Computer detection of cognitive impairment and associated neuropsychiatric dimensions from the content analysis of verbal samples

Performance of the Automated Neuropsychological Assessment Metrics (ANAM) in detecting cognitive impairment in heart failure patients

OBJECTIVE

Evaluate capacity of the Automated Neuropsychological Assessment Metrics (ANAM) to detect cognitive impairment (CI) in heart failure (HF) patients.

BACKGROUND

CI is a key prognostic marker in HF. Though the most widely used cognitive screen in HF, the Mini-Mental State Examination (MMSE) is insufficiently sensitive. The ANAM has demonstrated sensitivity to cognitive domains affected by HF, but has not been assessed in this population.

METHODS

Investigators administered the ANAM and MMSE to 57 HF patients, compared against a composite model of cognitive function.

RESULTS

ANAM efficiency (p < .05) and accuracy scores (p < .001) successfully differentiated CI and non-CI. ANAM efficiency and accuracy scores classified 97.7% and 93.0% of non-CI patients, and 14.3% and 21.4% with CI, respectively.

CONCLUSIONS

The ANAM is more effective than the MMSE for detecting CI, but further research is needed to develop a more optimal cognitive screen for routine use in HF patients.

Learning diagnostic models using speech and language measures

We describe results that show the effectiveness of machine learning in the automatic diagnosis of certain neurodegenerative diseases, several of which alter speech and language production. We analyzed audio from 9 control subjects and 30 patients diagnosed with one of three subtypes of Frontotemporal Lobar Degeneration. From this data, we extracted features of the audio signal and the words the patient used, which were obtained using our automated transcription technologies. We then automatically learned models that predict the diagnosis of the patient using these features. Our results show that learned models over these features predict diagnosis with accuracy significantly better than random. Future studies using higher quality recordings will likely improve these results.

Automated Neuropsychological Assessment Metrics (Anam) and Woodcock-Johnson III Tests of Cognitive Ability: A Concurrent Validity Study

This study examines the relationship between a computerized neuropsychological assessment battery, the Automated Neuropsychological Assessment Metrics (ANAM) and a widely used ability measure, Woodcock-Johnson III Tests of Cognitive Ability (WJ-III). Results indicated substantial relationship between the ANAM throughput (accuracy/response time) scores and the WJ-III Cognitive Efficiency cluster. An unexpectedly strong relationship was evident between accuracy scores on the ANAM Logical Reasoning scale and the WJ-III General Intellectual Ability score, purporting to measure the g factor. The findings support the viability of the ANAM as a time- and cost-effective tool for appraisal of cognitive function.

Initial validation of the pediatric automated neuropsychological assessment metrics for CHILDHOOD-ONSET systemic lupus erythematosus

OBJECTIVE

To evaluate the concurrent validity and diagnostic accuracy of the pediatric Automated Neuropsychological Assessment Metrics (Ped-ANAM) when used in childhood-onset systemic lupus erythematosus (SLE).

METHODS

Formal neuropsychological testing and the Ped-ANAM were performed on 27 children with SLE who had not been previously diagnosed with neuropsychiatric SLE. Performance when completing the 10 Ped-ANAM tests was based on accuracy (AC), mean time to correct response, coefficient of variation of the time required for a correct response (CVc), and throughput. Formal neuropsychological testing was used as a criterion standard for diagnosing neurocognitive dysfunction (NCD; yes/no).

RESULTS

NCD was common and present in 16 (59%) of 27 participants. Ped-ANAM performance parameters were often moderately correlated with the Z scores on formal neuropsychological testing. The NCD group differed significantly (P < 0.05) from the normal cognition group in 3 Ped-ANAM tests: CVc with mathematical processing (MTH-CVc), AC with continuous performance test (CPT-AC), and CVc with spatial processing (SPD-CVc). Areas under the receiver operating curves (AUCs) ranged between 0.75 and 0.84 when each of these parameters (CPT-AC, MTH-CVc, SPD-CVc) was used to identify NCD independently. The AUC was improved to 0.96 for the combined assessment.

CONCLUSION

The Ped-ANAM has concurrent validity when used in children with SLE. Initial validation suggests that the Ped-ANAM could be a useful screening tool for NCD in children with SLE.

The detection of neurocognitive decline in schizophrenia using the Mindstreams Computerized Cognitive Test Battery

BACKGROUND

The Mindstreams Computerized Cognitive Test Battery (Mindstreams) is a standardized computer-based battery that was designed for widespread clinical and research use. The capability of Mindstreams to test cognitive impairment in schizophrenia has yet to be evaluated. The aim of the present study was to determine the ability of Mindstreams in detecting cognitive dysfunction in schizophrenia patients and to compare it to the Cambridge Neuropsychological Test Automated Battery (CANTAB).

METHOD

Fifty-five schizophrenia patients and 63 healthy subjects were enrolled in the study. The Positive and Negative Syndrome Scale (PANSS) was used to quantify symptom severity. Neurocognitive functions were assessed using Mindstreams and CANTAB.

RESULTS

The schizophrenia patients scored significantly more poorly than healthy subjects on all tests comprising the Mindstreams battery. Comparable tasks of the Mindstreams and CANTAB batteries significantly correlated on raw scores and the standardized cognitive indices. The Mindstreams executive function tasks had significant correlations with the PANSS negative, autistic preoccupation and activation cluster scores, and with global functioning. Two-week test-retest reliability correlations were all significant (N=17, p<0.05-p<0.001).

CONCLUSIONS

This study indicates that Mindstreams is reliable in assessing the cognitive function of patients with schizophrenia and may play a role in standardizing the cognitive assessment of these patients in clinical and research settings.

GENDER DIFFERENCES IN PERFORMANCE ON THE STROOP TEST

This study assessed differences in gender performance among Kuwaiti male and women on the Stroop Test (Stroop, 1935). Participants were 504 university students, 122 men and 382 women (age M= 21:0, SD= 2.7 yrs). Prior studies have shown that females by and large display differential performance (shorter latencies) from males on the word card, color card, and color word card of the Stroop Test. Results indicate that the Kuwaiti women read faster on the color card than did the males, and especially were faster with intercepting three cards of tests (interaction effect). Gender differences were observed in the color card and color-word card tests but not significantly for the word card test. The results do substantiate the gender difference in Stroop color and interference.

Computerized content analysis of speech plus speech recognition in the measurement of neuropsychiatric dimensions

The Psychiatric Content Analysis and Diagnosis (PCAD) program performs automated content analysis of machine-readable transcriptions of speech samples to measure the magnitude of neuropsychiatric states and traits. Technological advances provided by computerized speech recognition may offer a possible alternative to labor-intensive manual transcription for preparation of samples for PCAD processing. To test this hypothesis, 25 digitally recorded verbal samples were transcribed both manually and by a commercially available speech recognition software package, and the transcriptions scored by PCAD. The inter-correlations between scores derived from the two different methods of transcriptions offer mixed results, with values ranging from a high of 0.920 to a low of -0.119.

Computerized Neuropsychiatric Assessment of Geriatric Subjects by Content Analysis of Brief Samples of Their Speech

The life expectancy of people living in the United States is increasing. Are very elderly individuals compromised mentally and physically in comparison to much younger persons? The purpose of this study was to test the efficacy of a computerized program applicable to the content analysis of 5-minute speech samples obtained from a group of individuals 90 years of age and older and to compare the results with those previously obtained in younger people with respect to their mental capacities in terms of a set of diverse neuropsychiatric dimensions. After obtaining informed consent from 26 elderly people, recorded verbal samples were elicited from each individual in response to purposely ambiguous instructions to talk for 5 minutes about any interesting or dramatic personal life experiences. The transcripts of their speech samples were digitized on a computer diskette and processed on the computer program. The computer program compared the scores obtained on each verbal sample with norms obtained on 15 previously validated content-analysis scales from individuals ranging in age from 5 to 80. The norms on these content-analysis scales are different for children (aged 5-10) and adults (aged 11-80). The computerized content-analysis scores obtained from this elderly cohort reveal plausible deviations from the norms for younger people.