Patients and their families often ask clinicians to estimate when full-time care (FTC) will be needed after Alzheimer's Disease (AD) is diagnosed. Although a few algorithms predictive algorithms for duration to FTC have been created, these have not been widely adopted for clinical use due to questions regarding precision from limited sample sizes and lack of an easy, user friendly prediction model. Our objective was to develop a clinically relevant, data-driven predictive model using machine learning to estimate time to FTC in AD based on information gathered from a) clinical interview alone, and b) clinical interview plus neuropsychological data.

The National Alzheimer's Coordinating Center dataset was used to examine 3,809 participants (M age at AD diagnosis = 76.05, SD = 9.76; 47.10% male; 87.20% Caucasian) with AD dementia who were aged >50 years, had no history of stroke, and not dependent on others for basic activities of daily living at time of diagnosis based on qualitative self or informant report. To develop a predictive model for time until FTC, supervised machine learning algorithms (e.g., gradient descent, gradient boosting) were implemented. In Model 1, 29 variables captured at the time of AD diagnosis and often gathered in a clinical interview, including sociodemographic factors, psychiatric conditions, medical history, and MMSE, were included. In Model 2, additional neuropsychological variables assessing episodic memory, language, attention, executive function, and processing speed were added. To train and test the algorithm(s), data were split into a 70:30 ratio. Prediction optimization was examined via cross validation using 1000 bootstrapped samples. Model evaluation included assessment of confusion matrices and calculation of accuracy and precision.

The average time to requiring FTC after AD diagnosis was 3.32 years (Range = 0.53-14.57 years). For the clinical interview only model (Model 1), younger age of onset, use of cholinesterase inhibitor medication, incontinence, and apathy were among the clinical variables that significantly predicted duration to FTC, with the largest effects shown for living alone, a positive family history of dementia, and lower MMSE score. In Model 2, the clinical predictors remained significant, and lower Boston Naming Test and Digit-Symbol Coding scores showed the largest effects in predicting duration to FTC among the neuropsychological measures. Final prediction models were further tested using five randomly selected cases. The average estimated time to FTC using the clinical interview model was within an average of 5.2 months of the recorded event and within an average of 5.8 months for the model with neuropsychological data.

Predicting when individuals diagnosed with AD will need FTC is important as the transition often carries significant financial costs related to caregiving. Duration to FTC was predicted by clinical and neuropsychological variables that are easily obtained during standard dementia evaluations. Implementation of the model for prediction of FTC in cases showed encouraging prognostic accuracy. The two models show promise as a first step towards creation of a user friendly prediction calculator that could help clinicians better counsel patients on when FTC after AD diagnosis may occur, though the development of separate models for use in more diverse populations will be essential.

Definitive diagnosis of Alzheimer’s disease (AD) is often unavailable, so clinical diagnoses with some degree of inaccuracy are often used in research instead. When researchers test methods that may improve clinical accuracy, the error in initial diagnosis can penalize predictions that are more accurate to true diagnoses but differ from clinical diagnoses. To address this challenge, the current study investigated the use of a simple bias adjustment for use in logistic regression that accounts for known inaccuracy in initial diagnoses.

A Bayesian logistic regression model was developed to predict unobserved/true diagnostic status given the sensitivity and specificity of an imperfect reference. This model considers cases as a mixture of true (with rate = sensitivity) and false positives (rate = 1 - specificity) while controls are mixtures of true (rate = specificity) and false negatives (rate = 1 - sensitivity). This bias adjustment was tested using Monte Carlo simulations over four conditions that varied the accuracy of clinical diagnoses. Conditions utilized 1000 iterations each generating a random dataset of n = 1000 based on a true logistic model with an intercept and three arbitrary predictors. Coefficients for parameters were randomly selected in each iteration and used to produce a set of two diagnoses: true diagnoses and observed diagnoses with imperfect accuracy. Sensitivity and specificity of the simulated clinical diagnosis varied with each of the four conditions (C): C1 = (0.77, 0.60), C2 = (0.87, 0.44), C3 = (0.71, 0.71), and C4 = (0.83, 0.55), which are derived from published values for clinical AD diagnoses against autopsy-confirmed pathology. Unadjusted and bias-adjusted logistic regressions were then fit to the simulated data to determine the models’ accuracy in estimating regression parameters and prediction of true diagnosis.

Under all conditions, the bias-adjusted logistic regression model outperformed its unadjusted counterpart. Root mean square error (the variability of estimated coefficients around their true parameter values) ranged from 0.23 to 0.79 for the unadjusted model versus 0.24 to 0.29 for the bias-adjusted model. The empirical coverage rate (the proportion of 95% credible intervals that include their true parameter) ranged from 0.00 to 0.47 for the unadjusted model versus 0.95 to 0.96 for the bias-adjusted model. Finally, the bias-adjusted model produced the best overall diagnostic accuracy with correct classification of true diagnostic values about 78% of the time versus 62-72% without adjustment.

Results of this simulation study, which used published AD sensitivity and specificity statistics, provide evidence that bias-adjustments to logistic regression models are needed when research involves diagnoses from an imperfect standard. Results showed that unadjusted methods rarely identified true effects with credible intervals for coefficients including the true value anywhere from never to less than half of the time. Additional simulations are needed to examine the bias-adjusted model’s performance under additional conditions. Future research is needed to extend the bias adjustment to multinomial logistic regressions and to scenarios where the rate of misdiagnosis is unknown. Such methods may be valuable for improving detection of other neurological disorders with greater diagnostic error as well.

A diagnosis of mild cognitive impairment (MCI) requires memory complaint and objective memory impairment. However, some individuals report subjective memory complaints (SMC) despite having intact memory performance, while others demonstrate subtle impairment on memory testing but have no memory complaints; neither case would meet criteria for MCI. This study aimed to compare memory performances over time in individuals who do not meet traditional MCI criteria to those with normal cognition and those who converted to MCI.

Diagnoses for a longitudinal sample from the Texas Alzheimer’s Research and Care Consortium were reviewed by a consensus panel of neuropsychologists and neurologists and reclassified at time of last visit. Diagnostic categories included SMC (i.e., memory complaint but no impairment on testing), objective cognitive impairment but no complaint (Impaired but not MCI), normal control (NC), MCI, and dementia. In this study, 827 participants were divided into 4 groups: 1) NC over 5 visits (n=511, 71% female; 42% Latinx/Hispanic), 2) baseline NC to amnestic MCI (n=62; 63% female; 57% Latinx/Hispanic), 3) SMC at last visit (n=133; 58% female; 70% Latinx/Hispanic), and 4) impaired but not MCI at last visit (n=121; 71% female; 60% Latinx/Hispanic). A memory composite (z-score) was created from the CERAD list-learning task (immediate, delayed, and recognition-discrimination) and Wechsler Memory Scale (Immediate and Delayed Logical Memory and Visual Reproduction) to evaluate memory performance over time. A linear mixed-model adjusting for age, education, sex, ethnicity, and number of APOE e4 alleles evaluated memory performance across 5 visits for the groups. To assess if depression followed a similar course, a linear mixed-model evaluated Geriatric Depression Scale (GDS) scores over time.

At baseline, groups differed by age (F=22.82; p<.001), education (F=8.60; p<.001), MMSE scores (F=9.38; p<.001), GDS-30 scores (F=3.56; p=.015), and memory composites (F=24.29; p<.001). A significant group X time interaction was observed (F=4.83, p<.001). Memory performance improved in both the SMC and the NC groups, remained stable in the impaired but not MCI group, and declined (as expected) in those who converted to amnestic MCI. Depression scores also showed a significant group X time interaction (F=2.43; p=.004), in which the NC to MCI group endorsed slightly more depression symptoms over time, while other groups declined or remained stable.

Memory trajectories in this diverse sample differed across groups. Individuals with SMC but without objective memory impairment and normal controls showed some improvement in memory over time, presumably due to practice effects. Those with subtle memory impairments but no complaint (i.e., did not meet MCI criteria) remained stable and those who converted to amnestic MCI had worse memory across time. The stability of memory performances in the impaired not MCI group suggests these subtle memory inefficiencies may be longstanding or unperceived. However, because our sample achieved retrospective diagnoses of SMC and impaired not MCI, it will be important for future studies to prospectively follow these groups to determine which risk factors may predict progression to MCI and what impact ethnicity may have on these trajectories.

Learning curve patterns on list-learning tasks can help clinicians determine the nature of memory difficulties, as an “impaired” score may actually reflect attention and/or executive difficulties rather than a true memory impairment. Though such pattern analysis is often qualitative, there are quantitative methods to assess these concepts that have been generally underutilized. This study aimed to develop a model that decomposes learning over repeated trials into separate cognitive processes and then include other testing data to predict performance at each trial as a function of general cognitive functioning.

Data for CVLT-II learning trials were obtained from an outpatient neuropsychology service within an academic medical center referred for clinical reasons. Participants with a cognitive diagnosis of non-demented (ND) or probable Alzheimer’s disease (AD) were included. The final sample consisted of 323 ND [Mage = 58.6 (14.8); Medu = 15.4 (2.7); 55.7% female] and 915 AD [Mage = 72.6 (9.0); Medu = 14.2 (3.1); 60.1% female cases. A Bayesian non-linear beta-binomial multilevel model was used, which uses three parameters to predict CVLT-II recall-by-trial: verbal attention span (VAS), maximal learning potential (MLP), and learning rate (LR). Briefly, VAS predicts expected first trial performance while MLP, conversely, predicts the expected best performance as trials are repeated, and LR weights the influence of VAS versus MLR over repeated trials. Predictors of these parameters included age, education, sex, race, and clinical diagnosis, in addition to raw scores on Trail Making Test Parts A and B, phonemic (FAS) fluency, animal fluency, Boston Naming Test, Wisconsin Card Sorting Test (WCST) Categories Completed, and then age-adjusted scaled scores from WAIS-IV Digit Span, Block Design, Vocabulary, and Coding. Random intercepts were included for each parameter and extracted for comparison of residual differences by diagnosis.

The model explained 84% of the variance in CVLT-II raw scores. VAS reduced with age and time-to-complete Trails B but improved with both verbal fluencies and confrontation naming. MLP increased as a function of WAIS Digit Span, animal fluency, confrontation naming, and WCST categories completed. Finally, LR was greater for females and WAIS-IV Coding and Vocabulary performances but reduced with age. Participants with AD had lower estimates of all three parameters: Cohen’s d = 2.49 (VAS) - 3.48 (LR), though including demographic and neuropsychological tests attenuated differences, Cohen’s d = 0.34 (LR) - 0.95 (MLP).

The resulting model highlights how non-memory neuropsychological deficits affect list-learning test performance. At the same time, the model demonstrated that memory patterns on the CVLT-II can still be identified beyond other confounding deficits since having AD affected all parameters independent of other cognitive impairments. The modeling approach can generate conditional learning curves for individual patient data, and when multiple diagnoses are included in the model, a person-fit statistic can be computed to return the mostly likely diagnosis for an individual. The model can also be used in research to quantify or adjust for the effect of other patient data (e.g., neuroimaging, biomarkers, medications).

Episodic memory functioning is distributed across two brain circuits, one of which courses through the dorsal anterior cingulate cortex (dACC). Thus, delivering non-invasive neuromodulation technology to the dACC may improve episodic memory functioning in patients with memory problems such as in amnestic mild cognitive impairment (aMCI). This preliminary study is a randomized, double-blinded, sham-controlled clinical trial to examine if high definition transcranial direct current stimulation (HD-tDCS) can be a viable treatment in aMCI.

Eleven aMCI participants, of whom 9 had multidomain deficits, were randomized to receive 1 mA HD-tDCS (N=7) or sham (N=4) stimulation. HD-tDCS was applied over ten 20-minute sessions targeting the dACC. Neuropsychological measures of episodic memory, verbal fluency, and executive function were completed at baseline and after the last HD-tDCS session. Changes in composite scores for memory and language/executive function tests were compared between groups (one-tailed t-tests with a = 0.10 for significance). Clinically significant change, defined as > 1 SD improvement on at least one test in the memory and non-memory domains, was compared between active and sham stimulation based on the frequency of participants in each.

No statistical or clinically significant change (N-1 X2; p = 0.62) was seen in episodic memory for the active HD-tDCS (MDiff = 4.4; SD = 17.1) or sham groups (MDiff = -0.5; SD = 9.7). However, the language and executive function composite showed statistically significant improvement (p = 0.04; MDiff = -15.3; SD = 18.4) for the active HD-tDCS group only (Sham MDiff = -5.8; SD = 10.7). Multiple participants (N=4) in the active group had clinically significant enhancement in language and executive functioning tests, while nobody in the sham group did (p = 0.04).

HD-tDCS targeting the dACC had no direct benefit for episodic memory deficits in aMCI based on preliminary findings for this ongoing clinical trial. However, significant improvement in language and executive function skills occurred in response to HD-tDCS, suggesting HD-tDCS in this configuration has promising potential as an intervention for language and executive function deficits in MCI.

Early detection of mild cognitive impairment (MCI) and dementia is crucial for initiation of treatment and access to appropriate care. While comprehensive neuropsychological assessment is often an intrinsic part of the diagnostic process, access to services may be limited and cannot be utilized effectively on a large scale. For these reasons, cognitive screening instruments are used as brief and cost-effective methods to identify individuals who require further evaluation. Novel technologies and automated software systems to screen for cognitive changes in older individuals are evolving as new avenues for early detection. The present study presents preliminary data on a new technology that uses automated linguistic analysis software to screen for MCI and dementia.

Data were collected from 148 Spanish-speaking individuals recruited in Spain (MAge=74.4, MEducation=12.93, 56.7% females) of whom 78 were diagnosed as cognitively normal [CN; Mmmse = 28.51 (1.39)], 49 as MCI [MMMSE = 25.65 (2.94)], and 21 as all-cause dementia [MMMSE = 22.52 (2.06)]. Participants were recorded performing various verbal tasks [Animal fluency, phonemic (F) fluency, Cookie Theft Description, and CERAD list learning task]. Recordings were processed via text-transcription and sound signal processing techniques to capture neuropsychological variables and audio characteristics. Features from each task were used in the development of an algorithm (for that task) to compute a score between 0 or 1 (healthy to more impairment), and a fifth algorithm was constructed using audio characteristics from all tasks. These five classifiers were combined algorithmically to provide the final algorithm. Receiver Operating Characteristic (ROC) analysis was conducted to determine sensitivity and specificity of predicted algorithm performance [CN vs. impaired (MCI or dementia)] against clinical diagnoses, and additional general linear modeling was used to test whether age, sex, education, and multilingualism significantly predicted logistically transformed weighted algorithm scores.

Scores were transformed to logit scores, with significant differences in mean logit scores between all groups (p <.001). Logit-inverse transformation of mean logit scores (possible range 0 -1) resulted in values of 0.06 for CN, 0.90 for MCI, and 0.99 for all-cause dementia groups. ROC curve analyses revealed the algorithm obtained a total area under the curve of 0.92, with an overall accuracy of 86.8%, a sensitivity of 0.92, and specificity of 0.82. Age was identified as a significant predictor (beta = 0.22; p <0.01) of algorithm output, whereas years of education (beta = -0.04; p = 0.64), sex (beta = 0.38; p = 0.02, did not survive correction for type-1 error), and multilingualism (beta = -0.24; p = 0.22) were non-significant.

These findings provide initial support for the utility of an automated speech analysis algorithm to detect cognitive impairment quickly and efficiently in a Spanish-speaking population. Although sociodemographic variables were not included in the algorithm, age significantly predicted algorithm output, and should be further explored to determine if age-adjusted formulas would improve algorithm accuracy for younger versus older individuals. Additional research is needed to validate this novel methodology in other languages, as this may represent a promising cross-cultural screening method for MCI and dementia detection.

Higher baseline dispersion (intra-individual variability) across neuropsychological test scores at a single time-point has been associated with more rapid cognitive decline, onset of Mild Cognitive Impairment (MCI) and Alzheimer’s disease (AD), faster rates of hippocampal and entorhinal atrophy, and increased AD neuropathology. Comparison between predictions made from test score dispersion within a cognitive domain versus global, cross-domain dispersion is understudied. Global dispersion may be influenced by ability-and test-specific characteristics. This study examined the performance of global versus domain-specific dispersion metrics to identify which is most predictive of cognitive decline over time.

Data for baseline and five follow-up visits of 308 participants with normal cognition (Mage=73.90, SD=8.12) were selected from the National Alzheimer’s Coordinating Center (NACC) Dataset. Participants were required to have no focal neurological deficits, or history of depression, stroke, or heart attack. Diagnoses and progression to MCI and/or dementia were determined at each visit through consensus conferences. Raw neuropsychological scores were standardized using NACC norms. Global baseline dispersion was defined as the intraindividual standard deviation (ISD) across the 10 scores in the NACC battery. Domain-specific dispersions were calculated by constructing composites and ISD was computed across tests sampling their respective domains (executive functioning/attention/processing speed [EFAS], language, and memory; see Table 1 for details on these tests). Higher values on each of these metrics reflect greater dispersion. Multinomial logistic regression model fit statistics and parameter estimates were compared across four different models (global, EFAS, Language, and Memory dispersion) covarying for age, years of education, sex, race, ethnicity, and ApoE4 status. Models were compared using the Likelihood Ratio Test (LRT) and the Akaike Information Criteria (AIC) of Models statistics.

Of the 308 participants, 70 (22.7%) progressed to MCI, and 82 (26.6%) progressed to dementia. Tables 1 and 2 show the results of the logistic regressions for the four models. All models fit the data well, with statistically significant predictions of conversion. Model 1 (global dispersion) showed a better fit than domain-specific models of dispersion per LRT and AIC values. Consistent with the results from mean differences between groups, parameter estimates showed that only global dispersion and EFAS dispersion significantly predicted conversion to dementia (when included with other covariates in models), with higher dispersion reflecting a greater risk of conversion.

In this sample, baseline global and EFAS dispersion measures significantly predicted conversion to dementia. Although global dispersion was a stronger predictor of dementia progression, findings suggest that executive functioning performance may be driving this relationship. A single index of global variability, from the calculation of standard deviation across test scores, may be supplementary for clinicians when distinguishing individuals at risk for dementia progression. None of the models were predictive of conversion to MCI. Further research is required to examine cognitive variability differences among patients who progress to MCI and patient-specific factors that may relate to test score dispersion and its utility in predicting the progression of symptoms.