Artificial Intelligence to Differentiate Pediatric Pseudopapilledema and True Papilledema on Fundus Photographs

Purpose

To develop and test an artificial intelligence (AI) model to aid in differentiating pediatric pseudopapilledema from true papilledema on fundus photographs.

Design

Multicenter retrospective study.

Subjects

A total of 851 fundus photographs from 235 children (age < 18 years) with pseudopapilledema and true papilledema.

Methods

Four pediatric neuro-ophthalmologists at 4 different institutions contributed fundus photographs of children with confirmed diagnoses of papilledema or pseudopapilledema. An AI model to classify fundus photographs as papilledema or pseudopapilledema was developed using a DenseNet backbone and a tribranch convolutional neural network. We performed 10-fold cross-validation and separately analyzed an external test set. The AI model's performance was compared with 2 masked human expert pediatric neuro-ophthalmologists, who performed the same classification task.

Main Outcome Measures

Accuracy, sensitivity, and specificity of the AI model compared with human experts.

Results

The area under receiver operating curve of the AI model was 0.77 for the cross-validation set and 0.81 for the external test set. The accuracy of the AI model was 70.0% for the cross-validation set and 73.9% for the external test set. The sensitivity of the AI model was 73.4% for the cross-validation set and 90.4% for the external test set. The AI model's accuracy was significantly higher than human experts on the cross validation set (P < 0.002), and the model's sensitivity was significantly higher on the external test set (P = 0.0002). The specificity of the AI model and human experts was similar (56.4%-67.3%). Moreover, the AI model was significantly more sensitive at detecting mild papilledema than human experts, whereas AI and humans performed similarly on photographs of moderate-to-severe papilledema. On review of the external test set, only 1 child (with nearly resolved pseudotumor cerebri) had both eyes with papilledema incorrectly classified as pseudopapilledema.

Conclusions

When classifying fundus photographs of pediatric papilledema and pseudopapilledema, our AI model achieved > 90% sensitivity at detecting papilledema, superior to human experts. Due to the high sensitivity and low false negative rate, AI may be useful to triage children with suspected papilledema requiring work-up to evaluate for serious underlying neurologic conditions.

Financial Disclosures

Proprietary or commercial disclosure may be found in the Footnotes and Disclosures at the end of this article.

Correlation between the particle size, structural and photoluminescence spectra of nano NiCr2O4 and La doped NiCr2O4 materials

Nano NiCr2O4 undoped and La doped NiCr2O4 nanorods array were successfully prepared by solution based conventional method[sbcm]. The synthesized samples were characterized by the diffuse reflectance spectroscopy (DRS) and photoluminescence (PL) spectroscopy for finding optical properties. Further, the samples structure confirmed by Fourier transforms infrared (FTIR), and X-ray diffraction (XRD)techniques. High-resolution transmission electron microscopy (HRTEM) analysis revealed the attachment of NiCr2O4 nanorods on surface of nanoparticles. From the results, it was found that the reaction time, band gap energy, and particle size strongly influenced by changing the concentration of La in NiCr2O4. This work is notable for its examination of the impact of the precursor on the optical and structural characteristics of samples of La-doped and undoped NiCr2O4. This was the first time the investigation had been done. The average particle size of the La-doped and undoped NiCr2O4 samples is between 16 and 24 nm.

Multivariable model of postoperative delirium in cardiac surgery patients: proteomic and demographic contributions

Background

Delirium following cardiac surgery is common, morbid, and costly, but may be prevented with risk stratification and targeted intervention. Preoperative protein signatures may identify patients at increased risk for worse postoperative outcomes, including delirium. In this study, we aimed to identify plasma protein biomarkers and develop a predictive model for postoperative delirium in older patients undergoing cardiac surgery, while also uncovering possible pathophysiological mechanisms.

Methods

SOMAscan analysis of 1,305 proteins in the plasma from 57 older adults undergoing cardiac surgery requiring cardiopulmonary bypass was conducted to define delirium-specific protein signatures at baseline (PREOP) and postoperative day 2 (POD2). Selected proteins were validated in 115 patients using the ELLA multiplex immunoassay platform. Proteins were combined with clinical and demographic variables to build multivariable models that estimate the risk of postoperative delirium and bring light to the underlying pathophysiology.

Results

A total of 115 and 85 proteins from SOMAscan analyses were found altered in delirious patients at PREOP and POD2, respectively (p<0.05). Using four criteria including associations with surgery, delirium, and biological plausibility, 12 biomarker candidates (Tukey's fold change (|tFC|)>1.4, Benjamini-Hochberg (BH)-p<0.01) were selected for ELLA multiplex validation. Eight proteins were significantly altered at PREOP, and seven proteins at POD2 (p<0.05), in patients who developed postoperative delirium compared to non-delirious patients. Statistical analyses of model fit resulted in the selection of a combination of age, sex, and three proteins (angiopoietin-2 (ANGPT2); C-C motif chemokine 5 (CCL5); and metalloproteinase inhibitor 1 (TIMP1); AUC=0.829) as the best performing predictive model for delirium at PREOP. The delirium-associated proteins identified as biomarker candidates are involved with inflammation, glial dysfunction, vascularization, and hemostasis, highlighting the multifactorial pathophysiology of delirium.

Conclusion

Our study proposes a model of postoperative delirium that includes a combination of older age, female sex, and altered levels of three proteins. Our results support the identification of patients at higher risk of developing postoperative delirium after cardiac surgery and provide insights on the underlying pathophysiology. ClinicalTrials.gov ( NCT02546765 ).

Intra-Operative Radiotherapy (IORT) in Breast Conserving Therapy in Early-Stage Breast Cancer and DCIS

PURPOSE/OBJECTIVE(S)

Initial breast intra-operative radiotherapy (IORT) results in clinical trials were encouraging though with longer follow up, increased local recurrences have been reported compared with whole breast radiation or other partial breast radiation including accelerated partial breast irradiation (APBI) methods. The goal of the study is to report our prospective single institution IORT breast study outcomes of local recurrence (LR) including true recurrence and breast elsewhere failures, breast cancer specific survival (BCSS), and overall survival (OS) with low energy x-ray IORT in early-stage breast cancer or ductal carcinoma in situ.

MATERIALS/METHODS

A total of 480 patients with early-stage breast cancer or DCIS were prospectively enrolled in an IRB approved single institution trial and treated with low energy X-ray IORT 20 Gy at time of breast-conserving surgery. Eligibility criteria included ≥ 45 years of age with unifocal tumors < 3 cm deemed candidates for partial mastectomy. Supplemental external beam radiation was recommended for patients with high-risk surgical pathology including multifocal disease, positive nodes, close margins < 2 mm, or lymphovascular invasion. Ipsilateral breast tumor recurrences were classified as true recurrence versus elsewhere failure by location and histology: same/different quadrant and similar/different histology. Kaplan-Meier methods were used to estimate survival probabilities across time.

RESULTS

Median age of enrolled patients was 64 years with the majority of patients having favorable phenotype with 94% ER+ and 93% Her-2 - disease. 110 patients (23%) had supplemental EBRT delivered; 103 to the whole breast and 7 to the breast and regional nodes. At a median follow up of 73 months (range 17 - 131 months), there were 23 (4.8%) ipsilateral breast tumor recurrences, of which 9 were true recurrences (1.9%) and 14 elsewhere failures (2.9%). One patient with true recurrence and 3 patients with elsewhere breast failures synchronously presented with clinical or radiographic regional node involvement. Seven patient developed contralateral breast cancer and 8 patients developed distant metastases during the follow-up period. There were 2 breast cancer related deaths. At 6-years, overall survival rate was 96.8% and breast cancer specific survival was 98.7%.

CONCLUSION

Our study outcomes reflect similar outcomes as other reported IORT studies with electron or low energy X-ray in breast cancer, with higher risk of local failure than historical whole breast and other partial breast radiation techniques. This supports current radiation society guidelines for IORT monotherapy for breast cancer to be optimally considered in the context of prospective clinical trials.

Data Driven Approach to Exactrac Setup Parameters after CBCT for Cranial Radiotherapy

PURPOSE/OBJECTIVE(S)

The purpose of this study is to 1) Determine the congruence of shifts derived from Cone-Beam CT (CBCT) and from Exactrac dynamic KV X-rays 2) To setup action levels for Exactrac imaging to determine if patient potentially moved between CBCT and Exactrac acquisition and 3) To analyze if Exactrac alone can be reliably used for cranial setup forgoing the CBCT step MATERIALS/METHODS: Exactrac dynamic, uses in-room KV X-ray imaging that is mounted on the floor to monitor patient positioning during treatment. The congruence of imaging and radiation isocenter for the LINAC and Exactrac system was verified using the Winston-Lutz (WL) test over a period of one year. The WL pointer was set up and its coincidence with imaging and radiation isocenter was confirmed. Exactrac images were then acquired at various couch angles and the pointer deviation from Exactrac imaging isocenter is noted. Secondly, translation and rotation shifts for 175 consecutive cranial cases were examined to determine the deviation between shifts as denoted by CBCT and Exactrac. These patients were initially set up using CBCT and then once in treatment position, Exactrac KV images were acquired to check for any deviation. The deviation between the two systems was collected and a Kolomogorov-Smirnov (KS) test was performed on the data to check for the normality of the distribution. Statistical Process Control (SPC) was performed to derive action levels for Exactrac based shifts after CBCT.

RESULTS

Based on repeated Winston-Lutz tests over a period of one year, the maximum deviation between radiation and imaging isocenters and Exactrac isocenter was 0.3mm and 0.3 deg over all couch angles. This number remained stable over the entire time period without necessitating any recalibration of Exactrac isocenter. Based on patient data for cranial cases, the mean and standard deviations for the largest shifts were (0.45 mm, 0.40 mm) for translations (range 0 - 2.03mm) and (0.44 deg and 0.32 deg) for rotations (range 0 - 2.21 degree). Using SPC, it was decided that the action level for translations and rotations could be set to 0.8mm and 0.5 deg respectively. Any deviation beyond this action level necessitates re-imaging to verify that the patient did not move in between the CBCT and Exactrac imaging acquisitions CONCLUSION: Exactrac system derived shifts show excellent agreement with CBCT. The isocentricity of the systems is maintained over a long period of time and shows no drift. Either system can be reliably used to set up cranial patients. With the added advantage of speed of acquisition, matching and shifts, the Exactrac system could replace CBCT for daily setup of patients undergoing cranial radiotherapy.

Relationship satisfaction, feelings of closeness and annoyance, and linkage in electrodermal activity

Physiological linkage refers to moment-to-moment, time-linked coordination in physiological responses among people in close relationships. Although people in romantic relationships have been shown to evidence linkage in their physiological responses over time, it is still unclear how patterns of covariation relate to in-the-moment, as well as general levels of, relationship functioning. In the present study with data collected between 2014 and 2017, we capture linkage in electrodermal activity (EDA) in a diverse sample of young-adult couples, generally representative and generalizable to the Los Angeles community from which we sampled. We test how naturally occurring, shifting feelings of closeness with and annoyance toward one's partner relate to concurrent changes in levels of physiological linkage over the course of 1 day. Additionally, we examine how linkage relates to overall relationship satisfaction. Results showed that couples evidenced significant covariation in their levels of physiological arousal in daily life. Further, physiological linkage increased during hours that participants felt close to their romantic partners but not during hours that participants felt annoyed with their partners. Finally, those participants with overall higher levels of relationship satisfaction showed lower levels of linkage over the day of data collection. These findings highlight how individuals respond in sync with their romantic partners and how this process ebbs and flows in conjunction with the shifting emotional tone of their relationships. The discussion focuses on how linkage might enhance closeness or, alternatively, contribute to conflict escalation and the potential of linkage processes to promote positive interpersonal relationships. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

SocialBit: protocol for a prospective observational study to validate a wearable social sensor for stroke survivors with diverse neurological abilities

INTRODUCTION

Social isolation has been found to be a significant risk factor for health outcomes, on par with traditional risk factors. This isolation is characterised by reduced social interactions, which can be detected acoustically. To accomplish this, we created a machine learning algorithm called SocialBit. SocialBit runs on a smartwatch and detects minutes of social interaction based on vocal features from ambient audio samples without natural language processing.

METHODS AND ANALYSIS

In this study, we aim to validate the accuracy of SocialBit in stroke survivors with varying speech, cognitive and physical deficits. Training and testing on persons with diverse neurological abilities allows SocialBit to be a universally accessible social sensor. We are recruiting 200 patients and following them for up to 8 days during hospitalisation and rehabilitation, while they wear a SocialBit-equipped smartwatch and engage in naturalistic daily interactions. Human observers tally the interactions via a video livestream (ground truth) to analyse the performance of SocialBit against it. We also examine the association of social interaction time with stroke characteristics and outcomes. If successful, SocialBit would be the first social sensor available on commercial devices for persons with diverse abilities.

ETHICS AND DISSEMINATION

This study has received ethical approval from the Institutional Review Board of Mass General Brigham (Protocol #2020P003739). The results of this study will be published in a peer-reviewed journal.

Azimuthal Correlations within Exclusive Dijets with Large Momentum Transfer in Photon-Lead Collisions

The structure of nucleons is multidimensional and depends on the transverse momenta, spatial geometry, and polarization of the constituent partons. Such a structure can be studied using high-energy photons produced in ultraperipheral heavy-ion collisions. The first measurement of the azimuthal angular correlations of exclusively produced events with two jets in photon-lead interactions at large momentum transfer is presented, a process that is considered to be sensitive to the underlying nuclear gluon polarization. This study uses a data sample of ultraperipheral lead-lead collisions at sqrt[s_{NN}]=5.02  TeV, corresponding to an integrated luminosity of 0.38  nb^{-1}, collected with the CMS experiment at the LHC. The measured second harmonic of the correlation between the sum and difference of the two jet transverse momentum vectors is found to be positive, and rising, as the dijet transverse momentum increases. A well-tuned model that has been successful at describing a wide range of proton scattering data from the HERA experiments fails to describe the observed correlations, suggesting the presence of gluon polarization effects.

Multimodal neuroimaging data from a 5-week heart rate variability biofeedback randomized clinical trial

We present data from the Heart Rate Variability and Emotion Regulation (HRV-ER) randomized clinical trial testing effects of HRV biofeedback. Younger (N = 121) and older (N = 72) participants completed baseline magnetic resonance imaging (MRI) including T1-weighted, resting and emotion regulation task functional MRI (fMRI), pulsed continuous arterial spin labeling (PCASL), and proton magnetic resonance spectroscopy (1H MRS). During fMRI scans, physiological measures (blood pressure, pulse, respiration, and end-tidal CO2) were continuously acquired. Participants were randomized to either increase heart rate oscillations or decrease heart rate oscillations during daily sessions. After 5 weeks of HRV biofeedback, they repeated the baseline measurements in addition to new measures (ultimatum game fMRI, training mimicking during blood oxygen level dependent (BOLD) and PCASL fMRI). Participants also wore a wristband sensor to estimate sleep time. Psychological assessment comprised three cognitive tests and ten questionnaires related to emotional well-being. A subset (N = 104) provided plasma samples pre- and post-intervention that were assayed for amyloid and tau. Data is publicly available via the OpenNeuro data sharing platform.

A Machine-Learning Algorithm for the Automated Perceptual Evaluation of Dysphonia Severity

OBJECTIVES

Auditory-perceptual assessments are the gold standard for assessing voice quality. This project aims to develop a machine-learning model for measuring perceptual dysphonia severity of audio samples consistent with assessments by expert raters.

METHODS

The Perceptual Voice Qualities Database samples were used, including sustained vowel and Consensus Auditory-Perceptual Evaluation of Voice sentences, which were previously expertly rated on a 0-100 scale. The OpenSMILE (audEERING GmbH, Gilching, Germany) toolkit was used to extract acoustic (Mel-Frequency Cepstral Coefficient-based, n = 1428) and prosodic (n = 152) features, pitch onsets, and recording duration. We utilized a support vector machine and these features (n = 1582) for automated assessment of dysphonia severity. Recordings were separated into vowels (V) and sentences (S) and features were extracted separately from each. Final voice quality predictions were made by combining the features extracted from the individual components with the whole audio (WA) sample (three file sets: S, V, WA).

RESULTS

This algorithm has a high correlation (r = 0.847) with estimates of expert raters. The root mean square error was 13.36. Increasing signal complexity resulted in better estimation of dysphonia, whereby combining the features outperformed WA, S, and V sets individually.

CONCLUSION

A novel machine-learning algorithm was able to perform perceptual estimates of dysphonia severity using standardized audio samples on a 100-point scale. This was highly correlated to expert raters. This suggests that ML algorithms could offer an objective method for evaluating voice samples for dysphonia severity.

LEVEL OF EVIDENCE: 4

Creating musical features using multi-faceted, multi-task encoders based on transformers

Computational machine intelligence approaches have enabled a variety of music-centric technologies in support of creating, sharing and interacting with music content. A strong performance on specific downstream application tasks, such as music genre detection and music emotion recognition, is paramount to ensuring broad capabilities for computational music understanding and Music Information Retrieval. Traditional approaches have relied on supervised learning to train models to support these music-related tasks. However, such approaches require copious annotated data and still may only provide insight into one view of music-namely, that related to the specific task at hand. We present a new model for generating audio-musical features that support music understanding, leveraging self-supervision and cross-domain learning. After pre-training using masked reconstruction of musical input features using self-attention bidirectional transformers, output representations are fine-tuned using several downstream music understanding tasks. Results show that the features generated by our multi-faceted, multi-task, music transformer model, which we call M3BERT, tend to outperform other audio and music embeddings on several diverse music-related tasks, indicating the potential of self-supervised and semi-supervised learning approaches toward a more generalized and robust computational approach to modeling music. Our work can offer a starting point for many music-related modeling tasks, with potential applications in learning deep representations and enabling robust technology applications.

Mel frequency spectral domain defenses against adversarial attacks on speech recognition systems

Automatic speech recognition (ASR) systems are vulnerable to adversarial attacks due to their reliance on machine learning models. Many of the defenses explored for defending ASR systems simply adapt defense approaches developed for the image domain. This paper explores speech-specific defenses in the feature domain and introduces a defense method called mel domain noise flooding (MDNF). MDNF injects additive noise to the mel spectrogram speech representation prior to re-synthesizing the audio signal input to ASR. The defense is evaluated against strong white-box threat models and shows competitive robustness.

It's not what you said, it's how you said it: An analysis of therapist vocal features during psychotherapy

Psychotherapy is a conversation, whereby, at its foundation, many interventions are derived from the therapist talking. Research suggests that the voice can convey a variety of emotional and social information, and individuals may change their voice based on the context and content of the conversation (e.g., talking to a baby or delivering difficult news to patients with cancer). As such, therapists may adjust aspects of their voice throughout a therapy session depending on if they are beginning a therapy session and checking in with a client, conducting more therapeutic "work," or ending the session. In this study, we modeled three vocal features-pitch, energy, and rate-with linear and quadratic multilevel models to understand how therapists' vocal features change throughout a therapy session. We hypothesized that all three vocal features would be best fit with a quadratic function - starting high and more congruent with a conversational voice, decreasing during the middle portions of therapy where more therapeutic interventions were being administered, and increasing again at the end of the session. Results indicated a quadratic model for all three vocal features was superior in fitting the data, as compared to a linear model, suggesting that therapists begin and end therapy using a different style of voice than in the middle of a session.

Measurements of the associated production of a W boson and a charm quark in proton-proton collisions at s = 8 TeV

Measurements of the associated production of a W boson and a charm ( c ) quark in proton-proton collisions at a centre-of-mass energy of 8 TeV are reported. The analysis uses a data sample corresponding to a total integrated luminosity of 19.7 fb - 1 collected by the CMS detector at the LHC. The W bosons are identified through their leptonic decays to an electron or a muon, and a neutrino. Charm quark jets are selected using distinctive signatures of charm hadron decays. The product of the cross section and branching fraction σ ( pp → W + c + X ) B ( W → ℓ ν ) , where ℓ = e or μ , and the cross section ratio σ ( pp → W + + c ¯ + X ) / σ ( pp → W - + c + X ) are measured in a fiducial volume and differentially as functions of the pseudorapidity and of the transverse momentum of the lepton from the W boson decay. The results are compared with theoretical predictions. The impact of these measurements on the determination of the strange quark distribution is assessed.

Phone duration modeling for speaker age estimation in children

Automatic inference of paralinguistic information from speech, such as age, is an important area of research with many technological applications. Speaker age estimation can help with age-appropriate curation of information content and personalized interactive experiences. However, automatic speaker age estimation in children is challenging due to the paucity of speech data representing the developmental spectrum, and the large signal variability including within a given age group. Most prior approaches in child speaker age estimation adopt methods directly drawn from research on adult speech. In this paper, we propose a novel technique that exploits temporal variability present in children's speech for estimation of children's age. We focus on phone durations as biomarker of children's age. Phone duration distributions are derived by forced-aligning children's speech with transcripts. Regression models are trained to predict speaker age among children studying in kindergarten up to grade 10. Experiments on two children's speech datasets are used to demonstrate the robustness and portability of proposed features over multiple domains of varying signal conditions. Phonemes contributing most to estimation of children speaker age are analyzed and presented. Experimental results suggest phone durations contain important development-related information of children. The proposed features are also suited for application under low data scenarios.

You never know what you are going to get: Large-scale assessment of therapists’ supportive counseling skill use

Supportive counseling skills like empathy and active listening are critical ingredients of all psychotherapies, but most research relies on client or therapist reports of the treatment process. This study utilized machine-learning models trained to evaluate counseling skills to evaluate supportive skill use in 3,917 session recordings. We analyzed overall skill use and variation in practice patterns using a series of mixed effects models. On average, therapists scored moderately high on observer-rated empathy (i.e., 3.8 out of 5), 3.3% of the therapists' utterances in a session were open questions, and 12.9% of their utterances were reflections. However, there were substantial differences in skill use across therapists as well as across clients within-therapist caseloads. These findings highlight the substantial variability in the process of counseling that clients may experience when they access psychotherapy. We discuss findings in the context of both the need for therapists to be responsive and flexible with their clients, but also potential costs related to the lack of a more uniform experience of care. (PsycInfo Database Record (c) 2022 APA, all rights reserved).

Enhancing the quality of cognitive behavioral therapy in community mental health through artificial intelligence generated fidelity feedback (Project AFFECT): a study protocol

Background

Each year, millions of Americans receive evidence-based psychotherapies (EBPs) like cognitive behavioral therapy (CBT) for the treatment of mental and behavioral health problems. Yet, at present, there is no scalable method for evaluating the quality of psychotherapy services, leaving EBP quality and effectiveness largely unmeasured and unknown. Project AFFECT will develop and evaluate an AI-based software system to automatically estimate CBT fidelity from a recording of a CBT session. Project AFFECT is an NIMH-funded research partnership between the Penn Collaborative for CBT and Implementation Science and Lyssn.io, Inc. (“Lyssn”) a start-up developing AI-based technologies that are objective, scalable, and cost efficient, to support training, supervision, and quality assurance of EBPs. Lyssn provides HIPAA-compliant, cloud-based software for secure recording, sharing, and reviewing of therapy sessions, which includes AI-generated metrics for CBT. The proposed tool will build from and be integrated into this core platform.

Methods

Phase I will work from an existing software prototype to develop a LyssnCBT user interface geared to the needs of community mental health (CMH) agencies. Core activities include a user-centered design focus group and interviews with community mental health therapists, supervisors, and administrators to inform the design and development of LyssnCBT. LyssnCBT will be evaluated for usability and implementation readiness in a final stage of Phase I. Phase II will conduct a stepped-wedge, hybrid implementation-effectiveness randomized trial (N = 1,875 clients) to evaluate the effectiveness of LyssnCBT to improve therapist CBT skills and client outcomes and reduce client drop-out. Analyses will also examine the hypothesized mechanism of action underlying LyssnCBT.

Discussion

Successful execution will provide automated, scalable CBT fidelity feedback for the first time ever, supporting high-quality training, supervision, and quality assurance, and providing a core technology foundation that could support the quality delivery of a range of EBPs in the future.

Trial registration

ClinicalTrials.gov; NCT05340738; approved 4/21/2022.

TILES-2019: A longitudinal physiologic and behavioral data set of medical residents in an intensive care unit

The TILES-2019 data set consists of behavioral and physiological data gathered from 57 medical residents (i.e., trainees) working in an intensive care unit (ICU) in the United States. The data set allows for the exploration of longitudinal changes in well-being, teamwork, and job performance in a demanding environment, as residents worked in the ICU for three weeks. Residents wore a Fitbit, a Bluetooth-based proximity sensor, and an audio-feature recorder. They completed daily surveys and interviews at the beginning and end of their rotation. In addition, we collected data from environmental sensors (i.e., Internet-of-Things Bluetooth data hubs) and obtained hospital records (e.g., patient census) and residents’ job evaluations. This data set may be may be of interest to researchers interested in workplace stress, group dynamics, social support, the physical and psychological effects of witnessing patient deaths, predicting survey data from sensors, and privacy-aware and privacy-preserving machine learning. Notably, a small subset of the data was collected during the first wave of the COVID-19 pandemic.

Measurement(s)	Stress • Burnout • Affect • Depression • Sleep • Physical Activity Measurement • Alcohol Use History • Frequency Any Tobacco Use • Personality • Social Support • Intragroup Conflict • Challenge and Hindrance Stressors • Demographics • Context and Atypical Events • Daily Stressors • Most Stressful Event • Work Context • Job Performance • Job Satisfaction • Stressors at Work • Charting at Home • Coworker Trust • Social Networks at Work • Socialization Outside of Work • Use of Wellness Resources • Heart Rate • Step Count • Acoustic Features • Team Interactions • Proximity to Key Objects • Cell Phone Use • Hospital Contextual Data • Coping with Stress • Productivity at Work • Pride at Work • Teamwork • Support System
Technology Type(s)	Perceived Stress Scale - 14 Questionnaire • Survey • Patient Health Questionnaire - 9 Item • Pittsburgh Sleep Quality Index • FitBit • International Physical Activity Questionnaire (August 2002) Short Last 7 Days Self-Administered Format • Unihertz Atom Phone • Minew E8- TILES Interaction Sensors • Minew E8- Eddystone Beach • Rescuetime • Evaluations • Patient Census • Interview
Sample Characteristic - Organism	Homo sapiens
Sample Characteristic - Location	Los Angeles County and University of Southern California Medical Center

An Automated Quality Evaluation Framework of Psychotherapy Conversations with Local Quality Estimates

Text-based computational approaches for assessing the quality of psychotherapy are being developed to support quality assurance and clinical training. However, due to the long durations of typical conversation based therapy sessions, and due to limited annotated modeling resources, computational methods largely rely on frequency-based lexical features or dialogue acts to assess the overall session level characteristics. In this work, we propose a hierarchical framework to automatically evaluate the quality of transcribed Cognitive Behavioral Therapy (CBT) interactions. Given the richly dynamic nature of the spoken dialog within a talk therapy session, to evaluate the overall session level quality, we propose to consider modeling it as a function of local variations across the interaction. To implement that empirically, we divide each psychotherapy session into conversation segments and initialize the segment-level qualities with the session-level scores. First, we produce segment embeddings by fine-tuning a BERT-based model, and predict segment-level (local) quality scores. These embeddings are used as the lower-level input to a Bidirectional LSTM-based neural network to predict the session-level (global) quality estimates. In particular, we model the global quality as a linear function of the local quality scores, which allows us to update the segment-level quality estimates based on the session-level quality prediction. These newly estimated segment-level scores benefit the BERT fine-tuning process, which in turn results in better segment embeddings. We evaluate the proposed framework on automatically derived transcriptions from real-world CBT clinical recordings to predict session-level behavior codes. The results indicate that our approach leads to improved evaluation accuracy for most codes when used for both regression and classification tasks.

Interpersonal synchrony across vocal and lexical modalities in interactions involving children with autism spectrum disorder

Quantifying behavioral synchrony can inform clinical diagnosis, long-term monitoring, and individualised interventions in neuro-developmental disorders characterized by deficit in communication and social interaction, such as autism spectrum disorder. In this work, three different objective measures of interpersonal synchrony are evaluated across vocal and linguistic communication modalities. For vocal prosodic and spectral features, dynamic time warping distance and squared cosine distance of (feature-wise) complexity are used, and for lexical features, word mover's distance is applied to capture behavioral synchrony. It is shown that these interpersonal vocal and linguistic synchrony measures capture complementary information that helps in characterizing overall behavioral patterns.

First Search for Exclusive Diphoton Production at High Mass with Tagged Protons in Proton-Proton Collisions at sqrt[s]=13 TeV

A search for exclusive two-photon production via photon exchange in proton-proton collisions, pp→pγγp with intact protons, is presented. The data correspond to an integrated luminosity of 9.4  fb^{-1} collected in 2016 using the CMS and TOTEM detectors at a center-of-mass energy of 13 TeV at the LHC. Events are selected with a diphoton invariant mass above 350 GeV and with both protons intact in the final state, to reduce backgrounds from strong interactions. The events of interest are those where the invariant mass and rapidity calculated from the momentum losses of the forward-moving protons match the mass and rapidity of the central, two-photon system. No events are found that satisfy this condition. Interpreting this result in an effective dimension-8 extension of the standard model, the first limits are set on the two anomalous four-photon coupling parameters. If the other parameter is constrained to its standard model value, the limits at 95% confidence level are |ζ_{1}|<2.9×10^{-13}  GeV^{-4} and |ζ_{2}|<6.0×10^{-13}  GeV^{-4}.

POS0763 A MULTIMODAL MAGNETIC RESONANCE IMAGING STUDY OF COGNITIVE FUNCTION IN SYSTEMIC LUPUS ERYTHEMATOSUS: A MACHINE LEARNING APPROACH

Background

Systemic lupus erythematosus (SLE) is a multisystem autoimmune disorder that can affect the central nervous system. Cognitive dysfuncion is the most common neuropsyhiatric event in SLE patients, yet it is also one of the hardest to diagnose.

Objectives

To investigate if multimodal imaging to assess anatomical magnetic resonance imaging (MRI) abnormalities in the brains of SLE patients can predict cognitive function.

Methods

Subjects underwent voxel-based morphometry (VBM), magnetization transfer imaging (MTI), and dynamic contrast-enhanced (DCE) MRI. Automated Neuropsychological Assessment Metrics (ANAM) was used to assess cognitive function in this cross-sectional study and the primary measure was the total throughput score (TTS). TTS is the total of the throughput scores for each of the 8 ANAM subtests: (i) code substitution learning (CSL); (ii) code substitution immediate (CSI); (iii) code substitution delayed (CSD); (iv) spatial processing (SP); (v) matching to sample (MSP); (vi) running memory continuous performance test (CPT); (vii) mathematical processing (MTH) and (viii) memory search (MS). Olfactory assessment was done using the University of Pennsylvania Smell Identification Test. We used a machine learning-based model (i.e. GLMnet) to predict TTS. Subjects with active SLE disease or above 40 years old were excluded.

Results

Thirty SLE patients [26 female, 32.0 (26.8-37.0) years] without clinically overt neuropsychiatric manifestations and 10 healthy controls (HCs) [9 females, 27.0 (23.0-31.5) years] were enrolled in this study. Both groups had comparable cognitive and olfactory functions. No significant differences were observed in VBM, MTR, olfactory blub and tract (OBT) volume in SLE patients compared to HCs. We observed increased blood-brain barrier (BBB) permeability parameters (Ktrans and PS) in several regions of SLE patients. DCE-MRI perfusion parameters such as perfusion (F) and vp but not permeability measures were associated with TTS. In particular, F right amygdala correlated with TTS in SLE patients (r = 0.636, FDR p < 0.05) (Table 1). Using GLMnet, we trained a multimodal MRI model comprising of VBM, MTR, DCE-MRI and OBT volume parameters to predict TTS in SLE patients (r = 0.998, p < 0.0005) (Figure 1).

Figure 1.

Machine learning-based models to predict cognitive function.

Table 1.

Correlation between ANAM tests with perfusion (F) in SLE patients, ranked in descending order of statistical significance for TTS.

VariableTTSCSLCSICSDSPMSPCPTMTHMSF right amygdala0.636‡*0.520‡0.3370.437†0.559‡0.3230.633‡0.412†0.598‡F left entorhinal0.504‡0.422†0.3660.416†0.3050.1850.530‡0.1860.416†F left amygdale0.495‡0.400†0.1890.378†0.3300.2370.491‡0.376†0.449†F choroid0.469†0.384†0.2160.413†0.458†0.2020.456†0.3400.406†plexusF right rostal anterior cingulate0.453†0.3010.1180.2960.393†0.2140.547‡0.420†0.383†F right entorhinal0.448†0.368†0.2320.3120.376†0.1560.438†0.2710.407†F cerebellum white matter0.427†0.3580.2010.370†0.2730.0780.449†0.2900.297F left hippocampus0.427†0.3550.1340.390†0.3560.2030.511‡0.3360.332F brain stem0.407†0.2980.1380.2750.2940.1530.478‡0.3080.369†F right insula0.407†0.3080.0740.3000.3240.1760.437†0.3230.347F left parietal0.400†0.2630.0920.2540.2940.2240.487‡0.2740.332F ventricles0.396†0.3030.0830.3210.370†0.1920.477‡0.2860.361F right temporal0.395†0.2800.1130.2810.2880.1670.477‡0.3220.331F right hippocampus0.395†0.3070.0770.3250.3560.1900.486‡0.3570.339F right parietal0.376†0.2490.0820.2740.2830.1390.460†0.2550.311F right parahippocampal gyrus0.375†0.3530.1190.3020.3410.2410.3530.2080.273

† p < 0.05, ‡ p < 0.01, *FDR p < 0.05

Conclusion

These findings suggest that the BBB may be affected early in the course of cognitive dysfunction, even preceding detectable changes in other MRI sequences and machine learning algorithms can be used to predict TTS measures, even in asymptomatic SLE patients.

References

Nil.

Disclosure of Interests

Sen Hee Tay: None declared, Mary Stephenson: None declared, Nur Azizah Allameen: None declared, Sriram Narayanan: None declared, Bernett Lee: None declared, Anselm Mak Speakers bureau: JnJ Apr 2019 and GSK Jan 2022, Grant/research support from: GSK - The Supported Studies Programme

Representation of professions in entertainment media: Insights into frequency and sentiment trends through computational text analysis

Societal ideas and trends dictate media narratives and cinematic depictions which in turn influence people’s beliefs and perceptions of the real world. Media portrayal of individuals and social institutions related to culture, education, government, religion, and family affect their function and evolution over time as people perceive and incorporate the representations from portrayals into their everyday lives. It is important to study media depictions of social structures so that they do not propagate or reinforce negative stereotypes, or discriminate against a particular section of the society. In this work, we examine media representation of different professions and provide computational insights into their incidence, and sentiment expressed, in entertainment media content. We create a searchable taxonomy of professional groups, synsets, and titles to facilitate their retrieval from short-context speaker-agnostic text passages like movie and television (TV) show subtitles. We leverage this taxonomy and relevant natural language processing models to create a corpus of professional mentions in media content, spanning more than 136,000 IMDb titles over seven decades (1950-2017). We analyze the frequency and sentiment trends of different occupations, study the effect of media attributes such as genre, country of production, and title type on these trends, and investigate whether the incidence of professions in media subtitles correlate with their real-world employment statistics. We observe increased media mentions over time of STEM, arts, sports, and entertainment occupations in the analyzed subtitles, and a decreased frequency of manual labor jobs and military occupations. The sentiment expressed toward lawyers, police, and doctors showed increasing negative trends over time, whereas the mentions about astronauts, musicians, singers, and engineers appear more favorably. We found that genre is a good predictor of the type of professions mentioned in movies and TV shows. Professions that employ more people showed increased media frequency.

Search for low-mass dilepton resonances in Higgs boson decays to four-lepton final states in proton-proton collisions at s = 13 TeV

A search for low-mass dilepton resonances in Higgs boson decays is conducted in the four-lepton final state. The decay is assumed to proceed via a pair of beyond the standard model particles, or one such particle and a Z boson. The search uses proton-proton collision data collected with the CMS detector at the CERN LHC, corresponding to an integrated luminosity of 137 fb - 1 , at a center-of-mass energy s = 13 TeV . No significant deviation from the standard model expectation is observed. Upper limits at 95% confidence level are set on model-independent Higgs boson decay branching fractions. Additionally, limits on dark photon and axion-like particle production, based on two specific models, are reported.

Leveraging Social Networks for the Assessment and Management of Neurological Patients

Social networks are the persons surrounding a patient who provide support, circulate information, and influence health behaviors. For patients seen by neurologists, social networks are one of the most proximate social determinants of health that are actually accessible to clinicians, compared with wider social forces such as structural inequalities. We can measure social networks and related phenomena of social connection using a growing set of scalable and quantitative tools increasing familiarity with social network effects and mechanisms. This scientific approach is built on decades of neurobiological and psychological research highlighting the impact of the social environment on physical and mental well-being, nervous system structure, and neuro-recovery. Here, we review the biology and psychology of social networks, assessment methods including novel social sensors, and the design of network interventions and social therapeutics.

Variation in compensatory strategies as a function of target constriction degree in post-glossectomy speech

Individuals who have undergone treatment for oral cancer oftentimes exhibit compensatory behavior in consonant production. This pilot study investigates whether compensatory mechanisms utilized in the production of speech sounds with a given target constriction location vary systematically depending on target manner of articulation. The data reveal that compensatory strategies used to produce target alveolar segments vary systematically as a function of target manner of articulation in subtle yet meaningful ways. When target constriction degree at a particular constriction location cannot be preserved, individuals may leverage their ability to finely modulate constriction degree at multiple constriction locations along the vocal tract.

Automated evaluation of psychotherapy skills using speech and language technologies

With the growing prevalence of psychological interventions, it is vital to have measures which rate the effectiveness of psychological care to assist in training, supervision, and quality assurance of services. Traditionally, quality assessment is addressed by human raters who evaluate recorded sessions along specific dimensions, often codified through constructs relevant to the approach and domain. This is, however, a cost-prohibitive and time-consuming method that leads to poor feasibility and limited use in real-world settings. To facilitate this process, we have developed an automated competency rating tool able to process the raw recorded audio of a session, analyzing who spoke when, what they said, and how the health professional used language to provide therapy. Focusing on a use case of a specific type of psychotherapy called "motivational interviewing", our system gives comprehensive feedback to the therapist, including information about the dynamics of the session (e.g., therapist's vs. client's talking time), low-level psychological language descriptors (e.g., type of questions asked), as well as other high-level behavioral constructs (e.g., the extent to which the therapist understands the clients' perspective). We describe our platform and its performance using a dataset of more than 5000 recordings drawn from its deployment in a real-world clinical setting used to assist training of new therapists. Widespread use of automated psychotherapy rating tools may augment experts' capabilities by providing an avenue for more effective training and skill improvement, eventually leading to more positive clinical outcomes.

Advancing Chemical Separations: Unraveling the Structure and Dynamics of Phase Splitting in Liquid-Liquid Extraction

Liquid-liquid extraction (LLE), the go-to process for a variety of chemical separations, is limited by spontaneous organic phase splitting upon sufficient solute loading, called third phase formation. In this study we explore the applicability of critical phenomena theory to gain insight into this deleterious phase behavior with the goal of improving separations efficiency and minimizing waste. A series of samples representative of rare earth purification were constructed to include each of one light and one heavy lanthanide (cerium and lutetium) paired with one of two common malonamide extractants (DMDOHEMA and DMDBTDMA). The resulting postextraction organic phases are chemically complex and often form rich hierarchical structures whose statics and dynamics near the critical point were probed herein with small-angle X-ray scattering and high-speed X-ray photon correlation spectroscopy. Despite their different extraction behaviors, all samples show remarkably similar critical behavior with exponents well described by classical critical point theory consistent with the 3D Ising model, where the critical behavior is characterized by fluctuations with a single diverging length scale. This unexpected result indicates a significant reduction in relevant chemical parameters at the critical point, indicating that the underlying behavior of phase transitions in LLE rely on far fewer variables than are generally assumed. The obtained scalar order parameter is attributed to the extractant fraction of the extractant/diluent mixture, revealing that other solution components and their respective concentrations simply shift the critical temperature but do not affect the nature of the critical fluctuations. These findings point to an opportunity to drastically simplify studies of liquid-liquid phase separation and phase diagram development in general while providing insights into LLE process improvement.

Using Z Boson Events to Study Parton-Medium Interactions in Pb-Pb Collisions

The spectra measurements of charged hadrons produced in the shower of a parton originating in the same hard scattering with a leptonically decaying Z boson are reported in lead-lead nuclei (Pb-Pb) and proton-proton (pp) collisions at a nucleon-nucleon center-of-mass energy of 5.02 TeV. Both Pb-Pb and pp data sets are recorded by the CMS experiment at the LHC and correspond to an integrated luminosity of 1.7  nb^{-1} and 320  pb^{-1}, respectively. Hadronic collision data with one reconstructed Z boson candidate with the transverse momentum p_{T}>30  GeV/c are analyzed. The Z boson constrains the initial energy and direction of the associated parton. In heavy ion events, azimuthal angular distributions of charged hadrons with respect to the direction of a Z boson are sensitive to modifications of the in-medium parton shower and medium response. compared to reference data from pp interactions, the results for central Pb-Pb collisions indicate a modification of the angular correlations. The measurements of the fragmentation functions and p_{T} spectra of charged particles in Z boson events, which are sensitive to medium modifications of the parton shower longitudinal structure, are also reported. Significant modifications in central Pb-Pb events compared to the pp reference data are also found for these observables.

Search for strongly interacting massive particles generating trackless jets in proton-proton collisions at s = 13 TeV

A search for dark matter in the form of strongly interacting massive particles (SIMPs) using the CMS detector at the LHC is presented. The SIMPs would be produced in pairs that manifest themselves as pairs of jets without tracks. The energy fraction of jets carried by charged particles is used as a key discriminator to suppress efficiently the large multijet background, and the remaining background is estimated directly from data. The search is performed using proton-proton collision data corresponding to an integrated luminosity of 16.1 fb - 1 , collected with the CMS detector in 2016. No significant excess of events is observed above the expected background. For the simplified dark matter model under consideration, SIMPs with masses up to 100 GeV are excluded and further sensitivity is explored towards higher masses.

Intra-topic latency as an automated behavioral marker of treatment response in autism spectrum disorder

Data science advances in behavioral signal processing and machine learning hold the promise to automatically quantify clinically meaningful behaviors that can be applied to a large amount of data. The objective of this study was to identify an automated behavioral marker of treatment response in social communication in children with autism spectrum disorder (ASD). First, using an automated computational method, we successfully derived the amount of time it took for a child with ASD and an adult social partner (N pairs = 210) to respond to each other while they were engaged in conversation bits (“latency”) using recordings of brief, natural social interactions. Then, we measured changes in latency at pre- and post-interventions. Children with ASD who were receiving interventions showed significantly larger reduction in latency compared to those who were not receiving interventions. There was also a significant group difference in the changes in latency for adult social partners. Results suggest that the automated measure of latency derived from natural social interactions is a scalable and objective method to quantify treatment response in children with ASD.

Evidence for X(3872) in Pb-Pb Collisions and Studies of its Prompt Production at sqrt[s_{NN}]=5.02 TeV

The first evidence for X(3872) production in relativistic heavy ion collisions is reported. The X(3872) production is studied in lead-lead (Pb-Pb) collisions at a center-of-mass energy of sqrt[s_{NN}]=5.02  TeV per nucleon pair, using the decay chain X(3872)→J/ψπ^{+}π^{-}→μ^{+}μ^{-}π^{+}π^{-}. The data were recorded with the CMS detector in 2018 and correspond to an integrated luminosity of 1.7  nb^{-1}. The measurement is performed in the rapidity and transverse momentum ranges |y|<1.6 and 15<p_{T}<50  GeV/c. The significance of the inclusive X(3872) signal is 4.2 standard deviations. The prompt X(3872) to ψ2S yield ratio is found to be ρ^{Pb-Pb}=1.08±0.49(stat)±0.52(syst), to be compared with typical values of 0.1 for pp collisions. This result provides a unique experimental input to theoretical models of the X(3872) production mechanism, and of the nature of this exotic state.

Multi-label Multi-task Deep Learning for Behavioral Coding

We propose a methodology for estimating human behaviors in psychotherapy sessions using mutli-label and multi-task learning paradigms. We discuss the problem of behavioral coding in which data of human interactions is the annotated with labels to describe relevant human behaviors of interest. We describe two related, yet distinct, corpora consisting of therapist client interactions in psychotherapy sessions. We experimentally compare the proposed learning approaches for estimating behaviors of interest in these datasets. Specifically, we compare single and multiple label learning approaches, single and multiple task learning approaches, and evaluate the performance of these approaches when incorporating turn context. We demonstrate the prediction performance gains which can be achieved by using the proposed paradigms and discuss the insights these models provide into these complex interactions.

Causal Indicators for Assessing the Truthfulness of Child Speech in Forensic Interviews

When interviewing a child who may have witnessed a crime, the interviewer must ask carefully directed questions in order to elicit a truthful statement from the child. The presented work uses Granger causal analysis to examine and represent child-interviewer interaction dynamics over such an interview. Our work demonstrates that Granger Causal analysis of psycholinguistic and acoustic signals from speech yields significant predictors of whether a child is telling the truth, as well as whether a child will disclose witnessing a transgression later in the interview. By incorporating cross-modal Granger causal features extracted from audio and transcripts of forensic interviews, we are able to substantially outperform conventional deception detection methods and a number of simulated baselines. Our results suggest that a child's use of concreteness and imageability in their language are strong psycholinguistic indicators of truth-telling and that the coordination of child and interviewer speech signals is much more informative than the specific language used throughout the interview.

Suboptimal uptake, retention, and adherence of daily oral PrEP among people with OUD receiving HCV treatment

Background

Daily oral preexposure prophylaxis (PrEP) with tenofovir disoproxil fumarate (TDF)/emtricitabine (FTC) prevents human immunodeficiency (HIV) among people who inject drugs (PWID). Despite rising HIV incidence and injection drug use (IDU), PrEP use remains low and there is limited research about uptake, adherence, and retention among PWID.

Methods

The ANCHOR investigation evaluated a community-based care model collocating hepatitis C virus (HCV) treatment, medication for opioid use disorder (OUD), and PrEP in individuals in Washington, DC, and Baltimore, Maryland. PrEP counseling was conducted from HCV treatment day 0 until week 24. Subjects could start any time during this window, were followed for 48 weeks, and were assessed for adherence by self-report and dried blood spot TDF analysis.

Results

One hundred ninety-eight participants were enrolled, of whom 185 (93%) were HIV negative. Twenty-nine individuals (15.7% of HIV-negative cohort) initiated PrEP. One hundred sixteen participants (62.7%) met 2014 Centers for Disease Control and Prevention (CDC) PrEP criteria due to IDU (82 [44.3%]), sex (9 [4.9%]), or both practices (25 [13.5%]). Providers recommended PrEP to 94 individuals (50.8%), and recommendation was associated with PrEP uptake. Median treatment duration was 104 days (interquartile range, 28–276 days), with 8 participants retained through week 48. Adherence was variable over time by self-report and declined by TDF analysis. No HIV seroconversions occurred.

Conclusions

This cohort of people with HCV and OUD experienced low uptake of PrEP despite the majority meeting CDC criteria. High rates of disruption and discontinuation, compounded by variable adherence, made TDF/FTC a suboptimal prevention strategy. Emerging modalities like long-acting formulations may address these barriers, but PWID have been excluded from their development to date.

Microbial fermentation of Fossence™, a short-chain fructo-oligosaccharide, under simulated human proximal colonic condition and assessment of its prebiotic effects-a pilot study

A short-chain fructo-oligosaccharide (sc-FOS) was tested in a simulator of the human gut microbial ecosystem (SHIME) in vitro model to quantify its prebiotic effects according to Prebiotic Index (PI) and Measure of prebiotic effect (MPE) equations. FossenceTM, (sc-FOS, 0.5%) was fermented in a simulated human proximal colonic condition, using a fecal inoculum from a healthy individual. We analysed the pH reduction, substrate utilization, lactate and short-chain fatty acid (SCFA) production and microbial community modulation. Microbial fermentation of sc-FOS strongly reduced the media pH indicating the production of lactate and SCFA with accumulation of lactate and enhanced levels of acetate (34.38 ± 0.38 mM), propionate (20.93 ± 0.56 mM) and butyrate (4.93 ± 0.03 mM) compared to 18.46 ± 0.20 mM, 6.24 ± 0.10 mM and 3.3 ± 0.06 mM in the blank, respectively. Total SCFA production in test media was 61.91 ± 0.87 mM compared to 33.65 ± 0.36 mM in blank and the contribution of free-sugars present in sc-FOS to SCFAs was negligible. Modulation of the microbial community was analysed through 16S rRNA sequencing and we found that sc-FOS greatly stimulated the beneficial bacteria such as Bifidobacteria and Lactobacillus. We report the PI and MPE values for FossenceTM, as 14.9 and 0.01 respectively at the end of 24 h, which is an indicator of a strong prebiotic effect.

Feature Fusion Strategies for End-to-End Evaluation of Cognitive Behavior Therapy Sessions

Cognitive Behavioral Therapy (CBT) is a goal-oriented psychotherapy for mental health concerns implemented in a conversational setting. The quality of a CBT session is typically assessed by trained human raters who manually assign pre-defined session-level behavioral codes. In this paper, we develop an end-to-end pipeline that converts speech audio to diarized and transcribed text and extracts linguistic features to code the CBT sessions automatically. We investigate both word-level and utterance-level features and propose feature fusion strategies to combine them. The utterance level features include dialog act tags as well as behavioral codes drawn from another well-known talk psychotherapy called Motivational Interviewing (MI). We propose a novel method to augment the word-based features with the utterance level tags for subsequent CBT code estimation. Experiments show that our new fusion strategy outperforms all the studied features, both when used individually and when fused by direct concatenation. We also find that incorporating a sentence segmentation module can further improve the overall system given the preponderance of multi-utterance conversational turns in CBT sessions.

Automated quality assessment of cognitive behavioral therapy sessions through highly contextualized language representations

During a psychotherapy session, the counselor typically adopts techniques which are codified along specific dimensions (e.g., 'displays warmth and confidence', or 'attempts to set up collaboration') to facilitate the evaluation of the session. Those constructs, traditionally scored by trained human raters, reflect the complex nature of psychotherapy and highly depend on the context of the interaction. Recent advances in deep contextualized language models offer an avenue for accurate in-domain linguistic representations which can lead to robust recognition and scoring of such psychotherapy-relevant behavioral constructs, and support quality assurance and supervision. In this work, we propose a BERT-based model for automatic behavioral scoring of a specific type of psychotherapy, called Cognitive Behavioral Therapy (CBT), where prior work is limited to frequency-based language features and/or short text excerpts which do not capture the unique elements involved in a spontaneous long conversational interaction. The model focuses on the classification of therapy sessions with respect to the overall score achieved on the widely-used Cognitive Therapy Rating Scale (CTRS), but is trained in a multi-task manner in order to achieve higher interpretability. BERT-based representations are further augmented with available therapy metadata, providing relevant non-linguistic context and leading to consistent performance improvements. We train and evaluate our models on a set of 1,118 real-world therapy sessions, recorded and automatically transcribed. Our best model achieves an F1 score equal to 72.61% on the binary classification task of low vs. high total CTRS.

1063 Incidence, Risk Factors, and Outcomes of ARDS in Patients with SARS-CoV-2 Infection

Introduction

Many asymptomatic patients are diagnosed with SARS-CoV-2 infection on screening, which might alter their expected course of illness. We wanted to study the incidence, risk factors, and ARDS outcomes in these patients admitted to our ITU.

Method

A review of all admissions (medical, surgical, and obstetric) to our ITU from May to October 2020 was done after institutional ethics approval. Age, gender, comorbidities, admission diagnosis, APACHE II score, and in-hospital course were studied. ARDS was defined as PaO2/FiO2 ≤ 300 mmHg (with PEEP or CPAP ≥ 5 cmH2O) in the absence of cardiac failure or fluid overload. Data were analyzed using Statistical Package for Social Services (SPSS) software Version 21.0 (Armonk, NY: IBM Corp).

Results

Of the 832 cases, 119 (14.3%) had SARS-CoV-2 infection. 41 of 119 (34.4%) cases developed ARDS. Among the comorbidities studied, only hypertension (OR 2.6, 95% CI 1.0-6.2) seemed to increase ARDS odds. Patients with Severe Acute Respiratory Illness (SARI) had a higher incidence of ARDS when compared to the asymptomatic ones (P &lt; .05). Patients with sepsis (OR 5.8, 95% CI 2.4-13.7) and APACHE II score ≥10 (OR 5, 95% CI 2.0-12.3) had higher odds of developing ARDS. Age, gender, trauma, and recent surgery did not seem to increase the risk of ARDS.

Conclusions

Even though COVID-19 patients admitted with SARI and sepsis are at a higher risk of developing ARDS, further research will be needed to predict the extent to which SARS-CoV-2 infection will influence the course of their illness.

Morbidity, mortality, and emerging drug resistance in Device-associated infections (DAIs) in intensive care patients at a 1000-bedded tertiary care teaching hospital

Background

Device-associated infections (DAIs) such as ventilator associated pneumonia (VAP), central line-associated blood stream infection (CLABSI), and catheter-related urinary tract infection (CAUTI) are principal contributors to health hazard and a major preventable threat to patient safety. Robust surveillance of DAI delineates infections, pathogens, resistograms, and facilitates antimicrobial therapy, infection-control, antimicrobial stewardship, and improvement in quality of care.

Methods

This prospective outcome surveillance study was conducted amongst 2067 ICU patients in a 1000-bedded teaching hospital. Clinical, laboratory, and environmental surveillance, as well as screening of health care professionals (HCPs) were conducted using the modified US Centers for Disease Control and Prevention-National Healthcare Safety Network definitions and methods. Morbidity, mortality, and health-care indices were analyzed and two-tier infection prevention and control was promulgated.

Results

Mean occupancy was 95.34% for 2061 patients of 7381 patients/bed/ICU days. One hundred seventeen episodes of DAI occurred in 1258 patients of 12,882 device-days with mean device utilization ratio of 1.79. Mean rate of DAI was 7.40 per 1000 device days. Multiresistant Pseudomonas aeruginosa was most commonly followed by Acinetobacter. Mean all-cause mortality in ICU was 24.85%, whereas all-cause mortality after DAI was 9.79%. Methicillin-resistant Staphylococcus aureus prevalence was 38.46% amongst health-care professionals.

Conclusion

Mean rates of VAP, CLABSI, and CAUTI were 20.69, 2.53, and 2.23 per 1000 device days comparable with Indian and global ICUs. Resolute conviction and sustained momentum in infection prevention and control is an essential step toward patient safety.

Measurements of angular distance and momentum ratio distributions in three-jet and Z + two-jet final states in pp collisions

Collinear (small-angle) and large-angle, as well as soft and hard radiations are investigated in three-jet and Z  + two-jet events collected in proton-proton collisions at the LHC. The normalized production cross sections are measured as a function of the ratio of transverse momenta of two jets and their angular separation. The measurements in the three-jet and Z  + two-jet events are based on data collected at a center-of-mass energy of 8 TeV , corresponding to an integrated luminosity of 19.8 fb - 1 . The Z  + two-jet events are reconstructed in the dimuon decay channel of the Z  boson. The three-jet measurement is extended to include s = 13 TeV data corresponding to an integrated luminosity of 2.3 fb - 1 . The results are compared to predictions from event generators that include parton showers, multiple parton interactions, and hadronization. The collinear and soft regions are in general well described by parton showers, whereas the regions of large angular separation are often best described by calculations using higher-order matrix elements.