Structure-Activity Relationship Studies of Aryl Sulfoxides as Reversible Monoacylglycerol Lipase Inhibitors.

Monoacylglycerol lipase (MAGL) is the key enzyme for the hydrolysis of endocannabinoid 2-arachidonoylglycerol (2-AG). The central role of MAGL in the metabolism of 2-AG makes it an attractive therapeutic target for a variety of disorders, including inflammation-induced tissue injury, pain, multiple sclerosis, and cancer. Previously, we reported LEI-515, an aryl sulfoxide, as a peripherally restricted, covalent reversible MAGL inhibitor that reduced neuropathic pain and inflammation in preclinical models. Here, we describe the structure-activity relationship (SAR) of aryl sulfoxides as MAGL inhibitors that led to the identification of LEI-515. Optimization of the potency of high-throughput screening (HTS) hit 1 yielded compound ±43. However, ±43 was not metabolically stable due to its ester moiety. Replacing the ester group with α-CF2 ketone led to the identification of compound ±73 (LEI-515) as a metabolically stable MAGL inhibitor with subnanomolar potency. LEI-515 is a promising compound to harness the therapeutic potential of MAGL inhibition.

Hospital volume-outcome relationships for robot-assisted surgeries: a population-based analysis.

BACKGROUND: Associations between procedure volumes and outcomes can inform minimum volume standards and the regionalization of health services. Robot-assisted surgery continues to expand globally; however, data are limited regarding which hospitals should be using the technology. STUDY DESIGN: Using administrative health data for all residents of Ontario, Canada, this retrospective cohort study included adult patients who underwent a robot-assisted radical prostatectomy (RARP), total robotic hysterectomy (TRH), robot-assisted partial nephrectomy (RAPN), or robotic portal lobectomy using 4 arms (RPL-4) between January 2010 and September 2021. Associations between yearly hospital volumes and 90-day major complications were evaluated using multivariable logistic regression models adjusted for patient characteristics and clustering at the level of the hospital. RESULTS: A total of 10,879 patients were included, with 7567, 1776, 724, and 812 undergoing a RARP, TRH, RAPN, and RPL-4, respectively. Yearly hospital volume was not associated with 90-day complications for any procedure. Doubling of yearly volume was associated with a 17-min decrease in operative time for RARP (95% confidence interval [CI] - 23 to - 10), 8-min decrease for RAPN (95% CI - 14 to - 2), 24-min decrease for RPL-4 (95% CI - 29 to - 19), and no significant change for TRH (- 7 min; 95% CI - 17 to 3). CONCLUSION: The risk of 90-day major complications does not appear to be higher in low volume hospitals; however, they may not be as efficient with operating room utilization. Careful case selection may have contributed to the lack of an observed association between volumes and complications.

Factors Associated With Loss to Follow-Up in Surgical Trials: A Systematic Review and Meta-Analysis.

INTRODUCTION: Loss to follow-up (LTFU) distorts results of randomized controlled trials (RCTs). Understanding trial characteristics that contribute to LTFU may enable investigators to anticipate the extent of LTFU and plan retention strategies. The objective of this systematic review and meta-analysis was to investigate the extent of LTFU in surgical RCTs and evaluate associations between trial characteristics and LTFU. METHODS: MEDLINE, Embase, and PubMed Central were searched for surgical RCTs published between January 2002 and December 2021 in the 30 highest impact factor surgical journals. Two-hundred eligible RCTs were randomly selected. The pooled LTFU rate was estimated using random intercept Poisson regression. Associations between trial characteristics and LTFU were assessed using metaregression. RESULTS: The 200 RCTs included 37,914 participants and 1307 LTFU events. The pooled LTFU rate was 3.10 participants per 100 patient-years (95% confidence interval [CI] 1.85-5.17). Trial characteristics associated with reduced LTFU were standard-of-care outcome assessments (rate ratio [RR] 0.17; 95% CI 0.06-0.48), surgery for transplantation (RR 0.08; 95% CI 0.01-0.43), and surgery for cancer (RR 0.10; 95% CI 0.02-0.53). Increased LTFU was associated with patient-reported outcomes (RR 14.21; 95% CI 4.82-41.91) and follow-up duration ≥ three months (odds ratio 10.09; 95% CI 4.79-21.28). CONCLUSIONS: LTFU in surgical RCTs is uncommon. Participants may be at increased risk of LTFU in trials with outcomes assessed beyond the standard of care, surgical indications other than cancer or transplant, patient-reported outcomes, and longer follow-up. Investigators should consider the impact of design on LTFU and plan retention strategies accordingly.

Early evaluation of a natural language processing tool to improve access to educational resources for surgical patients.

PURPOSE: Accessible patient information sources are vital in educating patients about the benefits and risks of spinal surgery, which is crucial for obtaining informed consent. We aim to assess the effectiveness of a natural language processing (NLP) pipeline in recognizing surgical procedures from clinic letters and linking this with educational resources. METHODS: Retrospective examination of letters from patients seeking surgery for degenerative spinal disease at a single neurosurgical center. We utilized MedCAT, a named entity recognition and linking NLP, integrated into the electronic health record (EHR), which extracts concepts and links them to systematized nomenclature of medicine-clinical terms (SNOMED-CT). Investigators reviewed clinic letters, identifying words or phrases that described or identified operations and recording the SNOMED-CT terms as ground truth. This was compared to SNOMED-CT terms identified by the model, untrained on our dataset. A pipeline linking clinic letters to patient-specific educational resources was established, and precision, recall, and F1 scores were calculated. RESULTS: Across 199 letters the model identified 582 surgical procedures, and the overall pipeline after adding rules a total of 784 procedures (precision = 0.94, recall = 0.86, F1 = 0.91). Across 187 letters with identified SNOMED-CT terms the integrated pipeline linking education resources directly to the EHR was successful in 157 (78%) patients (precision = 0.99, recall = 0.87, F1 = 0.92). CONCLUSIONS: NLP accurately identifies surgical procedures in pre-operative clinic letters within an untrained subspecialty. Performance varies among letter authors and depends on the language used by clinicians. The identified procedures can be linked to patient education resources, potentially improving patients' understanding of surgical procedures.

Implementation of an Electronic Clinical Decision Support System for the Early Recognition and Management of Dysglycemia in an Inpatient Mental Health Setting Using CogStack: Protocol for a Pilot Hybrid Type 3 Effectiveness-Implementation Randomized Controlled Cluster Trial.

BACKGROUND: Severe mental illnesses (SMIs), including schizophrenia, bipolar affective disorder, and major depressive disorder, are associated with an increased risk of physical health comorbidities and premature mortality from conditions including cardiovascular disease and diabetes. Digital technologies such as electronic clinical decision support systems (eCDSSs) could play a crucial role in improving the clinician-led management of conditions such as dysglycemia (deranged blood sugar levels) and associated conditions such as diabetes in people with a diagnosis of SMI in mental health settings. OBJECTIVE: We have developed a real-time eCDSS using CogStack, an information retrieval and extraction platform, to automatically alert clinicians with National Health Service Trust-approved, guideline-based recommendations for dysglycemia monitoring and management in secondary mental health care. This novel system aims to improve the management of dysglycemia and associated conditions, such as diabetes, in SMI. This protocol describes a pilot study to explore the acceptability, feasibility, and evaluation of its implementation in a mental health inpatient setting. METHODS: This will be a pilot hybrid type 3 effectiveness-implementation randomized controlled cluster trial in inpatient mental health wards. A ward will be the unit of recruitment, where it will be randomly allocated to receive either access to the eCDSS plus usual care or usual care alone over a 4-month period. We will measure implementation outcomes, including the feasibility and acceptability of the eCDSS to clinicians, as primary outcomes, alongside secondary outcomes relating to the process of care measures such as dysglycemia screening rates. An evaluation of other implementation outcomes relating to the eCDSS will be conducted, identifying facilitators and barriers based on established implementation science frameworks. RESULTS: Enrollment of wards began in April 2022, after which clinical staff were recruited to take part in surveys and interviews. The intervention period of the trial began in February 2023, and subsequent data collection was completed in August 2023. Data are currently being analyzed, and results are expected to be available in June 2024. CONCLUSIONS: An eCDSS can have the potential to improve clinician-led management of dysglycemia in inpatient mental health settings. If found to be feasible and acceptable, then, in combination with the results of the implementation evaluation, the system can be refined and improved to support future successful implementation. A larger and more definitive effectiveness trial should then be conducted to assess its impact on clinical outcomes and to inform scalability and application to other conditions in wider mental health care settings. TRIAL REGISTRATION: ClinicalTrials.gov NCT04792268; https://clinicaltrials.gov/study/NCT04792268. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): DERR1-10.2196/49548.

Foresight-a generative pretrained transformer for modelling of patient timelines using electronic health records: a retrospective modelling study.

BACKGROUND: An electronic health record (EHR) holds detailed longitudinal information about a patient's health status and general clinical history, a large portion of which is stored as unstructured, free text. Existing approaches to model a patient's trajectory focus mostly on structured data and a subset of single-domain outcomes. This study aims to evaluate the effectiveness of Foresight, a generative transformer in temporal modelling of patient data, integrating both free text and structured formats, to predict a diverse array of future medical outcomes, such as disorders, substances (eg, to do with medicines, allergies, or poisonings), procedures, and findings (eg, relating to observations, judgements, or assessments). METHODS: Foresight is a novel transformer-based pipeline that uses named entity recognition and linking tools to convert EHR document text into structured, coded concepts, followed by providing probabilistic forecasts for future medical events, such as disorders, substances, procedures, and findings. The Foresight pipeline has four main components: (1) CogStack (data retrieval and preprocessing); (2) the Medical Concept Annotation Toolkit (structuring of the free-text information from EHRs); (3) Foresight Core (deep-learning model for biomedical concept modelling); and (4) the Foresight web application. We processed the entire free-text portion from three different hospital datasets (King's College Hospital [KCH], South London and Maudsley [SLaM], and the US Medical Information Mart for Intensive Care III [MIMIC-III]), resulting in information from 811 336 patients and covering both physical and mental health institutions. We measured the performance of models using custom metrics derived from precision and recall. FINDINGS: Foresight achieved a precision@10 (ie, of 10 forecasted candidates, at least one is correct) of 0·68 (SD 0·0027) for the KCH dataset, 0·76 (0·0032) for the SLaM dataset, and 0·88 (0·0018) for the MIMIC-III dataset, for forecasting the next new disorder in a patient timeline. Foresight also achieved a precision@10 value of 0·80 (0·0013) for the KCH dataset, 0·81 (0·0026) for the SLaM dataset, and 0·91 (0·0011) for the MIMIC-III dataset, for forecasting the next new biomedical concept. In addition, Foresight was validated on 34 synthetic patient timelines by five clinicians and achieved a relevancy of 33 (97% [95% CI 91-100]) of 34 for the top forecasted candidate disorder. As a generative model, Foresight can forecast follow-on biomedical concepts for as many steps as required. INTERPRETATION: Foresight is a general-purpose model for biomedical concept modelling that can be used for real-world risk forecasting, virtual trials, and clinical research to study the progression of disorders, to simulate interventions and counterfactuals, and for educational purposes. FUNDING: National Health Service Artificial Intelligence Laboratory, National Institute for Health and Care Research Biomedical Research Centre, and Health Data Research UK.

Identifying depression-related topics in smartphone-collected free-response speech recordings using an automatic speech recognition system and a deep learning topic model.

BACKGROUND: Prior research has associated spoken language use with depression, yet studies often involve small or non-clinical samples and face challenges in the manual transcription of speech. This paper aimed to automatically identify depression-related topics in speech recordings collected from clinical samples. METHODS: The data included 3919 English free-response speech recordings collected via smartphones from 265 participants with a depression history. We transcribed speech recordings via automatic speech recognition (Whisper tool, OpenAI) and identified principal topics from transcriptions using a deep learning topic model (BERTopic). To identify depression risk topics and understand the context, we compared participants' depression severity and behavioral (extracted from wearable devices) and linguistic (extracted from transcribed texts) characteristics across identified topics. RESULTS: From the 29 topics identified, we identified 6 risk topics for depression: 'No Expectations', 'Sleep', 'Mental Therapy', 'Haircut', 'Studying', and 'Coursework'. Participants mentioning depression risk topics exhibited higher sleep variability, later sleep onset, and fewer daily steps and used fewer words, more negative language, and fewer leisure-related words in their speech recordings. LIMITATIONS: Our findings were derived from a depressed cohort with a specific speech task, potentially limiting the generalizability to non-clinical populations or other speech tasks. Additionally, some topics had small sample sizes, necessitating further validation in larger datasets. CONCLUSION: This study demonstrates that specific speech topics can indicate depression severity. The employed data-driven workflow provides a practical approach for analyzing large-scale speech data collected from real-world settings.

Discovery of a Photoaffinity Probe that Captures the Active Conformation of the Cannabinoid CB2 Receptor.

The cannabinoid receptor type 2 (CB2R) is a G protein-coupled receptor with therapeutic potential for the treatment of inflammatory disorders. Fluorescent probes are desirable to study its receptor localization, expression and occupancy. Previously, we have reported a photoaffinity probe LEI-121 that stabilized the inactive conformation of the CB2R. Here, we report the structure-based design of a novel bifunctional probe that captures the active conformation of the CB2R upon irradiation with light. An alkyne handle was incorporated to visualize the receptor using click-chemistry with fluorophore-azides. These probes may hold promise to study different receptor conformations in relation to their cellular localization and function.

Hospital learning curves for robot-assisted surgeries: a population-based analysis.

BACKGROUND: Robot-assisted surgery has been rapidly adopted. It is important to define the learning curve to inform credentialling requirements, training programs, identify fast and slow learners, and protect patients. This study aimed to characterize the hospital learning curve for common robot-assisted procedures. STUDY DESIGN: This cohort study, using administrative health data for Ontario, Canada, included adult patients who underwent a robot-assisted radical prostatectomy (RARP), total robotic hysterectomy (TRH), robot-assisted partial nephrectomy (RAPN), or robotic portal lobectomy using four arms (RPL-4) between 2010 and 2021. The association between cumulative hospital volume of a robot-assisted procedure and major complications was evaluated using multivariable logistic models adjusted for patient characteristics and clustering at the hospital level. RESULTS: A total of 6814 patients were included, with 5230, 543, 465, and 576 patients in the RARP, TRH, RAPN, and RPL-4 cohorts, respectively. There was no association between cumulative hospital volume and major complications. Visual inspection of learning curves demonstrated a transient worsening of outcomes followed by subsequent improvements with experience. Operative time decreased for all procedures with increasing volume and reached plateaus after approximately 300 RARPs, 75 TRHs, and 150 RPL-4s. The odds of a prolonged length of stay decreased with increasing volume for patients undergoing a RARP (OR 0.87; 95% CI 0.82-0.92) or RPL-4 (OR 0.77; 95% CI 0.68-0.87). CONCLUSION: Hospitals may adopt robot-assisted surgery without significantly increasing the risk of major complications for patients early in the learning curve and with an expectation of increasing efficiency.

Anal Cancers in Previously Screened Versus Unscreened Patients: Tumor Stage and Treatment Outcomes.

BACKGROUND: Targeted screening programs for patients at high risk for anal squamous-cell carcinoma have been proposed; however, the evidence in support of screening remains unclear. OBJECTIVE: This study aimed to determine whether screening high-risk patients (predominantly those living with HIV) detected squamous-cell carcinoma at an earlier stage compared to the routine practice of not screening. DESIGN: This is a cohort study. SETTINGS: This study was conducted at a quaternary care center in Canada. PATIENTS: Included patients were at least 18 years old with a pathologic diagnosis of invasive anal squamous-cell carcinoma between 2002 and 2022. INTERVENTIONS: Patients diagnosed through a high-risk screening program were compared to those who did not undergo screening. MAIN OUTCOME MEASURES: The primary outcome was clinical stage at presentation, categorized as T1N0M0 vs other. Secondary outcomes included treatments received, treatment failure, and overall survival. RESULTS: A total of 612 patients with anal squamous-cell carcinoma were included, with 26 of those patients diagnosed through a screening program. Patients with screen-detected cancers had greater odds of presenting with T1N0M0 tumors compared to unscreened patients (18 [69.2%] vs 84 [14.3%]; adjusted OR 9.95; 95% CI, 3.95-25.08). A propensity score-matched sensitivity analysis found similar results (OR 11.13; 95% CI, 4.67-26.52). Screened patients had greater odds of treatment with wide local excision alone, as opposed to any combination of chemotherapy, radiation therapy, and surgery (3 [12.5%] vs 18 [3.2%]; OR 4.38; 95% CI, 1.20-16.04). There were no statistically significant differences in treatment failure or overall survival between groups. LIMITATIONS: The small number of screened patients limits the power of the analysis. CONCLUSIONS: Screening for anal squamous-cell carcinoma among high-risk populations detects cancers at an earlier stage. Patients with screen-detected cancers also had a greater likelihood of being candidates for wide local excision alone, which may have spared them the morbidity associated with chemoradiotherapy or abdominoperineal resection. See Video Abstract. CNCERES DE ANO EN PACIENTES PREVIAMENTE DETECTADOS POR CRIBADO VERSUS NO DETECTADOS ESTADIO DEL TUMOR Y RESULTADOS DEL TRATAMIENTO: ANTECEDENTES:Se han propuesto programas de cribado dirigidos a pacientes con alto riesgo de carcinoma anal de células escamosas; sin embargo, la evidencia a favor de la detección sigue sin estar clara.OBJETIVO:Este estudio tuvo como objetivo determinar si el cribado de pacientes de alto riesgo (predominantemente aquellos que viven con el VIH) detectó el carcinoma de células escamosas en una etapa más temprana en comparación con la práctica habitual de no cribado.DISEÑO:Este es un estudio de cohortes.CONFIGURACIÓN:Este estudio se realizó en un centro de atención cuaternaria en Canadá.PACIENTES:Los pacientes incluidos tenían al menos 18 años con un diagnóstico patológico de carcinoma de células escamosas anal invasivo entre 2002 y 2022.INTERVENCIONES:Los pacientes diagnosticados mediante un programa de cribado de alto riesgo se compararon con aquellos que no se sometieron a cribado.PRINCIPALES MEDIDAS DE RESULTADO:El resultado primario fue el estadio clínico en la presentación, categorizado como T1N0M0 versus otro. Los resultados secundarios incluyeron los tratamientos recibidos, el fracaso del tratamiento y la supervivencia general.RESULTADOS:Se incluyeron un total de 612 pacientes con carcinoma anal de células escamosas, con 26 de esos pacientes diagnosticados a través de un programa de cribado. Los pacientes con cánceres detectados mediante cribado tenían mayores probabilidades de presentar tumores T1N0M0 en comparación con los pacientes no cribados (18 [69.2%] frente a 84 [14.3%]; razón de probabilidad ajustada 9.95; intervalo de confianza del 95 % 3.95 -25.08). Un análisis de sensibilidad emparejado por puntaje de propensión encontró resultados similares (odds ratio 11.13; intervalo de confianza del 95% 4.67 -26.52; p < 0.001). Los pacientes examinados tenían mayores probabilidades de recibir tratamiento con escisión local amplia sola, en comparación con cualquier combinación de quimioterapia, radiación y cirugía (3 [12.5%] frente a 18 [3.2%]; razón de probabilidad 4.38; intervalo de confianza del 95 % 1.20 -16.04). No hubo diferencias estadísticamente significativas en el fracaso del tratamiento o la supervivencia global entre los grupos.LIMITACIONES:El pequeño número de pacientes evaluados limita el poder del análisis.CONCLUSIONES:La detección del carcinoma anal de células escamosas entre las poblaciones de alto riesgo detecta los cánceres en una etapa más temprana. Los pacientes con cánceres detectados mediante cribado también tenían una mayor probabilidad de ser candidatos para una escisión local amplia sola, lo que puede haberles evitado la morbilidad asociada con la quimiorradioterapia o la resección abdominoperineal. (Traducción --Dr. Aurian Garcia Gonzalez ).

Autonomous and non-cell autonomous role of cilia in structural birth defects in mice.

Ciliopathies are associated with wide spectrum of structural birth defects (SBDs), indicating important roles for cilia in development. Here, we provide novel insights into the temporospatial requirement for cilia in SBDs arising from deficiency in Ift140, an intraflagellar transport (IFT) protein regulating ciliogenesis. Ift140-deficient mice exhibit cilia defects accompanied by wide spectrum of SBDs including macrostomia (craniofacial defects), exencephaly, body wall defects, tracheoesophageal fistula (TEF), randomized heart looping, congenital heart defects (CHDs), lung hypoplasia, renal anomalies, and polydactyly. Tamoxifen inducible CAGGCre-ER deletion of a floxed Ift140 allele between E5.5 to 9.5 revealed early requirement for Ift140 in left-right heart looping regulation, mid to late requirement for cardiac outflow septation and alignment, and late requirement for craniofacial development and body wall closure. Surprisingly, CHD were not observed with 4 Cre drivers targeting different lineages essential for heart development, but craniofacial defects and omphalocele were observed with Wnt1-Cre targeting neural crest and Tbx18-Cre targeting epicardial lineage and rostral sclerotome through which trunk neural crest cells migrate. These findings revealed cell autonomous role of cilia in cranial/trunk neural crest-mediated craniofacial and body wall closure defects, while non-cell autonomous multi-lineage interactions underlie CHD pathogenesis, revealing unexpected developmental complexity for CHD associated with ciliopathies.

A monoacylglycerol lipase inhibitor showing therapeutic efficacy in mice without central side effects or dependence.

Monoacylglycerol lipase (MAGL) regulates endocannabinoid 2-arachidonoylglycerol (2-AG) and eicosanoid signalling. MAGL inhibition provides therapeutic opportunities but clinical potential is limited by central nervous system (CNS)-mediated side effects. Here, we report the discovery of LEI-515, a peripherally restricted, reversible MAGL inhibitor, using high throughput screening and a medicinal chemistry programme. LEI-515 increased 2-AG levels in peripheral organs, but not mouse brain. LEI-515 attenuated liver necrosis, oxidative stress and inflammation in a CCl4-induced acute liver injury model. LEI-515 suppressed chemotherapy-induced neuropathic nociception in mice without inducing cardinal signs of CB1 activation. Antinociceptive efficacy of LEI-515 was blocked by CB2, but not CB1, antagonists. The CB1 antagonist rimonabant precipitated signs of physical dependence in mice treated chronically with a global MAGL inhibitor (JZL184), and an orthosteric cannabinoid agonist (WIN55,212-2), but not with LEI-515. Our data support targeting peripheral MAGL as a promising therapeutic strategy for developing safe and effective anti-inflammatory and analgesic agents.

Multivariate GWAS of Alzheimer's disease CSF biomarker profiles implies GRIN2D in synaptic functioning.

BACKGROUND: Genome-wide association studies (GWAS) of Alzheimer's disease (AD) have identified several risk loci, but many remain unknown. Cerebrospinal fluid (CSF) biomarkers may aid in gene discovery and we previously demonstrated that six CSF biomarkers (ß-amyloid, total/phosphorylated tau, NfL, YKL-40, and neurogranin) cluster into five principal components (PC), each representing statistically independent biological processes. Here, we aimed to (1) identify common genetic variants associated with these CSF profiles, (2) assess the role of associated variants in AD pathophysiology, and (3) explore potential sex differences. METHODS: We performed GWAS for each of the five biomarker PCs in two multi-center studies (EMIF-AD and ADNI). In total, 973 participants (n = 205 controls, n = 546 mild cognitive impairment, n = 222 AD) were analyzed for 7,433,949 common SNPs and 19,511 protein-coding genes. Structural equation models tested whether biomarker PCs mediate genetic risk effects on AD, and stratified and interaction models probed for sex-specific effects. RESULTS: Five loci showed genome-wide significant association with CSF profiles, two were novel (rs145791381 [inflammation] and GRIN2D [synaptic functioning]) and three were previously described (APOE, TMEM106B, and CHI3L1). Follow-up analyses of the two novel signals in independent datasets only supported the GRIN2D locus, which contains several functionally interesting candidate genes. Mediation tests indicated that variants in APOE are associated with AD status via processes related to amyloid and tau pathology, while markers in TMEM106B and CHI3L1 are associated with AD only via neuronal injury/inflammation. Additionally, seven loci showed sex-specific associations with AD biomarkers. CONCLUSIONS: These results suggest that pathway and sex-specific analyses can improve our understanding of AD genetics and may contribute to precision medicine.

Multilingual markers of depression in remotely collected speech samples: A preliminary analysis.

BACKGROUND: Speech contains neuromuscular, physiological and cognitive components, and so is a potential biomarker of mental disorders. Previous studies indicate that speaking rate and pausing are associated with major depressive disorder (MDD). However, results are inconclusive as many studies are small and underpowered and do not include clinical samples. These studies have also been unilingual and use speech collected in controlled settings. If speech markers are to help understand the onset and progress of MDD, we need to uncover markers that are robust to language and establish the strength of associations in real-world data. METHODS: We collected speech data in 585 participants with a history of MDD in the United Kingdom, Spain, and Netherlands as part of the RADAR-MDD study. Participants recorded their speech via smartphones every two weeks for 18 months. Linear mixed models were used to estimate the strength of specific markers of depression from a set of 28 speech features. RESULTS: Increased depressive symptoms were associated with speech rate, articulation rate and intensity of speech elicited from a scripted task. These features had consistently stronger effect sizes than pauses. LIMITATIONS: Our findings are derived at the cohort level so may have limited impact on identifying intra-individual speech changes associated with changes in symptom severity. The analysis of features averaged over the entire recording may have underestimated the importance of some features. CONCLUSIONS: Participants with more severe depressive symptoms spoke more slowly and quietly. Our findings are from a real-world, multilingual, clinical dataset so represent a step-change in the usefulness of speech as a digital phenotype of MDD.

Challenges in Using mHealth Data From Smartphones and Wearable Devices to Predict Depression Symptom Severity: Retrospective Analysis.

BACKGROUND: Major depressive disorder (MDD) affects millions of people worldwide, but timely treatment is not often received owing in part to inaccurate subjective recall and variability in the symptom course. Objective and frequent MDD monitoring can improve subjective recall and help to guide treatment selection. Attempts have been made, with varying degrees of success, to explore the relationship between the measures of depression and passive digital phenotypes (features) extracted from smartphones and wearables devices to remotely and continuously monitor changes in symptomatology. However, a number of challenges exist for the analysis of these data. These include maintaining participant engagement over extended time periods and therefore understanding what constitutes an acceptable threshold of missing data; distinguishing between the cross-sectional and longitudinal relationships for different features to determine their utility in tracking within-individual longitudinal variation or screening individuals at high risk; and understanding the heterogeneity with which depression manifests itself in behavioral patterns quantified by the passive features. OBJECTIVE: We aimed to address these 3 challenges to inform future work in stratified analyses. METHODS: Using smartphone and wearable data collected from 479 participants with MDD, we extracted 21 features capturing mobility, sleep, and smartphone use. We investigated the impact of the number of days of available data on feature quality using the intraclass correlation coefficient and Bland-Altman analysis. We then examined the nature of the correlation between the 8-item Patient Health Questionnaire (PHQ-8) depression scale (measured every 14 days) and the features using the individual-mean correlation, repeated measures correlation, and linear mixed effects model. Furthermore, we stratified the participants based on their behavioral difference, quantified by the features, between periods of high (depression) and low (no depression) PHQ-8 scores using the Gaussian mixture model. RESULTS: We demonstrated that at least 8 (range 2-12) days were needed for reliable calculation of most of the features in the 14-day time window. We observed that features such as sleep onset time correlated better with PHQ-8 scores cross-sectionally than longitudinally, whereas features such as wakefulness after sleep onset correlated well with PHQ-8 longitudinally but worse cross-sectionally. Finally, we found that participants could be separated into 3 distinct clusters according to their behavioral difference between periods of depression and periods of no depression. CONCLUSIONS: This work contributes to our understanding of how these mobile health-derived features are associated with depression symptom severity to inform future work in stratified analyses.

Automatic Assessment of the 2-Minute Walk Distance for Remote Monitoring of People with Multiple Sclerosis.

The aim of this study was to investigate the feasibility of automatically assessing the 2-Minute Walk Distance (2MWD) for monitoring people with multiple sclerosis (pwMS). For 154 pwMS, MS-related clinical outcomes as well as the 2MWDs as evaluated by clinicians and derived from accelerometer data were collected from a total of 323 periodic clinical visits. Accelerometer data from a wearable device during 100 home-based 2MWD assessments were also acquired. The error in estimating the 2MWD was validated for walk tests performed at hospital, and then the correlation (r) between clinical outcomes and home-based 2MWD assessments was evaluated. Robust performance in estimating the 2MWD from the wearable device was obtained, yielding an error of less than 10% in about two-thirds of clinical visits. Correlation analysis showed that there is a strong association between the actual and the estimated 2MWD obtained either at hospital (r = 0.71) or at home (r = 0.58). Furthermore, the estimated 2MWD exhibits moderate-to-strong correlation with various MS-related clinical outcomes, including disability and fatigue severity scores. Automatic assessment of the 2MWD in pwMS is feasible with the usage of a consumer-friendly wearable device in clinical and non-clinical settings. Wearable devices can also enhance the assessment of MS-related clinical outcomes.

Remote Administration of ADHD-Sensitive Cognitive Tasks: A Pilot Study.

OBJECTIVE: We assessed the feasibility and validity of remote researcher-led administration and self-administration of modified versions of two cognitive tasks sensitive to ADHD, a four-choice reaction time task (Fast task) and a combined Continuous Performance Test/Go No-Go task (CPT/GNG), through a new remote measurement technology system. METHOD: We compared the cognitive performance measures (mean and variability of reaction times (MRT, RTV), omission errors (OE) and commission errors (CE)) at a remote baseline researcher-led administration and three remote self-administration sessions between participants with and without ADHD (n = 40). RESULTS: The most consistent group differences were found for RTV, MRT and CE at the baseline researcher-led administration and the first self-administration, with 8 of the 10 comparisons statistically significant and all comparisons indicating medium to large effect sizes. CONCLUSION: Remote administration of cognitive tasks successfully captured the difficulties with response inhibition and regulation of attention, supporting the feasibility and validity of remote assessments.

Hospital-wide natural language processing summarising the health data of 1 million patients.

Electronic health records (EHRs) represent a major repository of real world clinical trajectories, interventions and outcomes. While modern enterprise EHR's try to capture data in structured standardised formats, a significant bulk of the available information captured in the EHR is still recorded only in unstructured text format and can only be transformed into structured codes by manual processes. Recently, Natural Language Processing (NLP) algorithms have reached a level of performance suitable for large scale and accurate information extraction from clinical text. Here we describe the application of open-source named-entity-recognition and linkage (NER+L) methods (CogStack, MedCAT) to the entire text content of a large UK hospital trust (King's College Hospital, London). The resulting dataset contains 157M SNOMED concepts generated from 9.5M documents for 1.07M patients over a period of 9 years. We present a summary of prevalence and disease onset as well as a patient embedding that captures major comorbidity patterns at scale. NLP has the potential to transform the health data lifecycle, through large-scale automation of a traditionally manual task.

Discharge summary hospital course summarisation of in patient Electronic Health Record text with clinical concept guided deep pre-trained Transformer models.

Brief Hospital Course (BHC) summaries are succinct summaries of an entire hospital encounter, embedded within discharge summaries, written by senior clinicians responsible for the overall care of a patient. Methods to automatically produce summaries from inpatient documentation would be invaluable in reducing clinician manual burden of summarising documents under high time-pressure to admit and discharge patients. Automatically producing these summaries from the inpatient course, is a complex, multi-document summarisation task, as source notes are written from various perspectives (e.g. nursing, doctor, radiology), during the course of the hospitalisation. We demonstrate a range of methods for BHC summarisation demonstrating the performance of deep learning summarisation models across extractive and abstractive summarisation scenarios. We also test a novel ensemble extractive and abstractive summarisation model that incorporates a medical concept ontology (SNOMED) as a clinical guidance signal and shows superior performance in 2 real-world clinical data sets.