Segmenting computed tomograms for cardiac ablation using machine learning leveraged by domain knowledge encoding

Background

Segmentation of computed tomography (CT) is important for many clinical procedures including personalized cardiac ablation for the management of cardiac arrhythmias. While segmentation can be automated by machine learning (ML), it is limited by the need for large, labeled training data that may be difficult to obtain. We set out to combine ML of cardiac CT with domain knowledge, which reduces the need for large training datasets by encoding cardiac geometry, which we then tested in independent datasets and in a prospective study of atrial fibrillation (AF) ablation.

Methods

We mathematically represented atrial anatomy with simple geometric shapes and derived a model to parse cardiac structures in a small set of N = 6 digital hearts. The model, termed "virtual dissection," was used to train ML to segment cardiac CT in N = 20 patients, then tested in independent datasets and in a prospective study.

Results

In independent test cohorts (N = 160) from 2 Institutions with different CT scanners, atrial structures were accurately segmented with Dice scores of 96.7% in internal (IQR: 95.3%-97.7%) and 93.5% in external (IQR: 91.9%-94.7%) test data, with good agreement with experts (r = 0.99; p < 0.0001). In a prospective study of 42 patients at ablation, this approach reduced segmentation time by 85% (2.3 ± 0.8 vs. 15.0 ± 6.9 min, p < 0.0001), yet provided similar Dice scores to experts (93.9% (IQR: 93.0%-94.6%) vs. 94.4% (IQR: 92.8%-95.7%), p = NS).

Conclusions

Encoding cardiac geometry using mathematical models greatly accelerated training of ML to segment CT, reducing the need for large training sets while retaining accuracy in independent test data. Combining ML with domain knowledge may have broad applications.

Camrelizumab with Chemoradiotherapy for Locally Advanced Biliary Tract Cancer: Preliminary Results from A Phase II Study

PURPOSE/OBJECTIVE(S)

For locally advanced biliary tract cancer (BTC), capecitabine-based chemoradiotherapy (CRT) is commonly used but has limited benefits. Immunotherapy is potentially effective for BTC and may be synergized with CRT. Followed by gemcitabine and cisplatin (GP) consolidation chemotherapy (CT), we evaluated the safety and efficacy of combined camrelizumab and capecitabine-based CRT for locally advanced BTC.

MATERIALS/METHODS

Patients had stage II-III (T4N0M0, T1-4N+M0) BTC (per the 7th [2010] edition of the American Joint Committee on Cancer staging system) were eligible for CRT (capecitabine plus [50-60 Gy] radiotherapy), to be followed by GP CT. Camrelizumab was given concurrently with CRT. Safety was defined as the incidence and severity of adverse events (AEs), while efficacy was defined as overall survival (OS), progression-free survival (PFS), objective response rate (ORR) and disease control rate (DCR).

RESULTS

Ten patients completed the planned treatment. None experienced grade ≥3 treatment-related AEs during CRT. Grade ≥3 immune-related AEs occurred in 2 of 10 patients (20%) only during GP CT. The mean OS time was 18.2 months (95% confidence interval [CI] 12.9m-23.5m) while the median OS time was 14.1 months (95% CI 10.1m-18.1m). OS rates were 100%, 59%, 44% at 6 months, 1 year and 2 years, respectively. The ORR was 30% while the DCR was 90%. Two patients (20%) obtained OS over 2 years with partial response (25.9m, 29.1m). Median PFS time was 14.1 months (95% CI 9.3m-18.9m).

CONCLUSION

Camrelizumab in combination with concurrent CRT was well tolerated and did not impair delivery of CRT in patients with locally advanced BTC.

[A close contact of coronavirus disease 2019 with severe imported malaria: a case report]

This article presents a severe cerebral malaria patient in shock with a close contact of COVID-19 that was successfully cured in a negative pressure ward during the global pandemic of COVID-19. The patient experienced a sudden onset of high fever and coma in a designated isolation hotel after returning from Africa, and was transferred to a designated hospital. Following antimalarial therapy, blood pressure elevation, increase of blood volume, bedside hemodialysis, mechanical ventilation, plasma and platelet transfusions, the case gradual recovered.

Prevalence, drivers and surveillance of antibiotic resistance and antibiotic use in rural China: Interdisciplinary study

This study aimed to characterise antibiotic prescribing and dispensing patterns in rural health facilities in China and determine the community prevalence of antibiotic resistance. We investigated patterns and drivers of antibiotic use for common respiratory and urinary tract infections (RTI/UTI) in community settings, examined relationships between presenting symptoms, clinical diagnosis and microbiological results in rural outpatient clinics, and assessed potential for using patient records to monitor antibiotic use. This interdisciplinary mixed methods study included: (i) Observations and exit interviews in eight village clinics and township health centres and 15 retail pharmacies; (ii) Urine, throat swab and sputum samples from patients to identify potential pathogens and test susceptibility; (iii) 103 semi-structured interviews with doctors, patients, pharmacy workers and antibiotic-purchasing customers; (iv) Assessment of completeness and accuracy of electronic patient records through comparison with observational data. 87.9% of 1123 recruited clinic patients were prescribed antibiotics (of which 35.5% contained antibiotic combinations and >40% were for intravenous administration), most of whom had RTIs. Antibiotic prescribing for RTIs was not associated with presence of bacterial pathogens but was correlated with longer duration of infection (OR = 3.33) and presence of sore throat (OR = 1.64). Fever strongly predicted prescription of intravenous antibiotics (OR = 2.87). Resistance rates in bacterial pathogens isolated were low compared with national data. 25.8% of patients reported antibiotics use prior to their clinic visit, but only 56.2% of clinic patients and 53% of pharmacy customers could confirm their prescription or purchase included antibiotics. Diagnostic uncertainty, financial incentives, understanding of antibiotics as anti-inflammatory and limited doctor-patient communication were identified as key drivers of antibiotic use. Completion and accuracy of electronic patient records were highly variable. Prevalence of antibiotic resistance in this rural population is relatively low despite high levels of antibiotic prescribing and self-medication. More systematic use of e-records and in-service training could improve antibiotic surveillance and stewardship in rural facilities. Combining qualitative and observational anthropological methods and concepts with microbiological and epidemiological investigation of antibiotic resistance at both research design and analytic synthesis stages substantially increases the validity of research findings and their utility in informing future intervention development.

[A single-center study on the distribution and antibiotic resistance of pathogens causing bloodstream infection in patients with hematological malignancies]

Objective: To study the incidence of bloodstream infections, pathogen distribution, and antibiotic resistance profile in patients with hematological malignancies. Methods: From January 2018 to December 2021, we retrospectively analyzed the clinical characteristics, pathogen distribution, and antibiotic resistance profiles of patients with malignant hematological diseases and bloodstream infections in the Department of Hematology, Nanfang Hospital, Southern Medical University. Results: A total of 582 incidences of bloodstream infections occurred in 22,717 inpatients. From 2018 to 2021, the incidence rates of bloodstream infections were 2.79%, 2.99%, 2.79%, and 2.02%, respectively. Five hundred ninety-nine types of bacteria were recovered from blood cultures, with 487 (81.3%) gram-negative bacteria, such as Klebsiella pneumonia, Escherichia coli, and Pseudomonas aeruginosa. Eighty-one (13.5%) were gram-positive bacteria, primarily Staphylococcus aureus, Staphylococcus epidermidis, and Enterococcus faecium, whereas the remaining 31 (5.2%) were fungi. Enterobacteriaceae resistance to carbapenems, piperacillin/tazobactam, cefoperazone sodium/sulbactam, and tigecycline were 11.0%, 15.3%, 15.4%, and 3.3%, with a descending trend year on year. Non-fermenters tolerated piperacillin/tazobactam, cefoperazone sodium/sulbactam, and quinolones at 29.6%, 13.3%, and 21.7%, respectively. However, only two gram-positive bacteria isolates were shown to be resistant to glycopeptide antibiotics. Conclusions: Bloodstream pathogens in hematological malignancies were broadly dispersed, most of which were gram-negative bacteria. Antibiotic resistance rates vary greatly between species. Our research serves as a valuable resource for the selection of empirical antibiotics.

Quantifying a spectrum of clinical response in atrial tachyarrhythmias using spatiotemporal synchronization of electrograms

AIMS

There is a clinical spectrum for atrial tachyarrhythmias wherein most patients with atrial tachycardia (AT) and some with atrial fibrillation (AF) respond to ablation, while others do not. It is undefined if this clinical spectrum has pathophysiological signatures. This study aims to test the hypothesis that the size of spatial regions showing repetitive synchronized electrogram (EGM) shapes over time reveals a spectrum from AT, to AF patients who respond acutely to ablation, to AF patients without acute response.

METHODS AND RESULTS

We studied n = 160 patients (35% women, 65.0 ± 10.4 years) of whom (i) n = 75 had AF terminated by ablation propensity matched to (ii) n = 75 without AF termination and (iii) n = 10 with AT. All patients had mapping by 64-pole baskets to identify areas of repetitive activity (REACT) to correlate unipolar EGMs in shape over time. Synchronized regions (REACT) were largest in AT, smaller in AF termination, and smallest in non-termination cohorts (0.63 ± 0.15, 0.37 ± 0.22, and 0.22 ± 0.18, P < 0.001). Area under the curve for predicting AF termination in hold-out cohorts was 0.72 ± 0.03. Simulations showed that lower REACT represented greater variability in clinical EGM timing and shape. Unsupervised machine learning of REACT and extensive (50) clinical variables yielded four clusters of increasing risk for AF termination (P < 0.01, χ2), which were more predictive than clinical profiles alone (P < 0.001).

CONCLUSION

The area of synchronized EGMs within the atrium reveals a spectrum of clinical response in atrial tachyarrhythmias. These fundamental EGM properties, which do not reflect any predetermined mechanism or mapping technology, predict outcome and offer a platform to compare mapping tools and mechanisms between AF patient groups.

[Current status of diagnosis and treatment of chronic lymphocytic leukemia in China: A national multicenter survey research]

Objective: To understand the current status of diagnosis and treatment of chronic lymphocytic leukemia (CLL) /small lymphocytic lymphoma (SLL) among hematologists, oncologists, and lymphoma physicians from hospitals of different levels in China. Methods: This multicenter questionnaire survey was conducted from March 2021 to July 2021 and included 1,000 eligible physicians. A combination of face-to-face interviews and online questionnaire surveys was used. A standardized questionnaire regarding the composition of patients treated for CLL/SLL, disease diagnosis and prognosis evaluation, concomitant diseases, organ function evaluation, treatment selection, and Bruton tyrosine kinase (BTK) inhibitor was used. Results: ①The interviewed physicians stated that the proportion of male patients treated for CLL/SLL is higher than that of females, and the age is mainly concentrated in 61-70 years old. ②Most of the interviewed physicians conducted tests, such as bone marrow biopsies and immunohistochemistry, for patient diagnosis, in addition to the blood test. ③Only 13.7% of the interviewed physicians fully grasped the initial treatment indications recommended by the existing guidelines. ④In terms of cognition of high-risk prognostic factors, physicians' knowledge of unmutated immunoglobulin heavy-chain variable and 11q- is far inferior to that of TP53 mutation and complex karyotype, which are two high-risk prognostic factors, and only 17.1% of the interviewed physicians fully mastered CLL International Prognostic Index scoring system. ⑤Among the first-line treatment strategy, BTK inhibitors are used for different types of patients, and physicians have formed a certain understanding that BTK inhibitors should be preferentially used in patients with high-risk factors and elderly patients, but the actual use of BTK inhibitors in different types of patients is not high (31.6%-46.0%). ⑥BTK inhibitors at a reduced dose in actual clinical treatment were used by 69.0% of the physicians, and 66.8% of the physicians had interrupted the BTK inhibitor for >12 days in actual clinical treatment. The use of BTK inhibitors is reduced or interrupted mainly because of adverse reactions, such as atrial fibrillation, severe bone marrow suppression, hemorrhage, and pulmonary infection, as well as patients' payment capacity and effective disease progression control. ⑦Some differences were found in the perceptions and behaviors of hematologists and oncologists regarding the prognostic assessment of CLL/SLL, the choice of treatment options, the clinical use of BTK inhibitors, etc. Conclusion: At present, a gap remains between the diagnosis and treatment of CLL/SLL among Chinese physicians compared with the recommendations in the guidelines regarding the diagnostic criteria, treatment indications, prognosis assessment, accompanying disease assessment, treatment strategy selection, and rational BTK inhibitor use, especially the proportion of dose reduction or BTK inhibitor discontinuation due to high adverse events.

[Analysis of the causes of long-standing pelvic anterior sacral space infection and discussion of management techniques]

Objective: To investigate the causes and management of long-term persistent pelvic presacral space infection. Methods: Clinical data of 10 patients with persistent presacral infection admitted to the Cancer Hospital of Zhengzhou University from October 2015 to October 2020 were collected. Different surgical approaches were used to treat the presacral infection according to the patients' initial surgical procedures. Results: Among the 10 patients, there were 2 cases of presacral recurrent infection due to rectal leak after radiotherapy for cervical cancer, 3 cases of presacral recurrent infection due to rectal leak after radiotherapy for rectal cancer Dixons, and 5 cases of presacral recurrent infection of sinus tract after adjuvant radiotherapy for rectal cancer Miles. Of the 5 patients with leaky bowel, 4 had complete resection of the ruptured nonfunctional bowel and complete debridement of the presacral infection using an anterior transverse sacral incision with a large tipped omentum filling the presacral space; 1 had continuous drainage of the anal canal and complete debridement of the presacral infection using an anterior transverse sacral incision. 5 post-Miles patients all had debridement of the presacral infection using an anterior transverse sacral incision combined with an abdominal incision. The nine patients with healed presacral infection recovered from surgery in 26 to 210 days, with a median time of 55 days. Conclusions: Anterior sacral infections in patients with leaky gut are caused by residual bowel secretion of intestinal fluid into the anterior sacral space, and in post-Miles patients by residual anterior sacral foreign bodies. An anterior sacral caudal transverse arc incision combined with an abdominal incision is an effective surgical approach for complete debridement of anterior sacral recalcitrant infections.

Exome-wide screening identifies novel rare risk variants for bone mineral density

Bone mineral density (BMD) is an independent risk factor of osteoporosis-related fractures. We performed gene-based burden tests to assess the association between rare variants and BMD, and identified several BMD candidate genes.

PURPOSE

BMD is highly heritable and a major predictor of osteoporotic fractures, but its genetic basis remains unclear. We aimed to identify rare risk variants contributing to BMD.

METHODS

Utilizing the newly released UK Biobank 200,643 exome dataset, we conducted a gene-based exome-wide association study in males and females, respectively. First, 100,639 males and 117,338 females with BMD values were included in the polygenic risk scores (PRS) analysis. Among individuals with lower 30% PRS, cases were individuals with top 10% BMD, and individuals with bottom 10% BMD were the controls. Considering the effects of vitamin D (VD), individuals with the highest 30% VD concentration were selected for VD-BMD analysis. After quality control, 741 males and 697 females were included in the BMD analysis, and 717 males and 708 females were included in the VD-BMD analysis. The variants were annotated by ANNOVAR software, then BMD and VD-BMD qualified variants were imported into the SKAT R-package to perform gene-based burden tests, respectively.

RESULTS

The gene-based burden test of the exonic variants identified genome-wide candidate associations in ANKRD18A (P = 1.60 × 10^-5, P_{Bonferroni adjust} = 2.11 × 10^-3), C22orf31 (P = 3.49 × 10^-4, P_{Bonferroni adjust} = 3.17 × 10^-2), and SPATC1L (P = 1.09 × 10^-5, P_{Bonferroni adjust} = 8.80 × 10^-3). For VD-BMD analysis, three genes were associated with BMD, such as NIPAL1 (P = 1.06 × 10^-3, P_{Bonferroni adjust} = 3.91 × 10^-2).

CONCLUSIONS

Our study suggested that rare variants contribute to BMD, providing new sights for broadening the genetic structure of BMD.

Reduction of artifacts and noise in small electrogram datasets without manual annotation using transfer machine learning

Background/Introduction

Mapping AF is challenging. Monophasic action potentials (MAPs) show that most of the recorded signals are not representing the atrial activity, and arise from far-field or other artifacts. Thus, reducing noise in electrophysiological signals is essential, yet it can be difficult for cross-talk from other chambers and pacing. Strategies to reduce noise include template matching, averaging, and smoothing, but all of them have major limitations. Furthermore, expert interpretation requires knowledge to discriminate signals from noise, but is subjective.

Purpose

We hypothesised a) that atrial and ventricular electrograms with varying artifact and noise can be denoised using autoencoder neural networks (NNs) without requiring manual annotation and in a reproducible manner, and b) we could train these NNs on a large available dataset ventricular signals, then apply transfer learning to the original smaller atrial dataset. We applied this approach to MAPs, which have interpretable shapes and would help identifying local from far-field signals helping in diagnosis, mapping and ablation.

Methods

We first trained with 5706 left and right ventricular MAPs from 42 patients with ischemic cardiomyopathy (age 65±13y; Fig. 1A), with 60% for training, 20% (validation) and 20% (testing). Transfer learning and parameter-tuning were then used to apply this NN to a smaller sample of atrial MAPs (N=641 from 21 patients, 67±5y, 13 women; Fig. 2B, D, F). The autoencoder was used to eliminate pacing artifacts in ventricular MAPs (Fig. 1B, C) and denoise atrial MAPs (Fig. 2C, E, G) by reconstructing key learned features. The accuracy of the reconstruction was evaluated using Pearson Correlation Coefficient (PCC) and a novel similarity coefficient (SC). No manual annotation was required to identify noisy signals.

Results

The trained NN encoder learned key features of ventricular MAPs and reconstructed these clean signals with a SC=0.91±0.16 and PCC=0.99±0.01 (Fig. 1A). With this training, the NN was able to denoise ventricular MAPs with pacing artifact (Fig. 1B, C). After fine-tuning, the NN learned key signal features (upstroke, triangular descent, terminus) and thus reduced diverse noise without specific training or manual annotation. Namely, it was able to reconstruct atrial MAPs eliminating ventricular noise, high frequency noise and truncated signals (Fig. 2).

Conclusions

Machine learned encoder-decoders are powerful tools that can learn essential features of atrial and ventricular signals and hence isolate noise. Transfer learning is effective when large datasets are unavailable for training. This approach can separate atrial beats from far-field ventricular beats and other sources of noise. The ability to eliminate a diverse range of noise improves this approach over existing techniques and may have far-reaching applications in electrophysiology, such as mapping and ablation.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH

Novel electrogram featurization reveals a spectrum of response to ablation from atrial tachycardia to types of atrial fibrillation

Background

Although atrial tachycardia (AT) may interconvert with fibrillation (AF) in many patients, it is undefined if this represents a pathophysiological spectrum of organization, or whether it indicates that AF will respond better to ablation.

Objective

To test the hypothesis that the spatial area within which electrograms (EGMs) repeat in synchronized fashion over time indicates a spectrum from AT, in which areas span the entire atria, to AF, in which areas are limited. We further hypothesized that repetitive areas would be larger in AF patients with acute termination than in those with poor response to ablation.

Methods

We studied N=234 patients (47% women, 64±10Y), of whom (i) N=10 had AT, (ii) N=120 had AF that terminated with ablation (“Term”), (ii) N=104 had AF that did not terminate (“Non-term”). All patients had global left atrial mapping by 64 pole baskets (Abbott, IL). Spatial areas of repetitive activity (REACT) were calculated by correlating unipolar EGMs in 2x2 grids for 4 sec, repeated for the entire atria (Figure 1A, B). We quantified global organization by averaging the REACT map for each patient.

Results

Figure 1C shows progressively decreasing areas of repetitive EGM from AT to AF Term to AF Non-term (p&lt;0.001, ANOVA). Figure 1D shows a case of AT in a 71 YO male and global REACT &gt;0.90, a case of AF REACT 0.45 in a 65 YO male with termination by ablation, and a case of AF with REACT 0.19 in an 85 YO male that did not terminate. Further, ROC analysis of REACT analysis in AF cases predicted termination with an AUC of 0.71.

Conclusion

Spatial areas of repeating electrogram shapes indicates a spectrum from AT to AF with good and AF with poor acute response to ablation. Future studies should investigate whether REACT areas can be identified non-invasively, such as by body surface ECG, to guide ablation or prognosis.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): US National Institutes of Health

Spatiotemporal signatures of response to atrial fibrillation ablation

Background

Atrial fibrillation (AF) can have organized regions, in the form of consistent dominant frequency sites, focal or reentrant sites, but it is unclear how these overlap with or differ from focal atrial tachycardias (AT) or potential drivers. We set out to develop an intuitive method based on fundamental electrogram shape and timing to separate types of AF.

Objective

To test the hypothesis that spatial regions of electrogram (EGM) in AF that show similar shapes over time based on cross-correlation analysis may separate patients with differing response to ablation.

Methods

We recruited N=133 patients (63.8±12.1 Y, 32% women), (i) N=10 had AT, (ii) N=122 AF that was or was not terminated by ablation, and (iii) N=1 pacing. All patients had left atrial mapping by 64 pole baskets. We applied repetitive activity (REACT) mapping that correlates EGMs in contiguous 2x2 regions (Fig. 1A) over 4sec. To calibrate REACT, we introduced simulated variations in shape (gaussian noise) and timing (gaussian delay) to pacing EGMs and computed nomograph over 100 random trials (Fig. 1C).

Results

Fig. 1B shows that REACT in a 71-year-old man with AT is more organized than in a 65 YO man with AF (100% vs 40% mapped field). Overall, REACT was higher in AT than AF (0.63±0.15 vs 0.36±0.22, p&lt;0.001). There were 24 cases in which global REACT between AF and AT groups had the overlapping range of values, indicating organized “islands” in AF analogous to AT. From nomograph in Fig. 1C we identified that this overlap reflects 15 ms variation in cycle length and 20% variation in EGM shape (labelled “x” in Fig. 1C).

Conclusion

Basic electrogram properties in AF of similar shapes in spatial areas over time can separate response to ablation and may represent “islands” of AT. Future studies should investigate the mechanisms for such islands and whether they may be targeted for therapy.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): US National Institutes of Health

Automatic left atrial segmentation from cardiac CT using computer graphics imaging and deep learning

Introduction

Segmenting left atrial (LA) substructures, including the LA body, appendage (LAA), and pulmonary veins (PVs), from computed tomography (CT) is central to electroanatomic mapping for ablation and functional studies in patients with atrial fibrillation (AF). However, this process requires manual outlining which needs special training, is subjective, and is difficult to scale. Computer graphics imaging (CGI) has been applied in media, film, and computer-aided design to reliably segment complex structures using their basic geometric representations.

Purpose

We hypothesized that LA substructures can be “virtually” dissected using CGI to separate geometric contours of the “convex ellipsoid” LA, “tubular” PVs, and “conical” LAA. We further hypothesized that the results of virtual dissection can be used to train a deep learning (DL) model to segment raw CT scans.

Methods

First, a mathematical method based on CGI techniques – erosion and dilation – was developed to “virtually dissect” the convex LA body from the original concave shell in publicly available digital atria with diverse simulated morphologies (Fig. 1A). The PVs and LAA were then automatically revealed and labeled by a 3D subtraction approach. Second, we refined precise LA/PV/LAA boundaries by tuning hyper-parameters from N=5 patient shells (Fig. 1B). Third, we used virtual dissection to train a DL model to segment CTs in N=20 patient atria (Fig. 1C). Finally, we applied this pipeline to segment raw CTs in a validation cohort of N=105 patients (23.8% women, 63.8±10.3Y; Fig. 1D).

Results

Virtual dissection accurately identified LA/PV/LAA boundaries in the training set (Dice coefficients 89–98%). In the independent test cohort (N=105), this automated pipeline accurately segmented raw CTs with Dice 81–95% (Fig. 1D) compared to a panel of experts (p&lt;0.001).

Conclusion

CGI of basic cardiac geometry combined with deep learning in small datasets can accurately segment raw CT scans in large populations. This computational pipeline may automate and simplify cardiac image processing and ablation procedures, and could be applied to the ventricle or other organ systems for diverse therapeutic strategies or to train machine learning.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Institutes of Health

Artificial intelligence to reduce artifact in cardiac electrophysiological signals

Background/Introduction

Signals in Electrophysiology cases are often noisy despite laboratory shielding and filtering, and current noise-reduction methods are suboptimal. Template matching can identify a “nearest type” of electrogram, but libraries of signal shapes may be unavailable. Beat averaging can reduce noise but obscures beat-to-beat variations and is not optimal to analyze dynamically changing signals, such as when moving a catheter in the heart. Smoothing reduces noise yet blurs high frequency components.

Purpose

We set out to test if machine learned autoencoders could reduce noise in single beats without requiring massive training data or beat libraries. Specifically, we hypothesised that noisy electrograms in small datasets of atrial signals could be de-noised using an encoder-decoder neural network (NN) using transfer learning of machines trained to recognize key features in larger datasets of related signals.

Methods

We applied NN to monophasic action potentials (MAPs), because they have visually verifiable shapes. The NN was first trained to reconstruct 5706 left and right ventricular MAPs in 42 patients (67±13y; Fig. 1A). Transfer learning was then used to apply the NN to a much smaller dataset of 641 atrial MAPs in 21 patients (67±5y, 13 women; Fig. 1B, D, F).

Results

NN reconstructed atrial MAPs with a Pearson correlation of 0.87±0.11. After fine-tuning, NN reconstruction accuracy improved dramatically (Pearson 0.99±0.01; p&lt;0.001). In Fig. 1B–G the NN learned key MAP features (upstroke, triangular descent, terminus) and thus could eliminate ventricular artifact and electrical circuit noise without specific training or manual annotation.

Conclusion

Machine learned autoencoders are a novel and powerful approach to de-noise electrophysiological signals in a dynamic, beat-to-beat fashion. The ability to learn fundamental signal features from models trained in large datasets, and apply them via transfer learning to small datasets in different heart chambers may have wide ranging applications for automated signal annotation, mapping and ablation.

Funding Acknowledgement

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH

AB1485 PATIENT-REPORTED OUTCOMES AND BIOMARKERS ASSOCIATED WITH THE CUTANEOUS DERMATOMYOSITIS AREA AND SEVERITY ACTIVITY (CDASI-A) SCORE IN A PHASE 2 CLINICAL TRIAL IN DERMATOMYOSITIS

Background

Retrospective reviews of clinical databases from two sites have identified strong relationships between patient-reported outcomes and skin activity in dermatomyositis (DM), as measured by CDASI-A.1,2 No studies validate these associations in a controlled setting. Additionally, the relationship between the PROMIS-29 Short Form and skin activity in DM has not been assessed. Previous investigations have demonstrated a correlation between IL-31 and itch in DM.3 IFN-β and IFN-γ are known type I and II interferons, which are critical drivers of DM pathogenesis.4

Objectives

To assess correlations between CDASI-A, quality of life (QoL), and biomarkers of disease activity in a double-blind, randomized, placebo-controlled clinical trial.

Methods

Data were retrospectively collected from five visits of a Phase 2 trial evaluating Lenabasum, a cannabinoid receptor type 2 agonist. Quality of life assessments extracted from the trial included Patient Global Assessment (PtGA) scores, PROMIS domains, and Skindex domains. Skindex question 10, regarding itch, was included in the analysis as a separate domain. Physician Global Assessment scores were also evaluated. Additionally, biomarkers derived from skin samples via IHC/PCR collected at visits 1 and 6 were assessed for predictors of CDASI-A response and association with disease activity. Analysis used linear mixed effect models to account for within subject-variability and repeated measures, where applicable. Analysis was performed without regard to treatment arm, as our goal was to correlate CDASI, QoL, and biomarkers among all subjects.

Results

Data from 22 subjects with DM and a combined total of 110 visits were included. Biopsies were collected from 12 subjects. Improvement in CDASI-A significantly correlated with Skindex-S, Skindex-E, Skindex-F, Skindex-Itch, PtGA global skin, PtGA global skin, PtGA global skin, and PtGA global skin, with p < 0.001. Improvement in PROMIS social role (p = 0.046) correlated with improvement in CDASI-A. Worsening of PROMIS fatigue (p = 0.019) and pain (p < 0.001) correlated with improvement in CDASI-A. Decreases in PGA overall disease, PGA skin activity, and PGA global skin all correlated with improvement of CDASI-A (p < 0.001). Change in IL-31 protein area positively correlated with change in disease activity (p = 0.047). A positive relationship between changes in IFN-β and IFN-γ protein area and disease activity trended towards significance.

Conclusion

In accordance with previous investigations from our group, well-established measures of QoL correlated significantly with CDASI-A. These findings support that CDASI-A reflects both clinical and patient-reported aspects of skin disease and is an appropriate outcome in DM clinical trials. Additionally, Skindex and PtGA scores may better relate to skin activity as measured by the CDASI compared to PROMIS domains. IL-31, a cytokine previously associated with itch in DM,3 correlated significantly with CDASI-A in our study. Trends for IFN-β and IFN-γ reduction with disease improvement support their role in the pathogenesis of DM. This study helps define patient-reported outcomes and biomarkers that may be informative in DM trials.

References

[1]Goreshi R, et al. J Am Acad Dermatol. 2011;65(6):1107-1116

[2]Robinson ES, et al. Br J Dermatol. 2015;172(1):169-174.

[3]Patel J, et al. J Invest Dermatol. 2021;141(9):2151-2160.

[4]Wong D, et al. PLoS One. 2012;7(1):e29161

Disclosure of Interests

Joshua Dan: None declared, Jay Patel: None declared, Grant Sprow: None declared, Josef Concha: None declared, Rui Feng: None declared, Nilesh Kodali: None declared, Thomas Vazquez: None declared, DeAnna Diaz: None declared, Barbara White Shareholder of: Corbus Pharmaceuticals, Victoria Werth Speakers bureau: University of Pennsylvania, which owns the copyright for the CDASI, Grant/research support from: Corbus Pharmaceuticals

Sleep apnea is associated with stroke in young patients with or without atrial fibrillation:A population study of &gt;2 million individuals

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH, R01 HL149134, R01HL83359

Background

Both Sleep Apnea (SA) and Atrial Fibrillation/flutter (AF) are known risk factors for stroke, and both are increasing in prevalence. They are both under-diagnosed in young adults &lt;60 Y. There is an urgent need to define stroke risk portended by SA and AF yet there a paucity of data in adults aged 20-60 years.

Purpose

To define the relationship between stroke, SA, and AF in a very large cohort of 2 million young-middle aged adults aged 20-60 Y in Northern California.

Methods

We probed the Stanford Research Repository of electronic health data from 01/01/2008 to 11/30/2021 for the diagnoses of stroke, transient ischemic attacks, AF and SA using relevant codes (stroke: 433.X, 434.X, 436.X, I63.X, I65.X, I66.X, G45.X, G46.X; AF: I48.X; SA: G47.X, 327.27).

Results

We identified 2267485 patients aged 20-60Y (55% F; 32% White, 12% Asian, 3% Black), of whom SA was diagnosed in 52730 (2.3%), AF in 10230 (0.4%) and incident stroke in 10385 (0.4%) (Figure 1A)

In patients with SA, 1.5% developed incident stroke. Stroke was more common in patients with SA than those without, regardless of co-existing diagnosis of AF; OR with AF: 1.5 [1.3-1.7, p&lt;0.001] and OR without AF: 3.0 [2.8-3.3 p&lt;0.0001]. Risk of stroke with SA than without was noted to be higher in the younger age subgroups (Figure 1B) regardless of AF.

Although AF was more common in patients with SA than without (odds ratio, OR: 10.1 [9.6-10.6, p&lt;0.0001]), the majority of SA patients (63% with CHADS2VASC ≥2) with stroke did not have a diagnosis of AF (75%), of whom 96% were not anticoagulated (Fig 1, left panel). Of the remaining patients with SA and incident stroke, who did have AF (25%), only 26% were taking OACs at the time of stroke despite median CHADS2 VASC score=3 (Fig 1A, left panel).

Finally, 7% of AF patients developed incident stroke. Of these, 73% had CHADS2VASC ≥2, yet 44% were not anticoagulated. Patients with SA comprised a third of all AF patients with stroke and, compared to AF patients with stroke and without SA, had higher CHADS2VASC (median 3 vs 2, p&lt;0.001) and a similarly low use of anticoagulation (56% vs 54% on OAC) (Fig 1A, right panel).

Conclusions

In &gt;2 million young individuals, we uncover a novel association between SA and incident stroke, regardless of the diagnosis of AF. Surprisingly, three quarters of patients with SA developed incident stroke in the absence of AF, and were not anticoagulated. These results underscore the need to screen for AF and sleep apnea in young adults.

Noise reduction in electrophysiological signals using transfer machine learning

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH

Background/Introduction

Reducing electrophysiological signal noise is essential for diagnosis, mapping and ablation, yet most approaches are suboptimal. Template matching requires libraries of known signal types, that are difficult to obtain. Beat averaging can reduce noise, yet cannot be applied to single beats and obscures beat-to-beat variations. Beat smoothing can lose critical and subtle signal features. We set out to use neural networks (NN) based on encoder-decoders, which are able to extract key signal features and hence reconstruct them without noise and artifact.

Purpose

We hypothesised that electrograms with varying sources of artifact can be denoised using autoencoder neural networks. We further hypothesised that this could be achieved in a small data set by developing the method in a larger dataset of related signals, then using transfer learning. We tested this approach for atrial monophasic action potentials (MAPs) that have verifiable shapes.

Methods

The NN was first trained with 5706 left and right ventricular MAPs from 42 patients with ischemic cardiomyopathy (age 65±13y; fig 1.A): 60% for training, 20% (validation) and 20% (testing). Transfer learning and parameter-tuning were then used to apply this NN to a smaller sample of atrial MAPs (N=641, 21 patients, 67±5y, 13 women; fig D,F,H).

Results

The autoencoder was able to learn key features of MAPs, and hence reconstruct them without artifacts. NN learned ventricular MAPs with similarity coefficient 0.91±0.16, Pearson correlation 0.99± 0.01 (fig A) and learned key features (upstroke, triangular descent, terminus) to reduce noise (fig B-C). Applying this trained NN to atrial MAPs, the approach automatically eliminated ventricular artifact (fig E), high frequency noise (fig G), truncation (fig I), saturation and other artifacts. After fine-tuning, the NN reconstructed atrial MAPs with Pearson correlation = 0.99±0.01 (p&lt;0.001).

Conclusions

Machine learned encoder-decoders are powerful tools that can automatically eliminate diverse types of noise in single beats by learning essential signal features. Transfer learning makes this possible without large datasets for training, even from signals in a different cardiac chamber. This approach may have far-reaching applications for mapping and ablation.

Defining refractoriness in single atrial beats using autoencoder neural networks

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): NIH

Background

Mapping atrial fibrillation (AF) is complicated by signals which may be local or far-field, but which cannot currently be separated. This could be clarified by a knowledge of atrial refractory periods, yet these are difficult to define from monophasic action potentials (MAP) in patients. We hypothesized that transfer learning using an autoencoder neural network (ANN), first trained with less-noisy ventricular signals, can be applied to de-noise and classify atrial MAPs.

Methods

We first developed an ANN to encode MAPs in 5706 ventricular MAPs from N=42 patients (age 65±13y) during pacing (fig1. A-B). This created a latent feature space. We now tuned the ANN to classify atrial MAPs in a different cohort of patients with AF. We used a statistical loss function based on mathematical optimization to evaluate the accuracy of final representations of the MAP and classify the different signals.

Results

The autoencoder ANN reconstructed ventricular MAPs with an average similarity of 0.85 (range 0-1) (an example is shown in fig 1.B). We tested on 3000 atrial MAPs in AF patients (N=21; 67±5y, 13 women). Atrial MAPs were accurately represented (fig 1.E-F) with similarity indices that were higher than those obtained by a panel of 3 experts. Fig. 1 shows the reconstruction of different signals: ventricular MAP (fig 1.A-B), ventricular MAP with pacing artifact (fig. 1.C-D), atrial MAP (transfer learning is assumed in here; fig 1.E-F) and noise or signals with morphologies of no interest (fig 1.G-H). Fig. 2 shows the classification of signals according to the similarity metric that allows distinguishing among the different types of signals without manual annotation (p&lt;0.05 between groups).

Conclusion

Atrial refractory periods can be defined in single beats in AF patients using autoencoder neural networks and transfer learning. This approach can separate atrial beats from far-field ventricular beats and other sources of noise. Future work can study if this approach can be used to improve AF mapping or define novel physiological phenotypes.

Machine-learned physiological signatures from the ECG predict sudden death in ischemic cardiomyopathy

Funding Acknowledgements

Type of funding sources: Public grant(s) – National budget only. Main funding source(s): National Institute of Health (NIH)

Background

Low left ventricular ejection fraction (LVEF) is an imperfect predictor of sudden cardiac death (SCD) in patients with ischemic cardiomyopathy. Novel features from the ECG might provide a readily available tool to better predict risk.

Purpose

We hypothesized that machine learning (ML) of the ECG can be used to predict SCD, and the ML-learned ECG features could be referenced to interpretable intracardiac signals (monophasic action potentials: MAP) to provide mechanistic insights.

Methods

We studied 5603 ECG Lead V1 beats in 41 patients (64±10 Y) with coronary disease and LVEF≤40% in steady-state pacing. Patients were randomly allocated to independent training and test cohorts in a 70:30 ratio, repeated K=10-fold. Support vector machines were trained to predict mortality at 3Y from the top 20 features derived from these beats. Patient-level predictions were made by computing an ECG score that indicates the proportion of test set beats in that patient computed by the beat-level model to predict death. Explainability analysis was performed using the arithmetic mean of MAP and ECG beats that predicted SCD versus those that predicted survival.

Results

Fig 1A. shows ECG lead V1 and MAP in a 79 Y man with LVEF 29%. Fig 1B shows the dataflow in the study. Predictive accuracies of ML models were 78 and 70% and optimal with 20 features for both ECG and MAP models respectively (Fig. 1C). Beat-level predictions in the validation (n=1678 Lead I beats) cohorts yielded c-statistics of 0.78 with the ECG (95% CI, 0.62–0.91) and 0.75 with MAPs (95% CI, 0.75-0.76) (data not shown). In multivariable patient-level models, c-statistic was 0.87 with ECGs (95% CI, 0.76-0.98) (Fig 1D) and 0.82 with MAPs. On explainability analysis, ECG beats that predicted SCD (Fig 2; red) had lower amplitude and more notched T-waves in lead V1 than beats that predicted no SCD (Fig 2; blue). MAP that predicted SCD had higher repolarization current at the same time points. Both QT duration (ECG) and action potential duration (MAP) did not differ (Fig 2).

Conclusions

Machine learning of the ECG reveals novel predictors of SCD risk in patients with ischemic cardiomyopathy analogous to those identified in intracardiac signals. This approach can be used as a point-of-care ECG risk tool to improve risk stratification and allocation for ICD therapy beyond LVEF alone and may shed insights into the pathophysiology of ventricular arrhythmias.

A Globally Stable LPNN Model for Sparse Approximation

The objective of compressive sampling is to determine a sparse vector from an observation vector. This brief describes an analog neural method to achieve the objective. Unlike previous analog neural models which either resort to the ℓ₁-norm approximation or are with local convergence only, the proposed method avoids any approximation of the ℓ₁-norm term and is probably capable of leading to the optimum solution. Moreover, its computational complexity is lower than that of the other three comparison analog models. Simulation results show that the error performance of the proposed model is comparable to several state-of-the-art digital algorithms and analog models and that its convergence is faster than that of the comparison analog neural models.

[The prognostic effects of two comprehensive geriatric assessment methods in elderly patients with acute myeloid leukemia]

Objective: To evaluate the prognostic effects of two comprehensive geriatric assessment (CGA) methods in elderly patients with acute myeloid leukemia (AML). Methods: Ninety-seven patients with newly diagnosed AML at Beijing Hospital from August 2008 to December 2019 were included (≥60 years old). All patients were evaluated by two methods of CGA. One was IACA index proposed by Beijing Hospital, including instrumental activities of daily living (IADL), age, Charlson comorbidity index (CCI), albumin; the other was proposed by Italian FIL study group (FIL-CGA), including activities of daily living (ADL), IADL, age, and modified cumulative illness rating score for geriatrics (MCIRS-G). Results: Among 97 patients, 54 patients received standard chemotherapy, 16 with decitabine, 2 with targeted therapy and 25 with the best supportive therapy. The overall response rate (ORR) in 72 treated patients were 67.7%, 33.3% and 0 respectively in fit, unfit and frail groups according to IACA index (P=0.001). Based on FIL-CGA, the ORRs of fit, unfit and frail groups were 52.5%, 41.7% and 35.0% respectively (P=0.418). The 1-year OS rates of fit, unfit and frail groups regarding IACA method were 78.7%, 27.7% and 0 respectively (P<0.01). The 1-year OS rates of fit, unfit and frail groups regarding FIL-CGA method were 67.8%, 28.2% and 13.9% respectively (P<0.01), while no significant difference was seen between unfit group and frail group (P=0.111). The early death rates of fit, unfit and frail groups by IACA were 0, 6.0% and 28.6% respectively (P=0.006), while those by FIL-CGA were 2.3%, 5.9%, 13.9% respectively (P=0.123). Conclusion: Compared with FIL-CGA method, IACA predicts more effectively the treatment response, survival and early mortality in elderly patients with AML.

[Reoperation and perioperative management of residual cyst wall with perineal intractable sinus after resection of presacral cyst tumors]

Objective: To investigate the reoperation and perioperative management of residual cyst wall with perineal intractable sinus after resection of presacral cyst tumors. Methods: The clinical data of 29 patients with residual cyst wall and perineal intractable sinus after resection of presacral cyst tumors in Affiliated Cancer Hospital of Zhengzhou University from January 2014 to August 2019 were reviewed, including the characteristics of the residual cyst wall with perineal intractable sinus after resection of presacral cyst tumors, surgical method, and perioperative management. Results: Twenty-nine patients with residual cyst wall and perineal intractable sinus after resection of presacral cyst tumors, including 9 cases of epidermoid cysts, 7 cases of dermoid cysts, 10 cases of mature teratomas and 3 cases of malignant cysts (including malignant transformation of caudate cyst and teratoma); The 29 patients underwent posterior approaches for cyst resection in other hospital before, of whom 1 patient underwent posterior combined with transabdominal approach. All of thes patients underwent resection of residual presacral cyst wall and perineal intractable sinus in our hospital, of whom 25 patients underwent a transperineal approach through an arc-shaped incision anterior to the apex of the coccyx, and the other 4 patients underwent transperineal arc-shaped incision combined with transabdominal approach. All of the patients were cured without serious complications occurring, postoperative pathological and the magnetic resonance imaging diagnosis showed that the residual cyst wall and perineal intractable sinus were all completely removed. Conclusion: Appropriate surgical approache and perioperative treatment for the patients with residual cyst wall and perineal intractable sinus are very important to promote the resection of residual cyst wall and the healing of perineal intractable sinus.

A Systematic Benchmarking Analysis of Transfer Learning for Medical Image Analysis

Transfer learning from supervised ImageNet models has been frequently used in medical image analysis. Yet, no large-scale evaluation has been conducted to benchmark the efficacy of newly-developed pre-training techniques for medical image analysis, leaving several important questions unanswered. As the first step in this direction, we conduct a systematic study on the transferability of models pre-trained on iNat2021, the most recent large-scale fine-grained dataset, and 14 top self-supervised ImageNet models on 7 diverse medical tasks in comparison with the supervised ImageNet model. Furthermore, we present a practical approach to bridge the domain gap between natural and medical images by continually (pre-)training supervised ImageNet models on medical images. Our comprehensive evaluation yields new insights: (1) pre-trained models on fine-grained data yield distinctive local representations that are more suitable for medical segmentation tasks, (2) self-supervised ImageNet models learn holistic features more effectively than supervised ImageNet models, and (3) continual pre-training can bridge the domain gap between natural and medical images. We hope that this large-scale open evaluation of transfer learning can direct the future research of deep learning for medical imaging. As open science, all codes and pre-trained models are available on our GitHub page https://github.com/JLiangLab/BenchmarkTransferLearning.

[Autologous stem cell transplantation improves outcomes of patients with multiple myeloma receiving proteasome inhibitors and lenalidomide treatment]

OBJECTIVE

To evaluate the effect of autologous stem cell transplantation (ASCT) on treatment response and survival outcomes in patients with newly diagnosed multiple myeloma (MM) receiving treatments with proteasome inhibitors and lenalidomide.

METHODS

We retrospectively collected the clinical data of newly diagnosed MM patients, who were eligible for ASCT and received proteasome inhibitors or lenalidomide-based treatment in our hospital from January, 2015 to December, 2019. The patients were divided into transplantation group and non-transplantation group, and in transplantation group, the patients received 4 to 6 courses of induction therapy with proteasome inhibitors or lenalidomide before ASCT, while those in the non-transplantation group received more than 8 courses of induction and consolidation therapy with proteasome inhibitors or lenalidomide-based regimens. The therapeutic efficacy and survival outcomes of the patinets were compared between the two groups.

RESULTS

A total of 105 patients were enrolled in the study, including 48 (45.7%) in transplantation group and 57 (54.3%) in non-transplantation group. The two groups were matched for gender, age and treatment response after 4 courses of induction therapy (P > 0.05). The rate of optimal response before relapse differed significantly between the two groups (P=0.000), and the patients receiving ASCT had significantly higher rates of complete response (85.4% vs 54.4%, P= 0.001) and very good partial response or better (95.8% vs 73.7%, P=0.002) than those without ASCT. At the end of follow-up, the median progression-free survival in the transplantation group was not reached, as compared with 29 months in the nontransplantation group (P=0.013). The median overall survival (OS) in the two groups was not reached, but the OS was better in the transplant group than in the non-transplant group (P=0.022).

CONCLUSION

ASCT can further improve the depth of remission and survival outcomes in patients with newly diagnosed MM receiving treatments with proteasome inhibitors and lenalidomide.

POS0315 LONG-TERM SAFETY AND EFFICACY OF LENABASUM DURING 3 YEARS IN AN OPEN-LABEL EXTENSION (OLE) OF A PHASE 2 STUDY OF LENABASUM IN REFRACTORY SKIN DISEASE IN DERMATOMYOSITIS (DM)

Background:

Lenabasum is a synthetic, non-immunosuppressive, selective cannabinoid receptor type 2 agonist that activates resolution of inflammation. Lenabasum had acceptable safety and tolerability and improved efficacy outcomes in the initial 16-week double-blinded, randomized, placebo-controlled Part A of Phase 2 trial JBT101-DM-001 (NCT02466243) in DM subjects with refractory skin involvement. In that study, lenabasum or placebo was added to stable background treatment, with immunosuppressive therapies allowed.

Objectives:

To assess long-term safety and efficacy in DM subjects in this study.

Methods:

Subjects who completed Part A of the Phase 2 study (n = 22) were eligible to receive oral lenabasum 20 mg BID in an open-label extension (OLE) that assessed safety and efficacy at 4 weeks, then every 8 weeks.

Results:

20/22 (91%) eligible subjects enrolled in the OLE, following a mean interval of 31 weeks from the end of Part A, during which they continued to receive standard-of care treatments, to the start of the OLE during which lenabasum 20 mg BID was added. 17/20 (85%) subjects were on stable baseline immunosuppressive drugs. At the time of this data cut-off, 17 subjects were still enrolled, 17 had completed 140 months (2.7 years), and 15 had completed 156 months (3 years) of OLE dosing.

All OLE subjects experienced at least 1 adverse event (AE), with 118 AEs during the OLE through Dec 2020. Most AEs were mild (n = 111, 94%), with 2 severe AEs (fatigue and metastatic prostate cancer) considered unrelated to lenabasum. AEs occurring in ≥ 3/20 OLE subjects were: URI (n = 5); fatigue (n = 4); nausea (n = 3); common cold (n = 3); UTI (n = 3); and DM flare (n = 3). No serious AEs related to lenabasum have been reported in this OLE to date. No subject discontinued the OLE because of an AE related to lenabasum.

Improvement was seen in multiple physician- and patient-reported efficacy outcomes. CDASI activity score improved through the first 15 months of lenabasum treatment in the OLE and remained stable thereafter, with an improvement of ~20 points from the beginning of the study maintained from Month 15 through Year 3 in the OLE. CDASI damage score increased through the first year of the OLE, even though skin activity was decreasing, but lessened thereafter, returning after 3 years to about the same level it was at the beginning of the OLE. Other outcomes shown in Figure 1 followed the same general pattern as CDASI activity score, with improvement through the first 12-16 months of the OLE, then stability thereafter. Of note, 2 subjects had disease flares shortly after stopping lenabasum for conclusion of the OLE.

Conclusion:

Lenabasum continues to have a favorable safety and tolerability profile in the OLE of the Phase 2 trial JBT101-DM-001 with no serious AEs or study discontinuations related to lenabasum. The CDASI activity score and multiple other physician and patient-reported outcomes improved and have remained stable, showing durability of improvement in these patients with refractory skin disease. Skin damage was reversible and began to improve once skin activity stabilized. The limitations of attributing this improvement to lenabasum in the setting of open-label dosing is acknowledged. These data support further testing of lenabasum for the treatment of DM, and a Phase 3 study of lenabasum in DM is ongoing.

Figure 1.

Change from Baseline in Selected Efficacy Outcomes in OLE of Phase 2 Trial JBT101-DM-001

Disclosure of Interests:

Victoria Werth Grant/research support from: Investigator for Corbus Pharmaceuticals and received funding to conduct trials, Josef Concha: None declared, Julie Burroughs: None declared, Joyce Okawa: None declared, Rui Feng: None declared, Anisha Jobanputra: None declared, Robert Borucki: None declared, Kathleen Hally Employee of: Employee of Corbus Pharmaceuticals, Emily Hejazi: None declared, Michael Tillinger Employee of: Employee of Corbus Pharmaceuticals, Scott Constantine Employee of: Employee of Corbus Pharmaceuticals, Nancy Dgetluck Employee of: Employee of Corbus Pharmaceuticals, Barbara White Employee of: Employee and stockholder of Corbus Pharmaceuticals