Mutations in the tail and rod domains of the neurofilament heavy-chain gene increase the risk of ALS.

OBJECTIVE: Neurofilament heavy-chain gene (NEFH) variants are associated with multiple neurodegenerative diseases, however, their relationship with ALS has not been robustly explored. Still, NEFH is commonly included in genetic screening panels worldwide. We therefore aimed to determine if NEFH variants modify ALS risk. METHODS: Genetic data of 11,130 people with ALS and 7,416 controls from the literature and Project MinE were analysed. We performed meta-analyses of published case-control studies reporting NEFH variants, and variant analysis of NEFH in Project MinE whole-genome sequencing data. RESULTS: Fixed-effects meta-analysis found that rare (MAF <1%) missense variants in the tail domain of NEFH increase ALS risk (OR 4.55, 95% CI 2.13-9.71, p < 0.0001). In Project MinE, ultrarare NEFH variants increased ALS risk (OR 1.37 95% CI 1.14-1.63, p = 0.0007), with rod domain variants (mostly intronic) appearing to drive the association (OR 1.45 95% CI 1.18-1.77, pMadsen-Browning = 0.0007, pSKAT-O = 0.003). While in the tail domain, ultrarare (MAF <0.1%) pathogenic missense variants were also associated with higher risk of ALS (OR 1.94, 95% CI 0.86-4.37, pMadsen-Browning = 0.039), supporting the meta-analysis results. Finally, several tail in-frame deletions were also found to affect disease risk, however, both protective and pathogenic deletions were found in this domain, highlighting an intricated architecture that requires further investigation. INTERPRETATION: We showed that NEFH tail missense and in-frame deletion variants, and intronic rod variants are risk factors for ALS. However, they are not variants of large effect, and their functional impact needs to be clarified in further studies. Therefore, their inclusion in routine genetic screening panels should be reconsidered.

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.

Characterising illness stages and recovery trajectories of eating disorders in young people via remote measurement technology (STORY): a multi-centre prospective cohort study protocol.

BACKGROUND: Eating disorders (EDs) are serious, often chronic, conditions associated with pronounced morbidity, mortality, and dysfunction increasingly affecting young people worldwide. Illness progression, stages and recovery trajectories of EDs are still poorly characterised. The STORY study dynamically and longitudinally assesses young people with different EDs (restricting; bingeing/bulimic presentations) and illness durations (earlier; later stages) compared to healthy controls. Remote measurement technology (RMT) with active and passive sensing is used to advance understanding of the heterogeneity of earlier and more progressed clinical presentations and predictors of recovery or relapse. METHODS: STORY follows 720 young people aged 16-25 with EDs and 120 healthy controls for 12 months. Online self-report questionnaires regularly assess ED symptoms, psychiatric comorbidities, quality of life, and socioeconomic environment. Additional ongoing monitoring using multi-parametric RMT via smartphones and wearable smart rings ('Oura ring') unobtrusively measures individuals' daily behaviour and physiology (e.g., Bluetooth connections, sleep, autonomic arousal). A subgroup of participants completes additional in-person cognitive and neuroimaging assessments at study-baseline and after 12 months. DISCUSSION: By leveraging these large-scale longitudinal data from participants across ED diagnoses and illness durations, the STORY study seeks to elucidate potential biopsychosocial predictors of outcome, their interplay with developmental and socioemotional changes, and barriers and facilitators of recovery. STORY holds the promise of providing actionable findings that can be translated into clinical practice by informing the development of both early intervention and personalised treatment that is tailored to illness stage and individual circumstances, ultimately disrupting the long-term burden of EDs on individuals and their families.

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.

Predicting Future Disorders via Temporal Knowledge Graphs and Medical Ontologies.

Despite the vast potential for insights and value present in Electronic Health Records (EHRs), it is challenging to fully leverage all the available information, particularly that contained in the free-text data written by clinicians describing the health status of patients. The utilization of Named Entity Recognition and Linking tools allows not only for the structuring of information contained within free-text data, but also for the integration with medical ontologies, which may prove highly beneficial for the analysis of patient medical histories with the aim of forecasting future medical outcomes, such as the diagnosis of a new disorder. In this paper, we propose MedTKG, a Temporal Knowledge Graph (TKG) framework that incorporates both the dynamic information of patient clinical histories and the static information of medical ontologies. The TKG is used to model a medical history as a series of snapshots at different points in time, effectively capturing the dynamic nature of the patient's health status, while a static graph is used to model the hierarchies of concepts extracted from domain ontologies. The proposed method aims to predict future disorders by identifying missing objects in the quadruple 〈s, r, ?, t 〉, where s and r denote the patient and the disorder relation type, respectively, and t is the timestamp of the query. The method is evaluated on clinical notes extracted from MIMIC-III and demonstrates the effectiveness of the TKG framework in predicting future disorders and of medical ontologies in improving its performance.

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.

A wearable device perspective on the standard definitions of disability progression in multiple sclerosis.

INTRODUCTION: Multiple sclerosis (MS) is a leading cause of disability among young adults, but standard clinical scales may not accurately detect subtle changes in disability occurring between visits. This study aims to explore whether wearable device data provides more granular and objective measures of disability progression in MS. METHODS: Remote Assessment of Disease and Relapse in Central Nervous System Disorders (RADAR-CNS) is a longitudinal multicenter observational study in which 400 MS patients have been recruited since June 2018 and prospectively followed up for 24 months. Monitoring of patients included standard clinical visits with assessment of disability through use of the Expanded Disability Status Scale (EDSS), 6-minute walking test (6MWT) and timed 25-foot walk (T25FW), as well as remote monitoring through the use of a Fitbit. RESULTS: Among the 306 patients who completed the study (mean age, 45.6 years; females 67%), confirmed disability progression defined by the EDSS was observed in 74 patients, who had approximately 1392 fewer daily steps than patients without disability progression. However, the decrease in the number of steps experienced over time by patients with EDSS progression and stable patients was not significantly different. Similar results were obtained with disability progression defined by the 6MWT and the T25FW. CONCLUSION: The use of continuous activity monitoring holds great promise as a sensitive and ecologically valid measure of disability progression in MS.

Artificial intelligence methods for improved detection of undiagnosed heart failure with preserved ejection fraction.

AIM: Heart failure with preserved ejection fraction (HFpEF) remains under-diagnosed in clinical practice despite accounting for nearly half of all heart failure (HF) cases. Accurate and timely diagnosis of HFpEF is crucial for proper patient management and treatment. In this study, we explored the potential of natural language processing (NLP) to improve the detection and diagnosis of HFpEF according to the European Society of Cardiology (ESC) diagnostic criteria. METHODS AND RESULTS: In a retrospective cohort study, we used an NLP pipeline applied to the electronic health record (EHR) to identify patients with a clinical diagnosis of HF between 2010 and 2022. We collected demographic, clinical, echocardiographic and outcome data from the EHR. Patients were categorized according to the left ventricular ejection fraction (LVEF). Those with LVEF ≥50% were further categorized based on whether they had a clinician-assigned diagnosis of HFpEF and if not, whether they met the ESC diagnostic criteria. Results were validated in a second, independent centre. We identified 8606 patients with HF. Of 3727 consecutive patients with HF and LVEF ≥50% on echocardiogram, only 8.3% had a clinician-assigned diagnosis of HFpEF, while 75.4% met ESC criteria but did not have a formal diagnosis of HFpEF. Patients with confirmed HFpEF were hospitalized more frequently; however the ESC criteria group had a higher 5-year mortality, despite being less comorbid and experiencing fewer acute cardiovascular events. CONCLUSIONS: This study demonstrates that patients with undiagnosed HFpEF are an at-risk group with high mortality. It is possible to use NLP methods to identify likely HFpEF patients from EHR data who would likely then benefit from expert clinical review and complement the use of diagnostic algorithms.

Unsupervised machine learning identifies distinct ALS molecular subtypes in post-mortem motor cortex and blood expression data.

Amyotrophic lateral sclerosis (ALS) displays considerable clinical and genetic heterogeneity. Machine learning approaches have previously been utilised for patient stratification in ALS as they can disentangle complex disease landscapes. However, lack of independent validation in different populations and tissue samples have greatly limited their use in clinical and research settings. We overcame these issues by performing hierarchical clustering on the 5000 most variably expressed autosomal genes from motor cortex expression data of people with sporadic ALS from the KCL BrainBank (N = 112). Three molecular phenotypes linked to ALS pathogenesis were identified: synaptic and neuropeptide signalling, oxidative stress and apoptosis, and neuroinflammation. Cluster validation was achieved by applying linear discriminant analysis models to cases from TargetALS US motor cortex (N = 93), as well as Italian (N = 15) and Dutch (N = 397) blood expression datasets, for which there was a high assignment probability (80-90%) for each molecular subtype. The ALS and motor cortex specificity of the expression signatures were tested by mapping KCL BrainBank controls (N = 59), and occipital cortex (N = 45) and cerebellum (N = 123) samples from TargetALS to each cluster, before constructing case-control and motor cortex-region logistic regression classifiers. We found that the signatures were not only able to distinguish people with ALS from controls (AUC 0.88 ± 0.10), but also reflect the motor cortex-based disease process, as there was perfect discrimination between motor cortex and the other brain regions. Cell types known to be involved in the biological processes of each molecular phenotype were found in higher proportions, reinforcing their biological interpretation. Phenotype analysis revealed distinct cluster-related outcomes in both motor cortex datasets, relating to disease onset and progression-related measures. Our results support the hypothesis that different mechanisms underpin ALS pathogenesis in subgroups of patients and demonstrate potential for the development of personalised treatment approaches. Our method is available for the scientific and clinical community at https://alsgeclustering.er.kcl.ac.uk .

Evaluating a Remote Monitoring Program for Respiratory Diseases: Prospective Observational Study.

BACKGROUND: Patients with chronic respiratory diseases and those in the postdischarge period following hospitalization because of COVID-19 are particularly vulnerable, and little is known about the changes in their symptoms and physiological parameters. Continuous remote monitoring of physiological parameters and symptom changes offers the potential for timely intervention, improved patient outcomes, and reduced health care costs. OBJECTIVE: This study investigated whether a real-time multimodal program using commercially available wearable technology, home-based Bluetooth-enabled spirometers, finger pulse oximeters, and smartphone apps is feasible and acceptable for patients with chronic respiratory diseases, as well as the value of low-burden, long-term passive data collection. METHODS: In a 3-arm prospective observational cohort feasibility study, we recruited 60 patients from the Royal Free Hospital and University College Hospital. These patients had been diagnosed with interstitial lung disease, chronic obstructive pulmonary disease, or post-COVID-19 condition (n=20 per group) and were followed for 180 days. This study used a comprehensive remote monitoring system designed to provide real-time and relevant data for both patients and clinicians. Data were collected using REDCap (Research Electronic Data Capture; Vanderbilt University) periodic surveys, Remote Assessment of Disease and Relapses-base active app questionnaires, wearables, finger pulse oximeters, smartphone apps, and Bluetooth home-based spirometry. The feasibility of remote monitoring was measured through adherence to the protocol, engagement during the follow-up period, retention rate, acceptability, and data integrity. RESULTS: Lowest-burden passive data collection methods, via wearables, demonstrated superior adherence, engagement, and retention compared with active data collection methods, with an average wearable use of 18.66 (SD 4.69) hours daily (77.8% of the day), 123.91 (SD 33.73) hours weekly (72.6% of the week), and 463.82 (SD 156.70) hours monthly (64.4% of the month). Highest-burden spirometry tasks and high-burden active app tasks had the lowest adherence, engagement, and retention, followed by low-burden questionnaires. Spirometry and active questionnaires had the lowest retention at 0.5 survival probability, indicating that they were the most burdensome. Adherence to and quality of home spirometry were analyzed; of the 7200 sessions requested, 4248 (59%) were performed. Of these, 90.3% (3836/4248) were of acceptable quality according to American Thoracic Society grading. Inclusion of protocol holidays improved retention measures. The technologies used were generally well received. CONCLUSIONS: Our findings provide evidence supporting the feasibility and acceptability of remote monitoring for capturing both subjective and objective data from various sources for respiratory diseases. The high engagement level observed with passively collected data suggests the potential of wearables for long-term, user-friendly remote monitoring in respiratory disease management. The unique piloting of certain features such as protocol holidays, alert notifications for missing data, and flexible support from the study team provides a reference for future studies in this field. INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID): RR2-10.2196/28873.

Molecular dynamics analysis of superoxide dismutase 1 mutations suggests decoupling between mechanisms underlying ALS onset and progression.

Mutations in the superoxide dismutase 1 (SOD1) gene are the second most common known cause of ALS. SOD1 variants express high phenotypic variability and over 200 have been reported in people with ALS. It was previously proposed that variants can be broadly classified in two groups, 'wild-type like' (WTL) and 'metal binding region' (MBR) variants, based on their structural location and biophysical properties. MBR variants, but not WTL variants, were associated with a reduction of SOD1 enzymatic activity. In this study we used molecular dynamics and large clinical datasets to characterise the differences in the structural and dynamic behaviour of WTL and MBR variants with respect to the wild-type SOD1, and how such differences influence the ALS clinical phenotype. Our study identified marked structural differences, some of which are observed in both variant groups, while others are group specific. Moreover, collecting clinical data of approximately 500 SOD1 ALS patients carrying variants, we showed that the survival time of patients carrying an MBR variant is generally longer (∼6 years median difference, p < 0.001) with respect to patients with a WTL variant. In conclusion, our study highlighted key differences in the dynamic behaviour between WTL and MBR SOD1 variants, and between variants and wild-type SOD1 at an atomic and molecular level, that could be further investigated to explain the associated phenotypic variability. Our results support the hypothesis of a decoupling between mechanisms of onset and progression of SOD1 ALS, and an involvement of loss-of-function of SOD1 with the disease progression.

Moving from development to implementation of digital innovations within the NHS: myHealthE, a remote monitoring system for tracking patient outcomes in child and adolescent mental health services.

Objective: This paper aims to report our experience of developing, implementing, and evaluating myHealthE (MHE), a digital innovation for Child and Adolescents Mental Health Services (CAMHS), which automates the remote collection and reporting of Patient-Reported Outcome Measures (PROMs) into National Health Services (NHS) electronic healthcare records. Methods: We describe the logistical and governance issues encountered in developing the MHE interface with patient-identifiable information, and the steps taken to overcome these development barriers. We describe the application's architecture and hosting environment to enable its operability within the NHS, as well as the capabilities needed within the technical team to bridge the gap between academic development and NHS operational teams. Results: We present evidence on the feasibility and acceptability of this system within clinical services and the process of iterative development, highlighting additional functions that were incorporated to increase system utility. Conclusion: This article provides a framework with which to plan, develop, and implement automated PROM collection from remote devices back to NHS infrastructure. The challenges and solutions described in this paper will be pertinent to other digital health innovation researchers aspiring to deploy interoperable systems within NHS clinical systems.

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.

Trustworthy Data and AI Environments for Clinical Prediction: Application to Crisis-Risk in People With Depression.

Depression is a common mental health condition that often occurs in association with other chronic illnesses, and varies considerably in severity. Electronic Health Records (EHRs) contain rich information about a patient's medical history and can be used to train, test and maintain predictive models to support and improve patient care. This work evaluated the feasibility of implementing an environment for predicting mental health crisis among people living with depression based on both structured and unstructured EHRs. A large EHR from a mental health provider, Mersey Care, was pseudonymised and ingested into the Natural Language Processing (NLP) platform CogStack, allowing text content in binary clinical notes to be extracted. All unstructured clinical notes and summaries were semantically annotated by MedCAT and BioYODIE NLP services. Cases of crisis in patients with depression were then identified. Random forest models, gradient boosting trees, and Long Short-Term Memory (LSTM) networks, with varying feature arrangement, were trained to predict the occurrence of crisis. The results showed that all the prediction models can use a combination of structured and unstructured EHR information to predict crisis in patients with depression with good and useful accuracy. The LSTM network that was trained on a modified dataset with only 1000 most-important features from the random forest model with temporality showed the best performance with a mean AUC of 0.901 and a standard deviation of 0.006 using a training dataset and a mean AUC of 0.810 and 0.01 using a hold-out test dataset. Comparing the results from the technical evaluation with the views of psychiatrists shows that there are now opportunities to refine and integrate such prediction models into pragmatic point-of-care clinical decision support tools for supporting mental healthcare delivery.

Unraveling ethnic disparities in antipsychotic prescribing among patients with psychosis: A retrospective cohort study based on electronic clinical records.

BACKGROUND: Previous studies have shown mixed evidence on ethnic disparities in antipsychotic prescribing among patients with psychosis in the UK, partly due to small sample sizes. This study aimed to examine the current state of antipsychotic prescription with respect to patient ethnicity among the entire population known to a large UK mental health trust with non-affective psychosis, adjusting for multiple potential risk factors. METHODS: This retrospective cohort study included all patients (N = 19,291) who were aged 18 years or over at their first diagnoses of non-affective psychosis (identified with the ICD-10 codes of F20-F29) recorded in electronic health records (EHRs) at the South London and Maudsley NHS Trust until March 2021. The most recently recorded antipsychotic treatments and patient attributes were extracted from EHRs, including both structured fields and free-text fields processed using natural language processing applications. Multivariable logistic regression models were used to calculate the odds ratios (OR) for antipsychotic prescription according to patient ethnicity, adjusted for multiple potential contributing factors, including demographic (age and gender), clinical (diagnoses, duration of illness, service use and history of cannabis use), socioeconomic factors (level of deprivation and own-group ethnic density in the area of residence) and temporal changes in clinical guidelines (date of prescription). RESULTS: The cohort consisted of 43.10 % White, 8.31 % Asian, 40.80 % Black, 2.64 % Mixed, and 5.14 % of patients from Other ethnicity. Among them, 92.62 % had recorded antipsychotic receipt, where 24.05 % for depot antipsychotics and 81.72 % for second-generation antipsychotic (SGA) medications. Most ethnic minority groups were not significantly different from White patients in receiving any antipsychotic. Among those receiving antipsychotic prescribing, Black patients were more likely to be prescribed depot (adjusted OR 1.29, 95 % confidence interval (CI) 1.14-1.47), but less likely to receive SGA (adjusted OR 0.85, 95 % CI 0.74-0.97), olanzapine (OR 0.82, 95 % CI 0.73-0.92) and clozapine (adjusted OR 0.71, 95 % CI 0.6-0.85) than White patients. All the ethnic minority groups were less likely to be prescribed olanzapine than the White group. CONCLUSIONS: Black patients with psychosis had a distinct pattern in antipsychotic prescription, with less use of SGA, including olanzapine and clozapine, but more use of depot antipsychotics, even when adjusting for the effects of multiple demographic, clinical and socioeconomic factors. Further research is required to understand the sources of these ethnic disparities and eliminate care inequalities.

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.

Terrain Characterization via Machine vs. Deep Learning Using Remote Sensing.

Terrain traversability is critical for developing Go/No-Go maps for ground vehicles, which significantly impact a mission's success. To predict the mobility of terrain, one must understand the soil characteristics. In-situ measurements performed in the field are the current method of collecting this information, which is time-consuming, costly, and can be lethal for military operations. This paper investigates an alternative approach using thermal, multispectral, and hyperspectral remote sensing from an unmanned aerial vehicle (UAV) platform. Remotely sensed data combined with machine learning (linear, ridge, lasso, partial least squares (PLS), support vector machines (SVM), and k nearest neighbors (KNN)) and deep learning (multi-layer perceptron (MLP) and convolutional neural network (CNN)) are used to perform a comparative study to estimate the soil properties, such as the soil moisture and terrain strength, used to generate prediction maps of these terrain characteristics. This study found that deep learning outperformed machine learning. Specifically, a multi-layer perceptron performed the best for predicting the percent moisture content (R2/RMSE = 0.97/1.55) and the soil strength (in PSI), as measured by a cone penetrometer for the averaged 0-6" (CP06) (R2/RMSE = 0.95/67) and 0-12" depth (CP12) (R2/RMSE = 0.92/94). A Polaris MRZR vehicle was used to test the application of these prediction maps for mobility purposes, and correlations were observed between the CP06 and the rear wheel slip and the CP12 and the vehicle speed. Thus, this study demonstrates the potential of a more rapid, cost-efficient, and safer approach to predict terrain properties for mobility mapping using remote sensing data with machine and deep learning algorithms.