BackgroundMood disorders are common and associated with significant morbidity and mortality. Better tools are needed for their diagnosis and treatment. Deeper phenotypic understanding of these disorders is integral to the development of such tools. This study is the first effort to use passively collected mobile phone keyboard activity to build deep digital phenotypes of depression and mania.ObjectiveThe objective of our study was to investigate the relationship between mobile phone keyboard activity and mood disturbance in subjects with bipolar disorders and to demonstrate the feasibility of using passively collected mobile phone keyboard metadata features to predict manic and depressive signs and symptoms as measured via clinician-administered rating scales.MethodsUsing a within-subject design of 8 weeks, subjects were provided a mobile phone loaded with a customized keyboard that passively collected keystroke metadata. Subjects were administered the Hamilton Depression Rating Scale (HDRS) and Young Mania Rating Scale (YMRS) weekly. Linear mixed-effects models were created to predict HDRS and YMRS scores. The total number of keystrokes was 626,641, with a weekly average of 9791 (7861), and that of accelerometer readings was 6,660,890, with a weekly average 104,076 (68,912).ResultsA statistically significant mixed-effects regression model for the prediction of HDRS-17 item scores was created: conditional R2=.63, P=.01. A mixed-effects regression model for YMRS scores showed the variance accounted for by random effect was zero, and so an ordinary least squares linear regression model was created: R2=.34, P=.001. Multiple significant variables were demonstrated for each measure.ConclusionsMood states in bipolar disorder appear to correlate with specific changes in mobile phone usage. The creation of these models provides evidence for the feasibility of using passively collected keyboard metadata to detect and monitor mood disturbances.

No abstract

No abstract

BACKGROUND Mood disorders are common and associated with significant morbidity and mortality. Better tools are needed for their diagnosis and treatment. Deeper phenotypic understanding of these disorders is integral to the development of such tools. This study is the first effort to use passively collected mobile phone keyboard activity to build deep digital phenotypes of depression and mania. OBJECTIVE The objective of our study was to investigate the relationship between mobile phone keyboard activity and mood disturbance in subjects with bipolar disorders and to demonstrate the feasibility of using passively collected mobile phone keyboard metadata features to predict manic and depressive signs and symptoms as measured via clinician-administered rating scales. METHODS Using a within-subject design of 8 weeks, subjects were provided a mobile phone loaded with a customized keyboard that passively collected keystroke metadata. Subjects were administered the Hamilton Depression Rating Scale (HDRS) and Young Mania Rating Scale (YMRS) weekly. Linear mixed-effects models were created to predict HDRS and YMRS scores. The total number of keystrokes was 626,641, with a weekly average of 9791 (7861), and that of accelerometer readings was 6,660,890, with a weekly average 104,076 (68,912). RESULTS A statistically significant mixed-effects regression model for the prediction of HDRS-17 item scores was created: conditional R2=.63, P=.01. A mixed-effects regression model for YMRS scores showed the variance accounted for by random effect was zero, and so an ordinary least squares linear regression model was created: R2=.34, P=.001. Multiple significant variables were demonstrated for each measure. CONCLUSIONS Mood states in bipolar disorder appear to correlate with specific changes in mobile phone usage. The creation of these models provides evidence for the feasibility of using passively collected keyboard metadata to detect and monitor mood disturbances.

No abstract

Background: End-stage renal disease (ESRD) patients experience immune compromise characterized by complex alterations of both innate and adaptive immunity, and results in higher susceptibility to infection and lower response to vaccination. This immune compromise, coupled with greater risk of exposure to infectious disease at hemodialysis (HD) centers, underscores the need for examination of the immune response to the COVID-19 mRNA-based vaccines.<br /><br />Methods: A transcriptomic analysis of the immune response to the Covid-19 BNT162b2 mRNA vaccine was assessed in 20 HD patients and cohort-matched controls. RNA sequencing of peripheral blood mononuclear cells (PBMCs) was performed longitudinally before and after each vaccination dose for a total of six time points per subject. Anti-spike antibody levels were quantified prior to the first vaccination dose (V1D0) and seven days after the second dose (V2D7) using anti-Spike IgG titers and antibody neutralization assays. Anti-spike IgG titers were additionally quantified six months after initial vaccination. Clinical history and lab values in HD patients were obtained to identify predictors of vaccination response.<br /><br />Results: Transcriptomic analyses demonstrated differing time courses of immune responses, with predominant T cell activity in controls one week after the first vaccination dose, compared to predominant myeloid cell activity in HD at this time point. HD demonstrated decreased metabolic activity and decreased antigen presentation compared to controls after the second vaccination dose. Anti-spike IgG titers and neutralizing function were substantially elevated in both controls and HD at V2D7, with a small but significant reduction in titers in HD groups (p < 0.05). Anti-spike IgG remained elevated above baseline at six months in both subject groups. Anti-spike IgG titers at V2D7 were highly predictive of 6-month titer levels. Transcriptomic biomarkers after the second vaccination dose and clinical biomarkers including ferritin levels were found to be predictive of antibody development.<br /><br />Conclusion: Overall, we demonstrate differing time courses of immune responses to the BTN162b2 mRNA COVID-19 vaccination in maintenance hemodialysis subjects (HD) comparable to healthy controls (HC) and identify transcriptomic and clinical predictors of anti-Spike IgG titers in HD. Analyzing vaccination as an in vivo perturbation, our results warrant further characterization of the immune dysregulation of end stage renal disease (ESRD).<br /><br />Funding:F30HD102093, F30HL151182, T32HL144909, R01HL138628<br />This research has been funded by the University of Illinois at Chicago Center for Clinical and Translational Science (CCTS) award UL1TR002003

No abstract