Accurate Step Count with Generalized and Personalized Deep Learning on Accelerometer Data.

Physical activity (PA) is globally recognized as a pillar of general health. Step count, as one measure of PA, is a well known predictor of long-term morbidity and mortality. Despite its popularity in consumer devices, a lack of methodological standards and clinical validation remains a major impediment to step count being accepted as a valid clinical endpoint. Previous works have mainly focused on device-specific step-count algorithms and often employ sensor modalities that may not be widely available. This may limit step-count suitability in clinical scenarios. In this paper, we trained neural network models on publicly available data and tested on an independent cohort using two approaches: generalization and personalization. Specifically, we trained neural networks on accelerometer signals from one device and either directly applied them or adapted them individually to accelerometer data obtained from a separate subject cohort wearing multiple distinct devices. The best models exhibited highly accurate step-count estimates for both the generalization (96-99%) and personalization (98-99%) approaches. The results demonstrate that it is possible to develop device-agnostic, accelerometer-only algorithms that provide highly accurate step counts, positioning step count as a reliable mobility endpoint and a strong candidate for clinical validation.

Analysis of Use and Outcomes of the Balance Digital Disease Management Tool for Patients with Type 2 Diabetes.

Management of type 2 diabetes mellitus (T2DM) is a serious medical need for millions of patients and clinicians worldwide. Numerous smartphone apps for T2DM management are available. Due to their global accessibility, computing power and cellular connectivity, the pervasiveness of mobile phones now provide an opportunity for non-invasive Digital Therapeutics that have the potential to manage disease by modifying patient behavior as new modality for disease management and intervention. However, this novel approach has yet to be tested in large clinical studies. The BALANCE clinical study was designed to evaluate mobile phone App usage in a large multi-center clinical trial and its impact on T2DM outcomes. It included a digital aid for the management of, blood glucose, diet, physical activity, and medication adherence. Overall, patient use of the BALANCE-App was low (21% of significant patients users), and it diminished over time. BALANCE showed no effect on HbA1c or weight, what is consistent with other smartphone apps for T2DM which were tested on large clinical trials. Nevertheless, post-hoc subgroup analysis showed women using the App significantly achieved a significant reduction in HbA1c and weight.Clinical relevance Suitability of Digital Therapeutics, at least in the form of smartphone apps, for T2DM is under question. The low use indicates need for a strong focus in patient acceptability and patient engagement in the design process.

Home-based Digital Assessments with Applied Sentiment & Emotion AI Capture Improved Quality-of-life in Asthma Patients.

With the rise of digital transformation in the pharmaceutical industry, digital therapeutics are being integrated in drug development clinical trials. In the TWINKLE study, information about asthmatic patients' disease control and quality-of-life (QoL) was measured by daily video recording, in conjunction with daily electronic questionnaires and home-based spirometry. From the video messages, sentiment and emotion AI was applied to detect subtle QoL changes in asthmatic patients after receiving treatments. Sentiment scores, derived from patients' daily messages via natural language processing, correlated strongly with metrics of lung functions and outcomes of electronic questionnaires. However, video-derived emotional analysis exhibited strong interpersonal variations and systematic biases, yet still showed utility in detecting QoL changes after personalized calibration and signal aggregation. Compared to traditional patient-reported outcomes, all three categories of digital measurements were able to detect significantly improved asthma control from patients who responded to treatments. The result provides insights into developing novel digital outcomes through the application of connected digital devices and advanced AI tailored to clinical settings.Clinical relevance- Digital outcomes involving connected digital devices and AI for sentiment/emotion analysis could capture subtle QoL changes reliably and earlier than hospital visits, reducing burden and improving disease management. Integrating digital therapeutics in asthma drug development trials may prove to be feasible and valuable.

Assessment of Objectively Measured Physical Activity as an Independent Estimator of Functional Status in Clinical Trials.

Functional status of patients is an important concept in clinical trials. It subsumes functional capacity, which is traditionally estimated by exercise tests, and functional performance, which is often estimated by questionnaires. Objectively measured physical activity by means of wearables devices containing accelerometers (PA) have recently been proposed as a novel and advantageous way to estimate physical status including capacity and performance. There is nonetheless insufficient evidence of the association between PA and traditional ways to estimate functional status. In the ACTIVATE clinical trial, cycle ergometry tests were performed multiple times in all 267 patients, PA was measured for a week prior to each cycle ergometry test, and questionnaires were answered daily during the same week. Pearson's correlation tests and clustering analysis revealed that PA, physical activity experience as assessed by questionnaires, and exercise endurance time as measured by the cycle ergometry test, are largely independent. Therefore, all three approaches together might achieve a complete assessment of the functional status of patients in clinical trials, as they each independently correlate with health-related quality of life and important clinical outcomes such as hospitalizations but are weakly associated among themselves.

Synovial phenotypes in rheumatoid arthritis correlate with response to biologic therapeutics.

INTRODUCTION: Rheumatoid arthritis (RA) is a complex and clinically heterogeneous autoimmune disease. Currently, the relationship between pathogenic molecular drivers of disease in RA and therapeutic response is poorly understood. METHODS: We analyzed synovial tissue samples from two RA cohorts of 49 and 20 patients using a combination of global gene expression, histologic and cellular analyses, and analysis of gene expression data from two further publicly available RA cohorts. To identify candidate serum biomarkers that correspond to differential synovial biology and clinical response to targeted therapies, we performed pre-treatment biomarker analysis compared with therapeutic outcome at week 24 in serum samples from 198 patients from the ADACTA (ADalimumab ACTemrA) phase 4 trial of tocilizumab (anti-IL-6R) monotherapy versus adalimumab (anti-TNFα) monotherapy. RESULTS: We documented evidence for four major phenotypes of RA synovium - lymphoid, myeloid, low inflammatory, and fibroid - each with distinct underlying gene expression signatures. We observed that baseline synovial myeloid, but not lymphoid, gene signature expression was higher in patients with good compared with poor European league against rheumatism (EULAR) clinical response to anti-TNFα therapy at week 16 (P =0.011). We observed that high baseline serum soluble intercellular adhesion molecule 1 (sICAM1), associated with the myeloid phenotype, and high serum C-X-C motif chemokine 13 (CXCL13), associated with the lymphoid phenotype, had differential relationships with clinical response to anti-TNFα compared with anti-IL6R treatment. sICAM1-high/CXCL13-low patients showed the highest week 24 American College of Rheumatology (ACR) 50 response rate to anti-TNFα treatment as compared with sICAM1-low/CXCL13-high patients (42% versus 13%, respectively, P =0.05) while anti-IL-6R patients showed the opposite relationship with these biomarker subgroups (ACR50 20% versus 69%, P =0.004). CONCLUSIONS: These data demonstrate that underlying molecular and cellular heterogeneity in RA impacts clinical outcome to therapies targeting different biological pathways, with patients with the myeloid phenotype exhibiting the most robust response to anti-TNFα. These data suggest a path to identify and validate serum biomarkers that predict response to targeted therapies in rheumatoid arthritis and possibly other autoimmune diseases. TRIAL REGISTRATION: ClinicalTrials.gov NCT01119859

Differential B cell expression of mouse Fc receptor homologs.

Five Fc receptor homologs (FcRH1-5) possessing inhibitory and/or activating signaling motifs are differentially expressed during B cell differentiation in humans. In this analysis we describe their three mouse orthologs, moFcRH1, moFcRH2 and moFcRH3. The moFcRH genes are located in a chromosome 3 region that is syntenic with the FcRH locus on human chromosome 1. They encode proteins with 2-5 Ig-like domains that share 20-61% extracellular identity with their human counterparts. One moFcRH1 isoform lacks a transmembrane domain as do both moFcRH2 isoforms. The other moFcRH1 isoform and two moFcRH3 isoforms have transmembrane domains and cytoplasmic ITIM and ITAM-like consensus sequences implying their inhibitory or activating signaling potential. Whereas the moFcRH1 and moFcRH3 orthologs are preferentially expressed at different stages in B cell differentiation, the structurally novel moFcRH2 gene is expressed in non-lymphoid tissues. The highly restricted pattern of moFcRH3 expression suggests this member of the phylogenetically conserved FcRH family may have an important immunoregulatory role in marginal zone B cells.

PubMatrix: a tool for multiplex literature mining.

BACKGROUND: Molecular experiments using multiplex strategies such as cDNA microarrays or proteomic approaches generate large datasets requiring biological interpretation. Text based data mining tools have recently been developed to query large biological datasets of this type of data. PubMatrix is a web-based tool that allows simple text based mining of the NCBI literature search service PubMed using any two lists of keywords terms, resulting in a frequency matrix of term co-occurrence. RESULTS: For example, a simple term selection procedure allows automatic pair-wise comparisons of approximately 1-100 search terms versus approximately 1-10 modifier terms, resulting in up to 1,000 pair wise comparisons. The matrix table of pair-wise comparisons can then be surveyed, queried individually, and archived. Lists of keywords can include any terms currently capable of being searched in PubMed. In the context of cDNA microarray studies, this may be used for the annotation of gene lists from clusters of genes that are expressed coordinately. An associated PubMatrix public archive provides previous searches using common useful lists of keyword terms. CONCLUSIONS: In this way, lists of terms, such as gene names, or functional assignments can be assigned genetic, biological, or clinical relevance in a rapid flexible systematic fashion. http://pubmatrix.grc.nia.nih.gov/

Identifying biological themes within lists of genes with EASE.

EASE is a customizable software application for rapid biological interpretation of gene lists that result from the analysis of microarray, proteomics, SAGE and other high-throughput genomic data. The biological themes returned by EASE recapitulate manually determined themes in previously published gene lists and are robust to varying methods of normalization, intensity calculation and statistical selection of genes. EASE is a powerful tool for rapidly converting the results of functional genomics studies from 'genes' to 'themes'.

DAVID: Database for Annotation, Visualization, and Integrated Discovery.

BACKGROUND: Functional annotation of differentially expressed genes is a necessary and critical step in the analysis of microarray data. The distributed nature of biological knowledge frequently requires researchers to navigate through numerous web-accessible databases gathering information one gene at a time. A more judicious approach is to provide query-based access to an integrated database that disseminates biologically rich information across large datasets and displays graphic summaries of functional information. RESULTS: Database for Annotation, Visualization, and Integrated Discovery (DAVID; http://www.david.niaid.nih.gov) addresses this need via four web-based analysis modules: 1) Annotation Tool - rapidly appends descriptive data from several public databases to lists of genes; 2) GoCharts - assigns genes to Gene Ontology functional categories based on user selected classifications and term specificity level; 3) KeggCharts - assigns genes to KEGG metabolic processes and enables users to view genes in the context of biochemical pathway maps; and 4) DomainCharts - groups genes according to PFAM conserved protein domains. CONCLUSIONS: Analysis results and graphical displays remain dynamically linked to primary data and external data repositories, thereby furnishing in-depth as well as broad-based data coverage. The functionality provided by DAVID accelerates the analysis of genome-scale datasets by facilitating the transition from data collection to biological meaning.

Gene expression and viral prodution in latently infected, resting CD4+ T cells in viremic versus aviremic HIV-infected individuals.

The presence of HIV-1 in latently infected, resting CD4(+) T cells has been clearly demonstrated in infected individuals; however, the extent of viral expression and the underlying mechanisms of the persistence of HIV-1 in this viral reservoir have not been fully delineated. Here, we show that resting CD4(+) T cells from the majority of viremic patients are capable of producing cell-free HIV-1 spontaneously ex vivo. The levels of HIV-1 released by resting CD4(+) T cells were not significantly reduced in the presence of inhibitors of cellular proliferation and viral replication. However, resting CD4(+) T cells from the majority of aviremic patients failed to produce virions, despite levels of HIV-1 proviral DNA and cell-associated HIV-1 RNA comparable to viremic patients. The DNA microarray analysis demonstrated that a number of genes involving transcription regulation, RNA processing and modification, and protein trafficking and vesicle transport were significantly upregulated in resting CD4(+) T cells of viremic patients compared to those of aviremic patients. These results suggest that active viral replication has a significant impact on the physiologic state of resting CD4(+) T cells in infected viremic patients and, in turn, allows release of HIV-1 without exogenous activation stimuli. In addition, given that no quantifiable virions were produced by the latent viral reservoir in the majority of aviremic patients despite the presence of cell-associated HIV-1 RNA, evidence for transcription of HIV-1 RNA in resting CD4(+) T cells of aviremic patients should not necessarily be taken as direct evidence for ongoing viral replication during effective therapy.

Cutting edge: L-selectin (CD62L) expression distinguishes small resting memory CD4+ T cells that preferentially respond to recall antigen.

Naive CD4+ T cells use L-selectin (CD62L) expression to facilitate immune surveillance. However, the reasons for its expression on a subset of memory CD4+ T cells are unknown. We show that memory CD4+ T cells expressing CD62L were smaller, proliferated well in response to tetanus toxoid, had longer telomeres, and expressed genes and proteins consistent with immune surveillance function. Conversely, memory CD4+ T cells lacking CD62L expression were larger, proliferated poorly in response to tetanus toxoid, had shorter telomeres, and expressed genes and proteins consistent with effector function. These findings suggest that CD62L expression facilitates immune surveillance by programming CD4+ T cell blood and lymph node recirculation, irrespective of naive or memory CD4+ T cell phenotype.

Fc receptor homologs: newest members of a remarkably diverse Fc receptor gene family.

Newfound relatives of the classical Fc receptors (FcR) have been provisionally named the Fc receptor homologs (FcRH). The recent identification of eight human and six mouse FcRH genes substantially increases the size and functional potential of the FcR family. The extended family of FcR and FcRH genes spans approximately 15 Mb of the human chromosome 1q21-23 region, whereas in mice this family is split between chromosomes 1 and 3. The FcRH genes encode molecules with variable combinations of five subtypes of immunoglobulin (Ig) domains. The presence of a conserved sequence motif in one Ig domain subtype implies Ig Fc binding capability for many FcRH family members that are preferentially expressed by B lineage cells. In addition, most FcRH family members have consensus tyrosine-based activating and inhibitory motifs in their cytoplasmic domains, while the others lack features typical of transmembrane receptors. The FcRH family members, like the classical FcRs, come in multiple isoforms and allelic variations. The unique individual and polymorphic properties of the FcR/FcRH members indicate a remarkably diverse Fc receptor gene family with immunoregulatory function.

HIV envelope induces a cascade of cell signals in non-proliferating target cells that favor virus replication.

Certain HIV-encoded proteins modify host-cell gene expression in a manner that facilitates viral replication. These activities may contribute to low-level viral replication in nonproliferating cells. Through the use of oligonucleotide microarrays and high-throughput Western blotting we demonstrate that one of these proteins, gp120, induces the expression of cytokines, chemokines, kinases, and transcription factors associated with antigen-specific T cell activation in the absence of cellular proliferation. Examination of transcriptional changes induced by gp120 in freshly isolated peripheral blood mononuclear cells and monocyte-derived-macrophages reveals a broad and complex transcriptional program conducive to productive infection with HIV. Observations include the induction of nuclear factor of activated T cells, components of the RNA polymerase II complex including TFII D, proteins localized to the plasma membrane, including several syntaxins, and members of the Rho protein family, including Cdc 42. These observations provide evidence that envelope-mediated signaling contributes to the productive infection of HIV in suboptimally activated T cells.