology Intensive Care Unit Hospitalizations

PURPOSE

Terminal oncology intensive care unit (ICU) hospitalizations are associated with high costs and inferior quality of care. This study identifies and characterizes potentially avoidable terminal admissions of oncology patients to ICUs.

METHODS

This was a retrospective case series of patients cared for in an academic medical center's ambulatory oncology practice who died in an ICU during July 1, 2012 to June 30, 2013. An oncologist, intensivist, and hospitalist reviewed each patient's electronic health record from 3 months preceding terminal hospitalization until death. The primary outcome was the proportion of terminal ICU hospitalizations identified as potentially avoidable by two or more reviewers. Univariate and multivariate analysis were performed to identify characteristics associated with avoidable terminal ICU hospitalizations.

RESULTS

Seventy-two patients met inclusion criteria. The majority had solid tumor malignancies (71%), poor performance status (51%), and multiple encounters with the health care system. Despite high-intensity health care utilization, only 25% had documented advance directives. During a 4-day median ICU length of stay, 81% were intubated and 39% had cardiopulmonary resuscitation. Forty-seven percent of these hospitalizations were identified as potentially avoidable. Avoidable hospitalizations were associated with factors including: worse performance status before admission (median 2 v 1; P = .01), worse Charlson comorbidity score (median 8.5 v 7.0, P = .04), reason for hospitalization (P = .006), and number of prior hospitalizations (median 2 v 1; P = .05).

CONCLUSION

Given the high frequency of avoidable terminal ICU hospitalizations, health care leaders should develop strategies to prospectively identify patients at high risk and formulate interventions to improve end-of-life care.

Generation and functional characterization of anti-human and anti-mouse IL-36R antagonist monoclonal antibodies

Deficiency of interleukin (IL)-36 receptor antagonist (DITRA) syndrome is a rare autosomal recessive disease caused by mutations in IL36RN. IL-36R is a cell surface receptor and a member of the IL1R family that is involved in inflammatory responses triggered in skin and other epithelial tissues. Accumulating evidence suggests that IL-36R signaling may play a role in the pathogenesis of psoriasis. Therapeutic intervention of IL-36R signaling offers an innovative treatment paradigm for targeting epithelial cell-mediated inflammatory diseases such as the life-threatening psoriasis variant called generalized pustular psoriasis (GPP). We report the discovery and characterization of MAB92, a potent, high affinity anti-human IL-36 receptor antagonistic antibody that blocks human IL-36 ligand (α, β and γ)-mediated signaling. In vitro treatment with MAB92 directly inhibits human IL-36R-mediated signaling and inflammatory cytokine production in primary human keratinocytes and dermal fibroblasts. MAB92 shows exquisite species specificity toward human IL-36R and does not cross react to murine IL-36R. To enable in vivo pharmacology studies, we developed a mouse cross-reactive antibody, MAB04, which exhibits overlapping binding and pharmacological activity as MAB92. Epitope mapping indicates that MAB92 and MAB04 bind primarily to domain-2 of the human and mouse IL-36R proteins, respectively. Treatment with MAB04 abrogates imiquimod and IL-36-mediated skin inflammation in the mouse, further supporting an important role for IL-36R signaling in epithelial cell-mediated inflammation.

Quick Sepsis-related Organ Failure Assessment, Systemic Inflammatory Response Syndrome, and Early Warning Scores for Detecting Clinical Deterioration in Infected Patients outside the Intensive Care Unit

RATIONALE

The 2016 definitions of sepsis included the quick Sepsis-related Organ Failure Assessment (qSOFA) score to identify high-risk patients outside the intensive care unit (ICU).

OBJECTIVES

We sought to compare qSOFA with other commonly used early warning scores.

METHODS

All admitted patients who first met the criteria for suspicion of infection in the emergency department (ED) or hospital wards from November 2008 until January 2016 were included. The qSOFA, Systemic Inflammatory Response Syndrome (SIRS), Modified Early Warning Score (MEWS), and the National Early Warning Score (NEWS) were compared for predicting death and ICU transfer.

MEASUREMENTS AND MAIN RESULTS

Of the 30,677 included patients, 1,649 (5.4%) died and 7,385 (24%) experienced the composite outcome (death or ICU transfer). Sixty percent (n = 18,523) first met the suspicion criteria in the ED. Discrimination for in-hospital mortality was highest for NEWS (area under the curve [AUC], 0.77; 95% confidence interval [CI], 0.76-0.79), followed by MEWS (AUC, 0.73; 95% CI, 0.71-0.74), qSOFA (AUC, 0.69; 95% CI, 0.67-0.70), and SIRS (AUC, 0.65; 95% CI, 0.63-0.66) (P < 0.01 for all pairwise comparisons). Using the highest non-ICU score of patients, ≥2 SIRS had a sensitivity of 91% and specificity of 13% for the composite outcome compared with 54% and 67% for qSOFA ≥2, 59% and 70% for MEWS ≥5, and 67% and 66% for NEWS ≥8, respectively. Most patients met ≥2 SIRS criteria 17 hours before the combined outcome compared with 5 hours for ≥2 and 17 hours for ≥1 qSOFA criteria.

CONCLUSIONS

Commonly used early warning scores are more accurate than the qSOFA score for predicting death and ICU transfer in non-ICU patients. These results suggest that the qSOFA score should not replace general early warning scores when risk-stratifying patients with suspected infection.

How the discovery of ISS-N1 led to the first medical therapy for spinal muscular atrophy

Spinal muscular atrophy (SMA), a prominent genetic disease of infant mortality, is caused by low levels of survival motor neuron (SMN) protein owing to deletions or mutations of the SMN1 gene. SMN2, a nearly identical copy of SMN1 present in humans, cannot compensate for the loss of SMN1 because of predominant skipping of exon 7 during pre-mRNA splicing. With the recent US Food and Drug Administration approval of nusinersen (Spinraza), the potential for correction of SMN2 exon 7 splicing as an SMA therapy has been affirmed. Nusinersen is an antisense oligonucleotide that targets intronic splicing silencer N1 (ISS-N1) discovered in 2004 at the University of Massachusetts Medical School. ISS-N1 has emerged as the model target for testing the therapeutic efficacy of antisense oligonucleotides using different chemistries as well as different mouse models of SMA. Here, we provide a historical account of events that led to the discovery of ISS-N1 and describe the impact of independent validations that raised the profile of ISS-N1 as one of the most potent antisense targets for the treatment of a genetic disease. Recent approval of nusinersen provides a much-needed boost for antisense technology that is just beginning to realize its potential. Beyond treating SMA, the ISS-N1 target offers myriad potentials for perfecting various aspects of the nucleic-acid-based technology for the amelioration of the countless number of pathological conditions.

Detecting Sepsis: Are Two Opinions Better Than One?

The diagnosis of sepsis requires that objective criteria be met with a corresponding subjective suspicion of infection. We conducted a study to characterize the agreement between different providers' suspicion of infection and the correlation with patient outcomes using prospective data from a general medicine ward. Registered nurse (RN) suspicion of infection was collected every 12 hours and compared with medical doctor or advanced practice professional (MD/APP) suspicion, defined as an existing order for antibiotics or a new order for blood or urine cultures within the 12 hours before nursing screen time. During the study period, 1386 patients yielded 11,489 screens, 3744 (32.6%) of which met at least 2 systemic inflammatory response syndrome (SIRS) criteria. Infection was suspected by RN and MD/APP in 5.8% of cases, by RN only in 22.2%, by MD/APP only in 7.2%, and by neither provider in 64.7%. Overall agreement rate was 80.7% for suspicion of infection (κ = 0.11, P < 0.001). Progression to severe sepsis or shock was highest when both providers suspected infection in a SIRS-positive patient (17.7%), was substantially reduced with single-provider suspicion (6.0%), and was lowest when neither provider suspected infection (1.5%) (P < 0.001). Provider disagreement regarding suspected infection is common, with RNs suspecting infection more often, suggesting that a collaborative model for sepsis detection may improve timing and accuracy. Journal of Hospital Medicine 2017;12:256-258.

An Emergency Department Validation of the SEP-3 Sepsis and Septic Shock Definitions and Comparison With 1992 Consensus Definitions

STUDY OBJECTIVE

The Third International Consensus Definitions Task Force (SEP-3) proposed revised criteria defining sepsis and septic shock. We seek to evaluate the performance of the SEP-3 definitions for prediction of inhospital mortality in an emergency department (ED) population and compare the performance of the SEP-3 definitions to that of the previous definitions.

METHODS

This was a secondary analysis of 3 prospectively collected, observational cohorts of infected ED subjects aged 18 years or older. The primary outcome was all-cause inhospital mortality. In accordance with the SEP-3 definitions, we calculated test characteristics of sepsis (quick Sequential Organ Failure Assessment [qSOFA] score ≥2) and septic shock (vasopressor dependence plus lactate level >2.0 mmol/L) for mortality and compared them to the original 1992 consensus definitions.

RESULTS

We identified 7,754 ED patients with suspected infection overall; 117 had no documented mental status evaluation, leaving 7,637 patients included in the analysis. The mortality rate for the overall population was 4.4% (95% confidence interval [CI] 3.9% to 4.9%). The mortality rate for patients with qSOFA score greater than or equal to 2 was 14.2% (95% CI 12.2% to 16.2%), with a sensitivity of 52% (95% CI 46% to 57%) and specificity of 86% (95% CI 85% to 87%) to predict mortality. The original systemic inflammatory response syndrome-based 1992 consensus sepsis definition had a 6.8% (95% CI 6.0% to 7.7%) mortality rate, sensitivity of 83% (95% CI 79% to 87%), and specificity of 50% (95% CI 49% to 51%). The SEP-3 septic shock mortality was 23% (95% CI 16% to 30%), with a sensitivity of 12% (95% CI 11% to 13%) and specificity of 98.4% (95% CI 98.1% to 98.7%). The original 1992 septic shock definition had a 22% (95% CI 17% to 27%) mortality rate, sensitivity of 23% (95% CI 18% to 28%), and specificity of 96.6% (95% CI 96.2% to 97.0%).

CONCLUSION

Both the new SEP-3 and original sepsis definitions stratify ED patients at risk for mortality, albeit with differing performances. In terms of mortality prediction, the SEP-3 definitions had improved specificity, but at the cost of sensitivity. Use of either approach requires a clearly intended target: more sensitivity versus specificity.

Targeting the T Helper 2 Inflammatory Axis in Atopic Dermatitis

Atopic dermatitis (AD) is a chronic inflammatory skin disease that affects up to 25% of children and 10% of adults. The skin of patients with moderate to severe AD is characterized by significant barrier disruption and T helper 2 (Th2)-driven inflammation, which are thought to play a significant role in the pathogenesis of AD. Current management of AD is aimed at suppressing the inflammatory response and restoring the barrier function of the skin, reducing exacerbations, and preventing secondary skin infections. Combinations of treatment strategies are used to alleviate the symptoms of the disease; however, resolution is often temporary, and long-term usage of some of the medications for AD can be associated with significant side effects. Antibody therapies previously approved for other inflammatory diseases have been evaluated in patients with AD. Unfortunately, they have often failed to result in significant clinical improvement. Monoclonal antibodies and novel small molecules currently in development may provide more consistent benefit to patients with AD by specifically targeting the immune and molecular pathways important for the pathogenesis of AD. Here we review the state-of-the-art therapeutics targeting the Th2 axis in AD.