Speech, Linguistic and Acoustic Markers in Parkinson's Disease: Complete Statistical Analysis

1. Trial at a Glance

This page covers the registry results for Speech, Linguistic and Acoustic Markers in Parkinson's Disease (NCT04273672), a registered phase not stated study. The primary outcome is Mild Cognitive Impairment.

2. Clinical Question

The study asks whether features of speech and language can provide information about cognitive function in Parkinson’s disease and help predict cognitive decline. It also describes exploring relationships between genetic factors, speech, and cognitive status. The primary outcome listed in the registry record is mild cognitive impairment at baseline, classified using Movement Disorders Society Task Force Level II Criteria.

The stated interest in predicting cognitive decline is broader than the listed primary outcome. A baseline classification can describe cognitive status at assessment, but by itself does not establish how well a marker predicts later change. The registry record does not report a result for prediction of decline.

3. Trial Design

This is a completed assessment study sponsored by the University of Massachusetts, Worcester. The registry record lists an enrollment of 58 and a study start date of 2020-01-13, with primary completion on 2023-09-01. It describes participants with Parkinson’s disease and a control group of people without Parkinson’s disease. The record does not state how participants were allocated to these groups.

The listed procedures are a cognitive battery; voice, speech and language analysis; questionnaires and clinical assessments; and DNA analysis. The brief summary describes administering speech tasks and cognitive assessments to participants with Parkinson’s disease and healthy controls, alongside exploration of genetic associations. These procedures indicate an assessment-focused study rather than a randomized comparison of treatments.

The primary outcome is mild cognitive impairment at baseline. Its population description says the baseline cohort was analyzed as 49 participants, then notes that one participant with dementia was excluded from outcome measure reporting, leaving outcome data for 48 participants. The registry record does not explain how the enrollment of 58 relates to the baseline cohort of 49. That difference should not be assigned a cause without further information.

The record lists two outcome measures and no analysis records. It does not report outcome counts, estimates of association, or statistical comparisons. Although the study’s stated aims include identifying markers and predicting decline, the listed baseline endpoint is a classification of cognitive status at one assessment time. The registry record does not describe the timing or results of follow-up assessments for cognitive decline. Because allocation is not stated and the groups are not a like-for-like control comparison, differences between groups could not be interpreted as effects of an assigned intervention.

4. Participant Flow and Accounting

The registry reports how participants moved through each stage of the study. All counts below are exactly as posted; missing counts are not inferred from other stages.

Overall Study

Analysis population for the primary outcome, as defined in the registry: The entire baseline cohort was analyzed (n=49). Per pre-specified exclusion criteria, one participant determined to have dementia (n=1) was excluded from outcome measure analysis reporting, thus the outcome measure data represents n=48 participants.

5. Baseline Characteristics

The table reproduces the baseline characteristics posted in the registry, which describe the participants analysed at baseline and help show whether the randomized groups were comparable.

Population: Analysis population is the same as the assignment information, all enrolled participants were analyzed. One participant could not be appropriately categorized into the cognitive subgroups, thus the number of participants with cognitive categorization was 48.

6. Primary Endpoint

The registry lists the primary outcome as Mild Cognitive Impairment, measured over baseline.

The primary endpoint is the count of participants classified as having mild cognitive impairment at baseline. Classification is described as using Movement Disorders Society Task Force Level II Criteria. The measure is reported in participants, and its stated timeframe is baseline.

This endpoint gives a categorical description of cognitive status in the assessed cohort. In general, a binary classification records whether each participant meets a defined criterion or does not; the count can then describe how many participants in a stated population meet that criterion. Here, the registry record does not report the number meeting the criteria, so the outcome distribution cannot be described from the record.

The population description states that the baseline cohort was 49 participants and that one participant determined to have dementia was excluded from outcome measure reporting. It therefore identifies 48 participants as contributing to the outcome measure data. The reason for the stated exclusion is part of the registry description; the record does not provide further details about classification procedures or how borderline cases were handled.

A baseline mild cognitive impairment measure is relevant to a study asking whether speech and language features relate to cognitive function. However, it is not, by itself, a measure of subsequent cognitive decline. The registry record does not report a longitudinal outcome or the results needed to assess prediction over time. It also does not report the endpoint count, an effect estimate, or an uncertainty interval.

7. Why No Re-analysis Is Shown

8. Statistical Interpretation

9. Statistical Methods Explained

The statistical information in the registry record is limited. It identifies a participant-count endpoint and describes the populations used for outcome and safety reporting, but it does not report outcome values or analysis results. The explanations below distinguish general statistical concepts from what the record actually states.

What does a participant count represent?

In general, a binary outcome classifies each participant into one of two categories, such as meeting or not meeting a stated criterion. A count reports how many participants fall into the category of interest. To interpret such a count, readers need the outcome definition and the number of participants assessed. The registry record names the mild cognitive impairment criteria and identifies 48 participants in outcome reporting, but it does not state the number who met the criteria.

A count alone is not an estimate of how common an outcome is unless its denominator is also known. Even with the denominator, a count or proportion describes the assessed sample; uncertainty remains about how well it represents a broader population. In general, a confidence interval expresses a range of values compatible with the data under a statistical model. No confidence interval for the primary outcome is reported in the registry record, so its precision cannot be evaluated from the record.

What can a group comparison show?

The study describes a Parkinson’s disease group and a control group without Parkinson’s disease. The registry record states that allocation is not stated and that the arms are not a like-for-like control comparison. In general, random allocation can support causal interpretation by balancing factors across groups on average, whereas an assessment comparison without random allocation can be affected by differences between the groups. This does not mean a nonrandomized comparison has no descriptive value; it means that observed differences should not automatically be attributed to a causal effect.

No statistical comparison between the groups is reported. The record gives no estimate of a difference or association and no measure of its uncertainty. It is therefore not possible to determine from the registry record whether the groups differed on the primary outcome, whether a speech measure was associated with cognition, or how large or precise any such relationship might be.

How should the analysis reporting be read?

The record lists two outcome measures and zero analysis records. The number of analysis records is a statement about what appears in the registry record; it is not proof that investigators conducted no analyses. Without reported estimates and methods, readers cannot assess model choice, adjustment for participant characteristics, handling of repeated measures, or the treatment of missing observations. Those details are not reported in the registry record.

In general, statistical models should match the outcome and the study question. A binary outcome can be analyzed using methods suited to categories, while a continuous speech measure may require a different model. If observations are more variable than a simple model expects, over-dispersion can make standard errors too small and uncertainty intervals too narrow unless the analysis accounts for it. This is a general point; the registry record does not report a model, a dispersion assessment, or an analysis of speech measurements.

For an estimate to be interpretable, readers also need to know which participants contributed to it, how outcomes were defined, and whether the estimate was adjusted. The record identifies an outcome population of 48 after one participant with dementia was excluded, but it does not describe additional exclusions, missing observations, or analytic adjustments. The baseline population description does not establish that every other planned assessment was complete.

What do planning illustrations mean?

The registry description of planning illustrations says they are based on the observed effect rather than the trial’s own design. It identifies a two-sided significance level of 0.05, equal allocation between arms, and a normal approximation; the effect to detect is expressed as a stated fraction of the observed effect. These are assumptions for planning illustrations, not evidence that the study was designed with those assumptions.

In general, a sample-size calculation asks how many participants a proposed design would require to detect a specified effect under stated assumptions. Such a calculation is conditional on the effect size, variability, significance level, allocation, and chosen method. A planning illustration is not observed power and does not show that a study had adequate power for its actual findings. No sample-size justification for this study is reported in the registry record. The record also does not report numerical effect estimates needed to judge the planning illustrations’ assumptions in context.

For time-to-event outcomes, the record’s planning description refers to a total number of events; other planning displays are described as participants per arm. This distinction is general to the stated planning approach. It does not imply that the primary endpoint in this study is time-to-event: the listed primary endpoint is a baseline participant count.

10. Multiplicity, Missing Data and Analysis Populations

The registry record lists two outcome measures and identifies mild cognitive impairment at baseline as the primary outcome. It does not report a multiplicity strategy, such as whether any secondary outcomes were treated as exploratory or how results across multiple outcomes were interpreted. In general, testing multiple hypotheses can increase the chance of at least one apparently unusual result, so an analysis plan may specify how to address multiple comparisons. No such plan is reported in the registry record.

The record lists zero analysis records. It therefore does not provide results for the primary or other outcome measures, nor does it state which analyses were conducted. The absence of analysis records should not be interpreted as confirmation that no analyses occurred. Statistical methods, including any adjustment for participant characteristics or multiple testing, are not reported in the registry record.

The outcome population description states that the baseline cohort comprised 49 participants and that one participant with dementia was excluded from outcome measure reporting, leaving 48 participants for the outcome data. The enrollment is 58. The registry record does not explain the difference between enrollment and the stated baseline cohort, or report reasons for any participants not represented in that cohort. It also does not describe missing data for individual assessments, how missing observations were handled, or whether the analysis population varied by outcome.

These gaps limit assessment of how completely the study population is represented and whether results could be affected by exclusions or missing observations. The record’s statement that the dementia exclusion followed pre-specified exclusion criteria describes that exclusion, but does not supply further details about the criteria or broader missing-data procedures. No additional analysis population is reported.

11. Safety Results

The registry reports serious adverse events as affected participants divided by participants at risk.

Deaths

Other (non-serious) adverse events

Participants with at least one non-serious event at or above the registry's 0% reporting threshold.

The registry record reports serious adverse event figures for the Parkinson’s disease group and the control group. For the Parkinson’s disease group, 49 participants were at risk, with 0 serious adverse events, 0 other adverse events, and 0 deaths recorded. For the control group, 9 participants were at risk, with 0 serious adverse events, 0 other adverse events, and 0 deaths recorded. No top serious adverse event terms are listed.

These are event counts alongside the recorded group sizes; they are not estimates of a difference between groups. In general, a zero count means that no event of the specified type was recorded in the stated group during the relevant reporting period. It does not establish that the underlying risk is zero, and the record does not report a follow-up duration or further detail about safety ascertainment.

The procedures listed are assessment and analysis activities, and the record does not describe a randomized treatment comparison. The adverse event figures should therefore be read as registry safety entries, not as evidence about treatment effects. The registry record does not provide additional context about how adverse events were collected or whether every participant completed every safety assessment.

12. What the Result Does, and Does Not, Mean

The record describes a completed study designed to assess speech, language, cognition, and genetic factors in Parkinson’s disease. It identifies baseline mild cognitive impairment as the primary outcome and names the criteria used for classification. It also describes a control group without Parkinson’s disease and lists assessment procedures. These details clarify the study’s focus and the kind of information it sought to collect.

The record does not report the count of participants classified with mild cognitive impairment, or any statistical estimates connecting speech or language features with cognitive status. It also does not report results about genetic factors or prediction of cognitive decline. As a result, the registry information does not establish whether any marker was associated with cognition, how strong an association might have been, or how precisely it was estimated.

The outcome is measured at baseline, while the stated aim includes predicting decline. In general, describing cognitive status at one assessment and predicting change over time are distinct questions. A baseline classification alone does not show that a marker forecasts later decline. The registry record does not report a prediction analysis or follow-up findings that would address that aim.

The enrollment is 58, while the outcome population is described as 48 after the stated exclusion of one participant with dementia from a baseline cohort of 49. The record does not explain how enrollment relates to the baseline cohort. That missing information limits assessment of who contributed to the reported endpoint, although no endpoint result is reported to evaluate.

The safety entries record zero serious adverse events, zero other adverse events, and zero deaths in each group. Those entries should be read as event counts, not proof that no risk existed. Overall, the registry record documents the study’s aims and procedures, but it does not contain the outcome results needed to determine what the assessments found.

13. Why This Trial Matters Statistically

This study is statistically interesting because it connects several types of measurement: speech and language features, cognitive assessment, clinical questionnaires, and genetic analysis. That combination raises distinct questions about measurement, association, and prediction. A speech feature may describe a participant, correlate with a cognitive classification, or potentially help forecast a later outcome; each claim requires a suitable analysis and supporting results.

The primary endpoint is a categorical baseline classification of mild cognitive impairment. That makes the definition of the classification and the population assessed central to interpretation. The registry record names the Movement Disorders Society Task Force Level II Criteria and identifies 48 participants in outcome reporting, but it does not report the number classified or an uncertainty interval. Readers can therefore understand the measurement target but cannot judge its observed distribution or precision.

The study’s stated interest in cognitive decline also highlights the difference between a cross-sectional association and a prediction question. In general, prediction requires evidence about later outcomes and an assessment of how well a marker anticipates them. A baseline endpoint alone cannot establish that. The registry record does not report findings that address predictive performance.

The groups are not described as a like-for-like control comparison, and allocation is not stated. This matters because a group contrast in an assessment study can be influenced by differences in the people assessed. Appropriate interpretation requires clear population definitions and reported methods, not merely a numerical comparison.

Finally, the registry record’s lack of analysis results is itself important for statistical interpretation. The study’s aims and procedures are documented, but estimates, uncertainty, and analysis methods are not. The record therefore illustrates why a clear research question and a named endpoint are not substitutes for complete reporting of results and analytic decisions.

14. Limitations

• The posted summary statistics are the only data these results rest on; patient-level data, full protocols and statistical analysis plans are not available.
• Recalculated results are simple, unadjusted calculations from posted summaries. They do not replace the sponsor's prespecified analysis.

The primary limitation for interpreting this study from the registry record is that the primary outcome value is not reported. Although the endpoint and its classification criteria are named, the number of participants meeting the criteria is absent. No estimate of association, uncertainty interval, or p-value is reported, so neither the magnitude nor precision of a finding can be assessed.

The record states an enrollment of 58 and describes a baseline cohort of 49, with outcome reporting for 48 after one participant with dementia was excluded. It does not explain how the enrollment relates to the baseline cohort. This prevents a full accounting of the population represented in the endpoint description. The record also does not report missing-data methods or participation in individual assessments.

The stated goal of predicting cognitive decline is not matched by a reported longitudinal result in the record. The listed primary outcome is at baseline, and no follow-up prediction estimates are reported. The record also does not provide enough information to assess speech measurement procedures, the definition of each candidate marker, or analytic handling of multiple measures.

Allocation is not stated, and the arms are not identified as a like-for-like control comparison. Without reported analyses and participant characteristics, differences between the groups cannot be attributed to a causal effect. Statistical methods, adjustment procedures, and a sample-size justification are not reported in the registry record. Planning illustrations based on an observed effect do not establish the study’s design justification or observed power.

Safety reporting is limited to the event counts and group sizes listed. The record does not give further details about the duration or methods of safety monitoring. These limitations concern what can be concluded from the registry record; they do not determine what analyses may have been conducted or what information may exist outside it.

15. Related Tutorials

16. Related Statistical Calculators

17. Sources

• ClinicalTrials.gov: Speech, Linguistic and Acoustic Markers in Parkinson's Disease — NCT04273672.
• Registry record last updated 2025-06-10; status last verified 2025-06.
• Results first posted 2025-06-10.
• Data retrieved from ClinicalTrials.gov on 2026-11-09.
• Group sizes, means, event counts and sponsor-reported p-values are reproduced as posted. Effect estimates, confidence intervals and p-values not attributed to the sponsor are independently calculated from the posted summary statistics.

18. Record Summary

The registry record describes a completed study sponsored by the University of Massachusetts, Worcester, with enrollment of 58. It lists a start date of 2020-01-13 and primary completion on 2023-09-01. The study assessed participants with Parkinson’s disease and controls without Parkinson’s disease using cognitive, speech, language, clinical, questionnaire, and genetic procedures.

The primary outcome is mild cognitive impairment at baseline, classified using Movement Disorders Society Task Force Level II Criteria. Outcome reporting is described for 48 participants after one participant with dementia was excluded from a baseline cohort of 49. The record does not report the outcome count or statistical analysis results. It lists two outcome measures and zero analysis records.

Safety entries report zero serious adverse events, zero other adverse events, and zero deaths in each group. Allocation is not stated, and the groups are not described as a like-for-like control comparison. The study’s stated aims include examining speech and language markers, cognitive status, and genetic associations, but results addressing those aims are not reported in the registry record.