Reliability of remote self-administered web-based digital cognitive measures and comparison to in-person neuropsychological tests: Stricker Learning Span, Symbols Test and the Mayo Test Drive Screening Battery Composite

Reliability of remote self-administered web-based digital cognitive measures and comparison to in-person neuropsychological tests: Stricker Learning Span, Symbols Test and the Mayo Test Drive Screening Battery Composite | medRxiv /* */ /* */ <!-- <!-- /*! * yepnope1.5.4 * (c) WTFPL, GPLv2 */ (function(a,b,c){function d(a){return"[object Function]"==o.call(a)}function e(a){return"string"==typeof a}function f(){}function g(a){return!a||"loaded"==a||"complete"==a||"uninitialized"==a}function h(){var a=p.shift();q=1,a?a.t?m(function(){("c"==a.t?B.injectCss:B.injectJs)(a.s,0,a.a,a.x,a.e,1)},0):(a(),h()):q=0}function i(a,c,d,e,f,i,j){function k(b){if(!o&&g(l.readyState)&&(u.r=o=1,!q&&h(),l.onload=l.onreadystatechange=null,b)){"img"!=a&&m(function(){t.removeChild(l)},50);for(var d in y[c])y[c].hasOwnProperty(d)&&y[c][d].onload()}}var j=j||B.errorTimeout,l=b.createElement(a),o=0,r=0,u={t:d,s:c,e:f,a:i,x:j};1===y[c]&&(r=1,y[c]=[]),"object"==a?l.data=c:(l.src=c,l.type=a),l.width=l.height="0",l.onerror=l.onload=l.onreadystatechange=function(){k.call(this,r)},p.splice(e,0,u),"img"!=a&&(r||2===y[c]?(t.insertBefore(l,s?null:n),m(k,j)):y[c].push(l))}function j(a,b,c,d,f){return q=0,b=b||"j",e(a)?i("c"==b?v:u,a,b,this.i++,c,d,f):(p.splice(this.i++,0,a),1==p.length&&h()),this}function k(){var a=B;return a.loader={load:j,i:0},a}var l=b.documentElement,m=a.setTimeout,n=b.getElementsByTagName("script")[0],o={}.toString,p=[],q=0,r="MozAppearance"in l.style,s=r&&!!b.createRange().compareNode,t=s?l:n.parentNode,l=a.opera&&"[object Opera]"==o.call(a.opera),l=!!b.attachEvent&&!l,u=r?"object":l?"script":"img",v=l?"script":u,w=Array.isArray||function(a){return"[object Array]"==o.call(a)},x=[],y={},z={timeout:function(a,b){return b.length&&(a.timeout=b[0]),a}},A,B;B=function(a){function b(a){var a=a.split("!"),b=x.length,c=a.pop(),d=a.length,c={url:c,origUrl:c,prefixes:a},e,f,g;for(f=0;f<d;f++)g=a[f].split("="),(e=z[g.shift()])&&(c=e(c,g));for(f=0;f<b;f++)c=x[f](c);return c}function g(a,e,f,g,h){var i=b(a),j=i.autoCallback;i.url.split(".").pop().split("?").shift(),i.bypass||(e&&(e=d(e)?e:e[a]||e[g]||e[a.split("/").pop().split("?")[0]]),i.instead?i.instead(a,e,f,g,h):(y[i.url]?i.noexec=!0:y[i.url]=1,f.load(i.url,i.forceCSS||!i.forceJS&&"css"==i.url.split(".").pop().split("?").shift()?"c":c,i.noexec,i.attrs,i.timeout),(d(e)||d(j))&&f.load(function(){k(),e&&e(i.origUrl,h,g),j&&j(i.origUrl,h,g),y[i.url]=2})))}function h(a,b){function c(a,c){if(a){if(e(a))c||(j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}),g(a,j,b,0,h);else if(Object(a)===a)for(n in m=function(){var b=0,c;for(c in a)a.hasOwnProperty(c)&&b++;return b}(),a)a.hasOwnProperty(n)&&(!c&&!--m&&(d(j)?j=function(){var a=[].slice.call(arguments);k.apply(this,a),l()}:j[n]=function(a){return function(){var b=[].slice.call(arguments);a&&a.apply(this,b),l()}}(k[n])),g(a[n],j,b,n,h))}else!c&&l()}var h=!!a.test,i=a.load||a.both,j=a.callback||f,k=j,l=a.complete||f,m,n;c(h?a.yep:a.nope,!!i),i&&c(i)}var i,j,l=this.yepnope.loader;if(e(a))g(a,0,l,0);else if(w(a))for(i=0;i (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0];var j=d.createElement(s);var dl=l!='dataLayer'?'&l='+l:'';j.src='//www.googletagmanager.com/gtm.js?id='+i+dl;j.type='text/javascript';j.async=true;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-P4HH5NV'); Skip to main content Home About Submit ALERTS / RSS Search for this keyword Advanced Search Reliability of remote self-administered web-based digital cognitive measures and comparison to in-person neuropsychological tests: Stricker Learning Span, Symbols Test and the Mayo Test Drive Screening Battery Composite Morgan A. Hughes , Ryan D. Frank , Rita L. Taylor , Winnie Z. Fan , Teresa J. Christianson , Walter K. Kremers , John L. Stricker , Mary M. Machulda , Jason Hassenstab , Michelle M. Mielke , John A. Lucas , Paula A. Aduen , View ORCID Profile Gregory S. Day , Neill R. Graff-Radford , View ORCID Profile Clifford R. Jack Jr. , Jonathan Graff-Radford , Ronald C. Petersen , View ORCID Profile Nikki H. Stricker doi: https://doi.org/10.1101/2025.09.26.25336467 Morgan A. Hughes a Department of Anesthesia and Perioperative Medicine , Mayo Clinic, Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ryan D. Frank b Division of Biomedical Statistics and Informatics, Department of Quantitative Health Sciences , Mayo Clinic, Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Rita L. Taylor c Division of Neurocognitive Disorders, Department of Psychiatry and Psychology, Mayo Clinic , Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Winnie Z. Fan b Division of Biomedical Statistics and Informatics, Department of Quantitative Health Sciences , Mayo Clinic, Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Teresa J. Christianson b Division of Biomedical Statistics and Informatics, Department of Quantitative Health Sciences , Mayo Clinic, Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Walter K. Kremers b Division of Biomedical Statistics and Informatics, Department of Quantitative Health Sciences , Mayo Clinic, Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site John L. Stricker d Department of Information Technology, Mayo Clinic , Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Mary M. Machulda c Division of Neurocognitive Disorders, Department of Psychiatry and Psychology, Mayo Clinic , Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Jason Hassenstab e Department of Neurology and Psychological & Brain Sciences, Washington University in Saint Louis , Saint Louis, Missouri, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Michelle M. Mielke f Department of Epidemiology and Prevention, Wake Forest University School of Medicine , Winston-Salem, North Carolina, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site John A. Lucas g Department of Psychiatry and Psychology , Mayo Clinic in Florida, Jacksonville, Florida, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Paula A. Aduen g Department of Psychiatry and Psychology , Mayo Clinic in Florida, Jacksonville, Florida, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Gregory S. Day h Department of Neurology, Mayo Clinic in Florida , Jacksonville, Florida, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Gregory S. Day Neill R. Graff-Radford h Department of Neurology, Mayo Clinic in Florida , Jacksonville, Florida, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Clifford R. Jack Jr. i Department of Radiology, Mayo Clinic , Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Clifford R. Jack Jr. Jonathan Graff-Radford j Department of Neurology, Mayo Clinic , Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Ronald C. Petersen j Department of Neurology, Mayo Clinic , Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site Nikki H. Stricker c Division of Neurocognitive Disorders, Department of Psychiatry and Psychology, Mayo Clinic , Rochester, Minnesota, USA Find this author on Google Scholar Find this author on PubMed Search for this author on this site ORCID record for Nikki H. Stricker For correspondence: stricker.nikki{at}mayo.edu Abstract Full Text Info/History Metrics Supplementary material Data/Code Preview PDF Structured Abstract INTRODUCTION We describe the reliability of remote self-administered digital cognitive measures completed via the Mayo Test Drive (MTD) web-based platform. METHODS 1,846 participants (mean age=70, SD=12, range 31-101; 48% male; 96% White; 99% non-Hispanic; 97% cognitively unimpaired) with 2-4 complete MTD sessions at ~7.5-month intervals were included. Test-retest reliability was assessed using single-rating, absolute-agreement, and two-way mixed intraclass correlation coefficients (ICCs) with 95% confidence intervals. ICCs for in-person-administered traditional neuropsychological measures were compared to MTD for a subset of 244 participants. RESULTS Reliability was good for the MTD Composite [total ICC = 0.79 (0.77, 0.80)], and moderate-to-good for the primary outcome variables for each MTD subtest [total ICCs 0.70-0.83 for Stricker Learning Span and Symbols]. The reliability of the remote self-administered MTD was similar to in-person-administered cognitive measures. DISCUSSION MTD showed moderate-to-good reliability, supporting its use in longitudinal monitoring. Introduction Mayo Test Development through Rapid Iteration, Validation and Expansion (DRIVE, MTD), is a web-based, multi-device (i.e. smartphone, tablet, and computers) digital platform used for remote self-administration of cognitive assessments with high usability. 1 The MTD cognitive screening battery includes the Stricker Learning Span (SLS) and Symbols (SYM) subtests, and is typically completed in 15-20 minutes. 1 The SLS is a computer adaptive word list memory test and the SYM test measures processing speed and working memory. The MTD screening battery composite score (MTD Comp ) is a combination of the SLS and SYM test that shows robust associations with the Mayo Preclinical Alzheimer’s disease Cognitive Composite (Mayo-PACC) 2 and multiple neuroimaging biomarkers including amyloid PET, tau PET, hippocampal volume, and white matter hyperintensity volume. 3 Normative data for remote self-administration of MTD are available. 4 The validity of MTD and its subtests are well-supported by prior publications. 3 – 5 Reliability is an additional key consideration for remote digital cognitive assessments. 6 Test-retest reliability refers to the ability to replicate a test over time, or how consistent test results are within an individual across sessions. 7 Because MTD subtests use a randomized item selection approach, test-retest reliability for MTD subtests also includes alternate-form reliability. 5 Remote assessments can be completed in multiple environments, which may lead to a higher likelihood of distractions or interruptions that may increase variability in performance and compromise reliability. Reliable remote self-administered digital cognitive assessments would expand options for monitoring cognition over time. The aim of the current study was to characterize the reliability of MTD. We compared the reliability of remotely administered MTD measures to traditional in-person-administered neuropsychological measures. We also examined the impact of demographics (age, education, sex), device type / input source, subtest interference 1 , and location on reliability. Method Participants and Study Procedures MTD study participants were primarily recruited from the Mayo Clinic Study of Aging (MCSA), which is a prospective, population-based study of aging within Olmsted County, MN. 1 , 4 MCSA study visits occurred every 15 months (or every 30 months for individuals <50 years of age) and included a physician exam, completion of the Clinical Dementia Rating® (CDR), 8 and in-person neuropsychological testing. 9 Clinical diagnoses of cognitively unimpaired (CU), mild cognitive impairment (MCI), or dementia were determined by consensus agreement, referencing published diagnostic criteria. 10 , 11 MCSA participants were invited to complete an MTD session the week following their MCSA study visit and every 7.5 months between study visits. 1 See Supplemental Online Resources for additional time interval details. Some participants were also recruited from the Mayo Alzheimer’s Disease Research Center, as previously described. 1 , 4 This study was conducted in accordance with the Declaration of Helsinki. The MTD study was approved by the Mayo Clinic IRB. Oral consent (that includes review of consent elements via email) was obtained. 1 , 4 MTD Sessions MTD subtests and variable derivation have been previously described in detail. 3 , 4 , 12 , 13 The SLS includes five adaptive learning trials and a delayed recognition memory trial. 5 During learning trials, participants are visually presented with one word at a time and asked to identify the presented words in a 4-word recognition format at the end of each trial. The delay trial is presented after the SYM test. SLS Sum of Trials (SLS Sum ) is the primary outcome variable (trials 1-5 total correct + delay correct). The SYM test requires rapid matching of symbol pairs. There are 12 items in each trial, and 4 trials are completed sequentially. 3 MTD SYM is an adaptation from the Symbols test administered in the Ambulatory Research in Cognition (ARC) App 14 ; the primary outcome variable is average correct item response time in seconds (SYM RT ). We provide an additional primary MTD SYM variable that weights SYM RT by accuracy, the SYM accuracy-weighted score (SYM AW ). MTD Comp is the sum of SLS Sum and SYM AW . 3 , 4 Secondary variables (see Table 2 ) can be considered for use as outcome variables for research studies and for clinical interpretation as needed (e.g., when immediate learning and delayed memory performance differentiation is emphasized). We included an alternative, z-score based version of the MTD Comp (MTD Composite-z) that has been previously described. 3 This may be used in research as an alternative outcome variable but no normative data are available for this version of the composite because it is derived from z-scores and thus is sample specific. Secondary process variables (see Table 2 ) are expected to have lower reliability because they represent single trial variables or are expected to have non-normal distributions. 15 Secondary process variables should not be used as outcome variables for research studies, but are available to characterize patterns of performance, an individual’s approach to testing (i.e., “process”), or to allow alternative metrics if an interruption impacts one or more primary variables (e.g., if an individual is interrupted during one or more SLS or SYM trial). Inclusion Criteria for Primary Analyses Inclusion criteria for the primary analyses were: 1) a complete baseline MTD session (i.e. MTD Comp not missing) and at least one complete and consecutive follow-up session; 2) a valid session, as previously defined 1 or per data cleaning/session review; 3) absence of dementia at baseline. MTD sessions completed between 5/25/21 and 6/15/25 were included. Sample Selection for Comparison to In-Person Traditional Neuropsychological Tests To compare the reliability of traditional in-person-administered neuropsychological tests to self-administered MTD measures, the sample was limited to participants newly enrolled into the parent study to ensure participants were naïve to both MTD and in-person neuropsychological tests. Because in-person-administered neuropsychological testing occurred approximately every 15 months, the 2 nd in-person visit occurred around the same time as the 3 rd MTD session (MTD is completed every 7.5 months). Comparisons to in-person testing focused on the first two MTD sessions (sessions 1-2) for consistency of the number of administrations between remote and person-administered measures, but session 1-3, 2-3, and total reliability across all 3 sessions are also reported to show a similar time interval. Comparisons focused on the following in-person-administered measures: (1) the Kokmen Short Test of Mental Status (STMS) 16 , which is a multi-domain global cognitive screening measure (similar to the Mini Mental State Examination), and (2) the Mayo-PACC, which is an average of z-scores from the Rey’s Auditory Verbal Learning Test (AVLT) sum of trials, Trail Making Test B (inversed) and animal fluency. 2 We additionally compared select subtest measures from Mayo-PACC considered most similar to MTD subtest measures (AVLT sum of trials and SLS Sum ; SYM AW /SYM RT and Trails B). Sample Selection for Subgroup Analyses To examine potential MTD reliability differences by demographics and by factors relevant for remote assessment (device type, subtest interference, and location), the primary analytic sample was limited to CU participants before creating subgroups. Dichotomous groups were created to facilitate comparisons for the following: age (age <70-vs ≥70-years old), sex, education (<16 vs ≥16 years of education), device and input source consistency (participants who consistently used the same device/input source for all sessions vs. participants who switched types across sessions), potential test interference (no endorsed potential interference during any session vs ≥1 potential distraction or interference during a session) 1 , and location (consistently took all MTD sessions at home vs. location varied across sessions). Statistical Methods Patient demographics were summarized using counts and percentages for categorical variables and means and standard deviations for continuous variables. Comparison of data distributions across groups were performed using chi-square tests for categorical variables and 2-sample t-tests for continuous variables. The ICCs were calculated as from a random effects model with random effects participant intercepts (unadjusted ICCs) and fixed effects for age at assessment, sex, and education (adjusted ICCs). Unadjusted ICCs are typically reported in studies reporting reliability of cognitive test data but are sample-specific. We therefore also provide adjusted ICCs. Bootstrap methods using 1000 simulations were used to estimate the standard error used in the confidence limits for ICCs. We also derived Pearson correlation coefficients and their 95% CI. Raw scores were Winsorized at the 1 st and 99 th percentile to lessen the influence of potential outliers. We applied reliability descriptives as defined by Koo et al. 7 (ICCs .90 = excellent). Unadjusted and adjusted ICCs (where the adjustment terms were included as fixed effects) were calculated in independent subsets of the overall sample for subgroup analyses (e.g. males vs females) and compared using the properties of variance distributions (i.e. Var(X-Y) = Var(X) + Var (Y) – Cox(X,Y) = Var(X) + Var(Y) in independent samples) and bootstrap methods; results interpretation focused on adjusted p -value comparisons for subgroup analyses (adjusting for demographic variables). Analyses were conducted using R version 4.4.1. Statistical tests were 2-sided; p-value <0.05 was considered statistically significant. Results Participant Demographics 1,846 participants met inclusion criteria and were included in the primary analyses. Participants were 31-101-years-old at baseline and completed 2-4 MTD sessions ( Table 1 ). Time between sessions was 7-9 months. Nearly all (99.5%) MTD sessions were completed remotely using the participants’ personal devices (61.9% computer, 22.6% smartphone, 15.2% tablet, 0.3% unknown/other). Most participants were White (95.9%), non-Hispanic (99.0%), college educated (mean years of education=15.7, SD=2.3, range 6-20), older adults (mean=69.7, SD=12.1) and CU (96.7% CU; 3.3% were diagnosed with MCI). View this table: View inline View popup Download powerpoint Table 1. Demographic and other characteristics of the sample. MTD Reliability Reliability was good for MTD Comp (total ICC = 0.79; see Table 2 for session-to-session ICCs and 95% CIs), and moderate-to-good for primary outcome variables for SLS and SYM (total ICC: SLS Sum = 0.75, SYM AW = 0.70, SYM RT = 0.83; see Figure 1 ). Weighting by accuracy reduced the reliability of the SYM test and MTD Comp ; SYM RT had a higher total ICC (0.83) than SYM AW (0.70). Similarly, the alternative MTD Composite-z (that includes the SYM RT instead of SYM AW ) showed subtly higher ICC values relative to MTD Comp with total ICCs of 0.81 and 0.79, respectively. SLS sum of trials had subtly higher reliability (0.75) than separate secondary measures of learning (1-5 total correct = 0.73, max span = 0.70) or delay (0.72). Alternative time-based SYM variables showed nearly identical reliability values (e.g., total ICC = 0.83 for SYM RT and average seconds across all four trials, and total ICC = 0.82 for middle two trials average seconds), and averaging across SYM trials yielded higher ICCs compared to single trial ICCs. All secondary variables had moderate-to-good reliability coefficients. As expected, some secondary process variables based on a single trial or with restricted ranges and non-normal distributions had poor reliability coefficients (SLS Percent Retention, SYM Accuracy/Total Correct, SLS Trial 1, SLS Trial 2), but most secondary process variables had moderate-to-good reliability coefficients. Pearson correlations were highly consistent with ICC reliability values; unadjusted ICCs of all primary variables were within .02 of the Pearson correlation coefficients (see Figure 1 and Supplemental Table 2). View this table: View inline View popup Table 2. Mayo Test Drive Intraclass Correlation Coefficients (ICC, 95% Confidence Interval) for all participants averaging across all sessions and for adjacent single test-retest session pairs. Download figure Open in new tab Figure 1. Scatterplots showing single session test-retest reliability for primary MTD variables for adjacent test sessions in all participants. Note . Unadjusted intraclass correlation coefficients and Pearson correlation coefficients for Winsorized raw scores are reported for each scatterplot (see Tables 2 and S2 for 95% confidence intervals, and Table S3 for Pearson correlation coefficients using non-Winsorized scores). MTD = Mayo Test Drive; Resp. Time = Response Time; SLS = Stricker Learning Span; SYM = Symbols. Figure used with permission of Mayo Foundation for Medical Education and Research, all rights reserved. MTD Reliability Compared to Reliability of In-Person Administered Tests Table 3 shows ICC values for in-person and remote MTD testing. When comparing two traditional in-person sessions (baseline to ~15 months) and two MTD sessions (baseline to ~7.5 months), MTD Comp ICC was similar to that of STMS and Mayo-PACC ( p ’s > .05; Supplemental Table 4). Subtest comparisons showed that SLS sum of trials ICC was similar to AVLT sum of trials ICC ( p = .15), SYM AW ICC was lower than Trails B ICC ( p = .04), and SYM RT ICC was higher than Trails B ICC at trend level ( p = .051). See Supplemental Table 5 for alternative comparisons (e.g., comparing 2 in-person sessions to the ICC across all 3 MTD sessions or to MTD sessions 1 and 3 to capture the same time interval). Across all comparisons, there is a trend for reliability of MTD composite to be higher than the STMS, and there is a trend for reliability of Trails B to be higher than SYM AW (but similar to SYM RT ). View this table: View inline View popup Download powerpoint Table 3. Intraclass Correlation Coefficients (ICC, 95% Confidence Interval) for remote self-administered Mayo Test Drive (MTD) and in-person-administered traditional neuropsychological measure reliability for a subset of 244 participants newly enrolled to the parent study. Reliability by Demographic Variables and by Factors Relevant to Remote Self-Administered Assessments The sample was limited to CU participants (N=1,786) prior to subgroup comparisons. See Supplemental Table 5 for subgroup ICC (95% CI) values, unadjusted p -values, p -values adjusted for demographic variables ( p adj ), and subgroup characteristics for these analyses. Reliability scores were similar across MTD primary variables when comparing education (<16 years education vs. ≥16 years education; p adj ’s ≥ 0.35) or sex (males vs. females; p adj ’s ≥ 0.30) subgroups. Most participants (73%, n=1310) used the same device/input source combination for all MTD sessions, typically a computer and mouse (61.9%). There were no significant differences between reliability scores for consistent versus inconsistent device/input source groups for most MTD primary variables ( p adj ’s ≥ 0.13). However, SYM RT showed higher reliability for the consistent group relative to the inconsistent device-input source group ( p adj = 0.049) 597 CU participants endorsed potential interference during at least 1 testing session (interference group). There were no significant reliability differences between the interference 1 and no interference groups ( p adj ’s > 0.10). Most participants (85%, n=1516) consistently completed all MTD sessions at home. MTD Comp and SLS Sum showed no reliability differences between consistent and inconsistent location groups ( p adj ’s > 0.14); however, both SYM primary variables showed higher reliability coefficients when all sessions were completed at home ( p adj 0.05). However, the ≥70 age group showed higher ICC compared to the <70 group for MTD Comp and SYM AW ( p adj ’s < 0.03). Chi-square analysis showed the ≥70 group was more likely to take all MTD tests at home compared to the <70 group ( p < 0.001), thus greater location consistency of the 70+ group is suspected to drive this age difference. Discussion This study provides a detailed characterization of the test-retest reliability of the remote, self-administered digital MTD screening battery composite and its subtests with 7-9-month test-retest intervals across 2-4 test sessions in a large community-based research sample. MTD Comp had good reliability overall. Primary and secondary subtest outcome variables had moderate-to-good reliability, similar to our prior report of 2-week test-retest reliability of SLS and SYM subtest variables in an initial pilot study. 13 MTD has favorable reliability relative to other digital cognitive assessments that use a single session approach for a given timepoint, including those administered in clinic and remotely. For example, Stricker et al. 17 examined the reliability of the in-clinic self-administered Cogstate Brief Battery with a 7.5-month test-retest interval in CU individuals and showed poor-to-moderate reliability (ICCs from 0.36-0.59) for a learning/memory measure (one card learning (OCL) accuracy). Kochan et al. 18 reported poor at-home self-administered 1-month test-retest reliability for Cogstate OCL (ICC = 0.43) and Cambridge Brain Sciences Paired Associates (ICC = 0.30), though use of various cross-battery global composites yielded good reliability (ICC’s 0.82-0.85). Feenstra et al. 19 reported moderate reliability for word list learning (ICC = 0.59), delayed recall (ICC = 0.50) and recognition (ICC = 0.70), moderate reliability for a measure similar to TMT (Connect the Dots ICCs = 0.67-0.71), and good reliability (0.83) for a 7-subtest composite using the personal-computer-based self-administered Amsterdam Cognition Scan 1-hour battery in 248 healthy adults completed twice within 6 weeks at home. Rigby et al. 20 found similar reliability to MTD subtest results in their cohort of CU and MCI participants when using the in-person-administered National Institute of Health Toolbox-Cognition Battery (NIHTB-CB) in a clinic setting twice within four months. The NIHTB-CB picture sequence memory test (ICC = 0.65) and the pattern comparison processing speed (ICC = 0.85) showed moderate-to-good reliability, and the Fluid Composite showed good reliability (ICC = 0.85). Reliability increases as the number of items, trials, tests, and assessments increases. 2 , 21 Thus, “one-shot” single session approaches tend to have lower reliability relative to paradigms that use the average across several very short sessions completed several times a day for several days or weeks (i.e., ecological momentary assessment) 14 , or longer sessions repeated once daily for several days. 22 , 23 Although individual sessions within these multi-test approaches are brief, cumulatively, they represent more testing time for a given timepoint compared to brief one-shot assessments like MTD. For example, one 15-minute daily session for 6 days represents 90 minutes of testing 22 and 4 daily 30-60 second sessions over 7 days represents 42-84 minutes of testing 14 . Nicosia et al. 14 found excellent reliability when assessing the ARC app in a cohort including CU and very mildly impaired (global CDR 0.5) participants After testing in cycles of 4x a day for 7 consecutive days, the ICCs of each ARC subtest was >0.85 and the reliability of the ARC composite scores were excellent (>0.90) between the initial testing cycle and both a 6-month and a 1-year follow-up cycle. Nicosia et al. 14 also showed that SYM RT reliability reaches 0.88 when averaging across 3 sessions; these data informed the decision to include 4 consecutive SYM trials within a single MTD session as an adaptation of ARC Symbols for inclusion in a “one-shot” assessment paradigm. The current study similarly demonstrates that averaging across ≥2 SYM trials yields ICC values >0.8, whereas single-trial SYM reliabilities ranged from 0.69-0.76. Weighting by accuracy reduced the reliability of SYM, but it helped capture non-speed related aspects of SYM test performance and facilitated creation of the MTD Comp . 3 Reliability of the remote self-administered MTD Comp was similar to an in-person-administered mental status screening measure (STMS) and a composite from traditional in-person-administered neuropsychological tests (Mayo-PACC). Subtest-level comparisons showed that the SLS had similar reliability compared to the AVLT, SYM AW had lower reliability relative to Trails B, and SYM AW had similar reliability relative to Trails B. Direct comparisons to in-person tests focused on comparing test 1 to test 2 ICCs to allow comparison on the same number of assessments, though this resulted in differing time intervals (7.5 months for MTD vs. 15 months for in-person measures), which is an important limitation of these findings. Results were broadly similar when comparing in-person-administered tests to total ICC that considers all 3 timepoints and to comparisons using only MTD sessions 1 and 3 to achieve a similar follow-up interval, though across comparisons there was a trend for reliability of MTD composite to be higher than the STMS. The reliability of the STMS in the current study is comparable to reliability coefficients reported for other global mental status screening measures. For example, Pedraza et al. 24 reported DRS reliability ranging from 0.54-0.71 (Pearson correlation coefficients for 16-24- and 9-15-month intervals, respectively) in CU older adults. MMSE reliability is consistently reported to be poor, including in 119 CU older adults over a test-retest interval of 1.6 years (Spearman correlation coefficient = 0.31) 25 , and in 65 CU participants over a test-retest interval of 83 days (Spearman correlation coefficient = 0.35). 26 To our knowledge, no other group has compared the reliability of remote and in-person-administered traditional cognitive measures in the same participants, making this a strength of the current study. Remote digital assessments offer several advantages to patients, including increased cost-effectiveness, time efficiency and convenience. In addition, remote digital assessment may reduce the “white-coat effect” that may occur with in-person-assessments 28 and allow measures to be easily repeated over time. 18 , 19 The potential benefits of remote digital assessment compared to person-administered measures such as the Mayo-PACC or STMS is demonstrated by a post-hoc power analysis using the results of this study. Because MTD can be completed more frequently remotely, a smaller number of patients is needed to detect effects in clinical trials. We used data derived from MTD vs in-person-administered measure comparisons to calculate the estimated magnitude of this difference. For example, if using the same visit/session frequency as used in the current study, for a clinical trial of 5 years there would be 5 in-person testing sessions (baseline, 15 months, 30 months, 45 months, end of study), whereas MTD would have 9 remote sessions (every 7.5 months). To obtain 80% power to detect a slope difference of 0.10 standard deviations, MTD would require 328 participants, Mayo-PACC would require 380 participants, and Kokmen STMS would require 418 participants, assuming a type I error rate of 0.05 and a ratio of subject-specific random slope variation to be 0.1 from a random effects model with random participant slopes and intercepts. Thus, MTD would reduce the sample size needed by 13.7% (Mayo-PACC) to 21.5% (STMS). Although remote digital assessments have many benefits, disadvantages are recognized. First, a lack of environmental control may lead to inconsistency and inaccurate measurements. Encouragingly, our results show that the reliability of MTD is minimally affected by self-reported potential test interferences. Second, some older adults may not have access to certain devices or may be uncomfortable using technology by themselves. 1 , 29 Multi-device platforms may help lessen this concern by allowing use of any available device the patient or participant are most comfortable with. The current results show that the reliability of the MTD is minimally affected by variation in device/input source type across sessions, although device consistency is recommended when feasible and location consistency may be important. It is important to note that the current study’s participants were predominately CU, White, non-Hispanic, and highly educated. Further research is needed to ensure generalizability of MTD to racial, ethnic, and socioeconomically diverse populations. In summary, the current study demonstrates that the MTD screening battery is a reliable assessment for tracking cognition over time, with moderate-to-good reliability. MTD reliability is comparable to in-person-administered neuropsychological tests as well as other digital cognitive assessments and is favorable compared to in-person mental status screening measures. Future studies are needed to determine the sensitivity of MTD to detect longitudinal cognitive decline. Funding & Acknowledgements Research reported in this publication was supported by the National Institute on Aging of the National Institutes of Health under Award Numbers R01AG081955, R21 AG073967, P30 AG062677, U01 AG006786, and R01 AG034676 (the Rochester Epidemiology Project). This work was also supported by the Kevin Merszei Career Development Award in Neurodegenerative Diseases Research IHO Janet Vittone, MD, the GHR Foundation, and the Mayo Foundation for Education and Research. The content is solely the responsibility of the authors and does not necessarily represent the official views of the National Institutes of Health or other sponsors. A Mayo Clinic invention disclosure has been submitted for the Stricker Learning Span and the Mayo Test Drive platform (NHS, JLS). We have no other conflicts of interest to disclose related to this work. The authors wish to thank the participants and staff at the Mayo Clinic Study of Aging and Mayo Alzheimer’s Disease Research Center. Disclosure Statement MHS, RDF, RTL, WZF and TJC have nothing to disclose. WKK reports grants from NIH during the conduct of the study. JLS reports grants from NIH during the conduct of the study. A Mayo Clinic invention disclosure has been submitted for the Stricker Learning Span and the Mayo Test Drive platform. JLS receives no personal compensation from any commercial entity. MaMM reports grants from NIH during the conduct of the study. JH reports personal fees from Parabon Nanolabs, Roche, AlzPath, Prothena, Caring Bridge and Wall-E and serves on Data Safety Monitoring Board/Advisory Boards for Caring Bridge and Wall-E, outside the submitted work. MiMM reports serving on scientific advisory boards and/or consulting for Acadia, Athira, Beckman Coulter, Biogen, Cognito Therapeutics, Eisai, Lilly, Merck, Neurogen Biomarking, Novo Nordisk, Roche, Siemens Healthineers and Sunbird Bio. JAL reports grants from NIH during the conduct of the study. PAA reports grants from NIH during the conduct of the study. GSD reports research support by NIH (R01AG089380, U01AG057195, U01NS120901, U19AG032438, P30AG062677). He serves as a consultant for Arialys Therapeutics, and as a Topic Editor (Dementia) for DynaMed (EBSCO). He is a co-Project PI for a clinical trial in anti-NMDAR encephalitis, which receives support from NIH/NINDS (U01NS120901) and Amgen Pharmaceuticals. He has developed educational materials for Continuing Education Inc, Ionis Pharmaceuticals, and MJH Life Sciences. He owns stock in ANI Pharmaceuticals. Dr. Day’s institution has received in-kind contributions for radiotracer precursors for tau-PET neuroimaging in studies of memory and aging (via Avid Radiopharmaceuticals, a wholly owned subsidiary of Eli Lilly). GSD reports no competing interests directly relevant to this work. NRGR reports grants from NIH during the conduct of the study. CRJ reports grants from NIH and grants from GHR Foundation during the conduct of the study, and he receives research support from the Alexander Family Alzheimer’s Disease Research Professorship of the Mayo Clinic. JGR reports serving on the Data and Safety Monitoring Board for StrokeNET NINDS, serves as site investigator for trials sponsored by Eisai and cognition therapeutics, and reports honoraria for serving as faculty member for American Academy of Neurology and IMPACT AD clinical trials course, outside the submitted work. RCP reports grants from NIH during the conduct of the study. RCP reports personal fees from Oxford University Press, UpToDate, Roche, Inc., Genentech, Inc., Eli Lilly and Co., Eisai, Inc., Novartis and Novo Nordisk, outside the submitted work. NHS reports grants from NIH during the conduct of the study. A Mayo Clinic invention disclosure has been submitted for the Stricker Learning Span and the Mayo Test Drive platform. NHS receives no personal compensation from any commercial entity. Data Availability All data produced in the present study are available upon reasonable request to the authors. CRediT Morgan A. Hughes: Writing – original draft, Writing – review and editing, Data curation, Visualization, Investigation Ryan D. Frank: Conceptualization, Supervision, Data curation, Methodology, Formal analysis, Visualization Rita L. Taylor: Supervision, Writing – review and editing Winnie Z. Fan: Formal analysis, Visualization Teresa J. Christianson: Data curation Walter K. Kremers: Conceptualization, Supervision, Methodology John L. Stricker: Data curation, Software, Writing – review and editing Mary M. Machulda: Supervision, Writing – review and editing, Investigation Jason Hassenstab: Conceptualization, Writing – review and editing Michelle M. Mielke: Funding acquisition, Writing – review and editing, Supervision John A. Lucas: Resources, Supervision, Writing – review and editing Paula A. Aduen: Resources, Supervision, Writing – review and editing Gregory S. Day: Resources, Writing – review and editing Neill R. Graff-Radford: Resources, Funding acquisition, Writing – review and editing Clifford R. Jack, Jr.: Conceptualization, Resources, Funding acquisition, Writing – review and editing Jonathan Graff-Radford: Resources, Funding acquisition, Writing – review and editing Ronald C. Petersen: Resources, Funding acquisition, Writing – review and editing, Supervision Nikki H. Stricker: Conceptualization, Funding acquisition, Project administration, Methodology, Data curation, Supervision, Writing – original draft, Writing – review and editing Footnotes Note. This work was presented at the 2024 Alzheimer’s Association International Conference (poster). Copyright 2025 Mayo Foundation for Medical Education and Research. All rights reserved. Abbreviations MTD Mayo Test Drive MTD Comp : Mayo Test Drive Test Battery Composite Score MTD Stricker Learning Span SLS Sum Stricker Learning Span Sum of Trials SYM Symbols Test SYM RT Symbols Test Average Correct Item Response Time in Seconds SYM AW Accuracy-Weighted Score that Weights SYM RT by Accuracy CU Cognitively Unimpaired Mayo-PACC Mayo Preclinical Alzheimer’s disease Cognitive Composite AVLT Rey’s Auditory Verbal Learning Test References 1. ↵ Patel JS , Christianson TJ , Monahan LT , et al. Usability of the Mayo Test Drive remote self-administered web-based cognitive screening battery in adults aged 35-100 with and without cognitive impairment . J Clin Exp Neuropsychol . Feb 20 2025 : 1 – 23 . doi: 10.1080/13803395.2025.2464633 OpenUrl CrossRef 2. ↵ Stricker NH , Twohy EL , Albertson SM , et al. Mayo-PACC: A parsimonious preclinical Alzheimer’s disease cognitive composite comprised of public-domain measures to facilitate clinical translation . Alzheimers Dement . Jun 2023 ; 19 ( 6 ): 2575 – 2584 . doi: 10.1002/alz.12895 OpenUrl CrossRef PubMed 3. ↵ Boots EA , Frank RD , Fan WZ , et al. Continuous Associations between Remote Self-Administered Cognitive Measures and Imaging Biomarkers of Alzheimer’s Disease . J Prev Alzheimers Dis . 2024 ; 11 ( 5 ): 1467 – 1479 . doi: 10.14283/jpad.2024.99 OpenUrl CrossRef 4. ↵ Stricker NH , Frank RD , Boots EA , et al. Mayo Normative Studies: regression-based normative data for remote self-administration of the Stricker Learning Span, Symbols Test, and Mayo Test Drive Screening Battery Composite and validation in individuals with mild cognitive impairment and dementia . Clin Neuropsychol . Mar 11 2025 : 1 – 30 . doi: 10.1080/13854046.2025.2469340 OpenUrl CrossRef 5. ↵ Stricker NH , Stricker JL , Frank RD , et al. Stricker Learning Span criterion validity: a remote self-administered multi-device compatible digital word list memory measure shows similar ability to differentiate amyloid and tau PET-defined biomarker groups as in-person Auditory Verbal Learning Test . J Int Neuropsychol Soc . Feb 2024 ; 30 ( 2 ): 138 – 151 . doi:Pii S1355617723000322 10.1017/S1355617723000322 OpenUrl CrossRef PubMed 6. ↵ Polk SE , Ohman F , Hassenstab J , et al. A scoping review of remote and unsupervised digital cognitive assessments in preclinical Alzheimer’s disease . NPJ Digit Med . May 10 2025 ; 8 ( 1 ): 266 . doi: 10.1038/s41746-025-01583-5 OpenUrl CrossRef PubMed 7. ↵ Koo TK , Li MY . A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research . J Chiropr Med . Jun 2016 ; 15 ( 2 ): 155 – 63 . doi: 10.1016/j.jcm.2016.02.012 OpenUrl CrossRef PubMed 8. ↵ Morris JC . The Clinical Dementia Rating (CDR): Current version and scoring rules . Neurology . Nov 1993 ; 43 ( 11 ): 2412 – 2414 . doi: 10.1212/WNL.43.11.2412-a OpenUrl CrossRef PubMed 9. ↵ Roberts RO , Geda YE , Knopman DS , et al. The Mayo Clinic Study of Aging: design and sampling, participation, baseline measures and sample characteristics . Neuroepidemiology . 2008 ; 30 ( 1 ): 58 – 69 . doi: 10.1159/000115751 OpenUrl CrossRef PubMed Web of Science 10. ↵ Petersen RC . Mild cognitive impairment as a diagnostic entity . J Intern Med. 2004 2004 ; 256 ( 3 ): 183 – 194 . doi: 10.1111/j.1365-2796.2004.01388.x . OpenUrl CrossRef PubMed Web of Science 11. ↵ American Psychiatric Association . Diagnostic and Statistical Manual of Mental Disorders (DSM-IV) . 4th ed. American Psychiatric Association ; 1994 . 12. ↵ Stricker JL , Corriveau-Lecavalier N , Wiepert DA , Botha H , Jones DT , Stricker NH . Neural network process simulations support a distributed memory system and aid design of a novel computer adaptive digital memory test for preclinical and prodromal Alzheimer’s disease . Neuropsychology . Sep 2023 ; 37 ( 6 ): 698 – 715 . doi: 10.1037/neu0000847 OpenUrl CrossRef PubMed 13. ↵ Stricker NH , Stricker JL , Karstens AJ , et al. A novel computer adaptive word list memory test optimized for remote assessment: Psychometric properties and associations with neurodegenerative biomarkers in older women without dementia . Alzheimers Dement (Amst) . 2022 ; 14 ( 1 ): e12299 . doi: 10.1002/dad2.12299 OpenUrl CrossRef 14. ↵ Nicosia J , Aschenbrenner AJ , Balota DA , et al. Unsupervised high-frequency smartphone-based cognitive assessments are reliable, valid, and feasible in older adults at risk for Alzheimer’s disease . J Int Neuropsychol Soc . Jun 2023 ; 29 ( 5 ): 459 – 471 . doi: 10.1017/S135561772200042X OpenUrl CrossRef PubMed 15. ↵ Delis DC , Kramer JH , Kaplan E , Ober BA . California Verbal Learning Test (2nd ed): Adult version, manual . Psychological Corporation ; 2000 . 16. ↵ Kokmen E , Smith GE , Petersen RC , Tangalos E , Ivnik RC . The short test of mental status: Correlations with standardized psychometric testing . Arch Neurol . Jul 1991 ; 48 ( 7 ): 725 – 8 . doi: 10.1001/archneur.1991.00530190071018 OpenUrl CrossRef PubMed Web of Science 17. ↵ Stricker NH , Lundt ES , Edwards KK , et al. Comparison of PC and iPad administrations of the Cogstate Brief Battery in the Mayo Clinic Study of Aging: Assessing cross-modality equivalence of computerized neuropsychological tests . Clin Neuropsychol . Aug 2019 ; 33 ( 6 ): 1102 – 1126 . doi: 10.1080/13854046.2018.1519085 OpenUrl CrossRef PubMed 18. ↵ Kochan NA , Heffernan M , Valenzuela M , et al. Reliability, Validity, and User-Experience of Remote Unsupervised Computerized Neuropsychological Assessments in Community-Living 55-to 75-Year-Olds . J Alzheimers Dis . 2022 ; 90 ( 4 ): 1629 – 1645 . doi: 10.3233/JAD-220665 OpenUrl CrossRef PubMed 19. ↵ Feenstra HEM , Murre JMJ , Vermeulen IE , Kieffer JM , Schagen SB . Reliability and validity of a self-administered tool for online neuropsychological testing: The Amsterdam Cognition Scan . J Clin Exp Neuropsychol . Apr 2018 ; 40 ( 3 ): 253 – 273 . doi: 10.1080/13803395.2017.1339017 OpenUrl CrossRef PubMed 20. ↵ Rigby T , Kavcic V , Shair SR , et al. Retest reliability and reliable change of community-dwelling Black/African American older adults with and without mild cognitive impairment using NIH Toolbox-Cognition Battery and Cogstate Brief Battery for laptop . J Int Neuropsychol Soc . Jan 2025 ; 31 ( 1 ): 42 – 52 . doi: 10.1017/S1355617724000444 OpenUrl CrossRef PubMed 21. ↵ Stenberg J , Karr JE , Karlsen RH , Skandsen T , Silverberg ND , Iverson GL . Examining Test-Retest Reliability and Reliable Change for Cognition Endpoints for the CENTER-TBI Neuropsychological Test Battery . Front Neurol . 2020 ; 11 : 541533 . doi: 10.3389/fneur.2020.541533 OpenUrl CrossRef PubMed 22. ↵ Weizenbaum EL , Soberanes D , Hsieh S , et al. Capturing learning curves with the multiday Boston Remote Assessment of Neurocognitive Health (BRANCH): Feasibility, reliability, and validity . Neuropsychology . Feb 2024 ; 38 ( 2 ): 198 – 210 . doi: 10.1037/neu0000933 OpenUrl CrossRef PubMed 23. ↵ Skirrow C , Meszaros M , Meepegama U , et al. Validation of a Remote and Fully Automated Story Recall Task to Assess for Early Cognitive Impairment in Older Adults: Longitudinal Case-Control Observational Study . JMIR Aging . Sep 30 2022 ; 5 ( 3 ): e37090 . doi: 10.2196/37090 OpenUrl CrossRef 24. ↵ Pedraza O , Smith GE , Ivnik RJ , et al. Reliable change on the Dementia Rating Scale . J Int Neuropsychol Soc . Jul 2007 ; 13 ( 4 ): 716 – 20 . doi: 10.1017/S1355617707070920 OpenUrl CrossRef PubMed Web of Science 25. ↵ Hensel A , Angermeyer MC , Riedel-Heller SG . Measuring cognitive change in older adults: reliable change indices for the Mini-Mental State Examination . J Neurol Neurosurg Psychiatry . Dec 2007 ; 78 ( 12 ): 1298 – 303 . doi: 10.1136/jnnp.2006.109074 OpenUrl Abstract / FREE Full Text 26. ↵ Spencer RJ , Wendell CR , Giggey PP , et al. Psychometric limitations of the mini-mental state examination among nondemented older adults: an evaluation of neurocognitive and magnetic resonance imaging correlates . Exp Aging Res . 2013 ; 39 ( 4 ): 382 – 97 . doi: 10.1080/0361073X.2013.808109 OpenUrl CrossRef PubMed Web of Science 27. Kiselica AM , Kaser AN , Webber TA , Small BJ , Benge JF . Development and Preliminary Validation of Standardized Regression-Based Change Scores as Measures of Transitional Cognitive Decline . Arch Clin Neuropsychol . Mar 10 2025 ; doi: 10.1093/arclin/acaf015 OpenUrl CrossRef 28. ↵ Shehab A , Abdulle A. Cognitive and autonomic dysfunction measures in normal controls, white coat and borderline hypertension . BMC Cardiovasc Disord . Jan 11 2011 ; 11 : 3 . doi: 10.1186/1471-2261-11-3 OpenUrl CrossRef PubMed 29. ↵ Nicosia J , Aschenbrenner AJ , Adams SL , et al. Bridging the Technological Divide: Stigmas and Challenges With Technology in Digital Brain Health Studies of Older Adults . Front Digit Health . 2022 ; 4 : 880055 . doi: 10.3389/fdgth.2022.880055 OpenUrl CrossRef View the discussion thread. Back to top Previous Next Posted September 29, 2025. Download PDF Supplementary Material Data/Code Email Thank you for your interest in spreading the word about medRxiv. NOTE: Your email address is requested solely to identify you as the sender of this article. Your Email * Your Name * Send To * Enter multiple addresses on separate lines or separate them with commas. You are going to email the following Reliability of remote self-administered web-based digital cognitive measures and comparison to in-person neuropsychological tests: Stricker Learning Span, Symbols Test and the Mayo Test Drive Screening Battery Composite Message Subject (Your Name) has forwarded a page to you from medRxiv Message Body (Your Name) thought you would like to see this page from the medRxiv website. Your Personal Message CAPTCHA This question is for testing whether or not you are a human visitor and to prevent automated spam submissions. Share Reliability of remote self-administered web-based digital cognitive measures and comparison to in-person neuropsychological tests: Stricker Learning Span, Symbols Test and the Mayo Test Drive Screening Battery Composite Morgan A. Hughes , Ryan D. Frank , Rita L. Taylor , Winnie Z. Fan , Teresa J. Christianson , Walter K. Kremers , John L. Stricker , Mary M. Machulda , Jason Hassenstab , Michelle M. Mielke , John A. Lucas , Paula A. Aduen , Gregory S. Day , Neill R. Graff-Radford , Clifford R. Jack Jr. , Jonathan Graff-Radford , Ronald C. Petersen , Nikki H. Stricker medRxiv 2025.09.26.25336467; doi: https://doi.org/10.1101/2025.09.26.25336467 Share This Article: Copy Citation Tools Reliability of remote self-administered web-based digital cognitive measures and comparison to in-person neuropsychological tests: Stricker Learning Span, Symbols Test and the Mayo Test Drive Screening Battery Composite Morgan A. Hughes , Ryan D. Frank , Rita L. Taylor , Winnie Z. Fan , Teresa J. Christianson , Walter K. Kremers , John L. Stricker , Mary M. Machulda , Jason Hassenstab , Michelle M. Mielke , John A. Lucas , Paula A. Aduen , Gregory S. Day , Neill R. Graff-Radford , Clifford R. Jack Jr. , Jonathan Graff-Radford , Ronald C. Petersen , Nikki H. Stricker medRxiv 2025.09.26.25336467; doi: https://doi.org/10.1101/2025.09.26.25336467 Citation Manager Formats BibTeX Bookends EasyBib EndNote (tagged) EndNote 8 (xml) Medlars Mendeley Papers RefWorks Tagged Ref Manager RIS Zotero Tweet Widget Facebook Like Google Plus One Subject Area Psychiatry and Clinical Psychology Subject Areas All Articles Addiction Medicine (570) Allergy and Immunology (864) Anesthesia (301) Cardiovascular Medicine (4445) Dentistry and Oral Medicine (444) Dermatology (383) Emergency Medicine (609) Endocrinology (including Diabetes Mellitus and Metabolic Disease) (1513) Epidemiology (15234) Forensic Medicine (30) Gastroenterology (1127) Genetic and Genomic Medicine (6610) Geriatric Medicine (669) Health Economics (999) Health Informatics (4545) Health Policy (1370) Health Systems and Quality Improvement (1613) Hematology (543) HIV/AIDS (1266) Infectious Diseases (except HIV/AIDS) (15925) Intensive Care and Critical Care Medicine (1104) Medical Education (623) Medical Ethics (147) Nephrology (668) Neurology (6612) Nursing (346) Nutrition (999) Obstetrics and Gynecology (1147) Occupational and Environmental Health (957) Oncology (3340) Ophthalmology (975) Orthopedics (369) Otolaryngology (420) Pain Medicine (436) Palliative Medicine (130) Pathology (665) Pediatrics (1694) Pharmacology and Therapeutics (693) Primary Care Research (714) Psychiatry and Clinical Psychology (5458) Public and Global Health (9243) Radiology and Imaging (2204) Rehabilitation Medicine and Physical Therapy (1370) Respiratory Medicine (1197) Rheumatology (596) Sexual and Reproductive Health (715) Sports Medicine (530) Surgery (713) Toxicology (99) Transplantation (289) Urology (265) (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'a0211e237efb8e2e',t:'MTc3OTg0Mzk5NA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();