Background

The aim of this work was to identify early clinical predictors of important outcomes in Parkinson's disease (PD). In PD, treatment-resistant (e.g., dementia, falling) and other important functional outcomes (e.g., declines in quality of life [QOL] and activities of daily living [ADL]) emerge and become increasingly disabling.

Methods

We analyzed longitudinal data from 491 early, untreated PD subjects who enrolled in the PreCEPT trial, had baseline SPECT dopamine transporter deficit, and have continued in the PostCEPT observational cohort. After PreCEPT, antiparkinsonian medications were added if needed. Baseline clinical precursors were examined as potential predictors of selected outcomes. Separate and multivariate logistic regressions, adjusted for certain baseline factors, were performed for dichotomized outcomes evaluated at the last PostCEPT visit.

Results

On enrollment, subjects had average disease duration of 0.8 years and were followed for an average of 5.5 years. Some baseline precursors were found to be predictive: disease stage, cognitive, and ADL scores for dementia; disease stage, ADL, and motor and freezing scores for hallucinations; disease stage, depression, ADL, and freezing and walking scores for falling; and ADL, depression, and motor and walking scores and disease stage for QOL decline. No baseline clinical feature predicted decline in ADL. Being on levodopa was not a significant predictor of any outcome, but subjects on a dopamine agonist were significantly less impaired with respect to falling, abnormal Mini-Mental State Examination, and QOL.

Conclusions

Although there are limitations, results support the value of longitudinal follow-up of clinical trial populations to identify early clinical precursors of important outcomes and thereby identify high-risk patients early on.

The objective of this study was to examine a remote method for maintaining long-term contact with Parkinson's disease (PD) patients participating in clinical studies. Long-term follow-up of PD patients is needed to fill critical information gaps on progression, biomarkers, and treatment. Prospective in-person assessment can be costly and may be impossible for some patients. Remote assessment using mail and telephone contact may be a practical follow-up method. Patients enrolled in the multi-center Longitudinal and Biomarker Study in Parkinson's Disease (LABS-PD) in-person follow-up study in 2006 were invited to enroll in Follow-up of Persons With Neurologic Diseases (FOUND), which is overseen by a single center under a separate, central institutional review board protocol. FOUND uses mailed questionnaires and telephone interviews to assess PD status. FOUND follow-up continued when LABS-PD in-person visits ended in 2011. Retention and agreement between remote and in-person assessments were determined. In total, 422 of 499 (84.5%) of eligible patients volunteered, AND 96% of participants were retained. Of 60 patients who withdrew consent from LABS-PD, 51 were retained in FOUND. Of 341 patients who were active in LABS-PD, 340 were retained in FOUND (99.7%) when the in-person visits ceased. Exact agreement between remote and in-person assessments was ≥ 80% for diagnosis, disease features (eg, dyskinesias), and PD medication. Correlation between expert-rated and self-reported Unified Parkinson's Disease Rating Scale and Movement Disorder Society Unified Parkinson's Disease Rating Scale, which were examined at times separated by several months, was moderate or substantial for most items. Retention was excellent using remote follow-up of research participants with PD, providing a safety net when combined with in-person visits, and also is effective as a stand-alone assessment method, providing a useful alternative when in-person evaluation is not feasible.

Background

The presence of invasive cribriform adenocarcinoma (ICC), an expanse of cells containing punched-out lumina uninterrupted by stroma, in radical prostatectomy (RP) specimens has been associated with biochemical recurrence (BCR). However, ICC identification has only moderate inter-reviewer agreement.

Objective

To investigate quantitative machine-based assessment of the extent and prognostic utility of ICC, especially within individual Gleason grade groups.

Design, setting, and participants

A machine learning approach was developed for ICC segmentation using 70 RP patients and validated in a cohort of 749 patients from four sites whose median year of surgery was 2007 and with median follow-up of 28 mo. ICC was segmented on one representative hematoxylin and eosin RP slide per patient and the fraction of tumor area composed of ICC, the cribriform area index (CAI), was measured.

Outcome measurements and statistical analysis

The association between CAI and BCR was measured in terms of the concordance index (c index) and hazard ratio (HR).

Results and limitations

CAI was correlated with BCR (c index 0.62) in the validation set of 411 patients with ICC morphology, especially those with Gleason grade group 2 cancer (n = 192; c index 0.66), and was less prognostic when patients without ICC were included (c index 0.54). A doubling of CAI in the group with ICC morphology was prognostic after controlling for Gleason grade, surgical margin positivity, preoperative prostate-specific antigen level, pathological T stage, and age (HR 1.19, 95% confidence interval 1.03-1.38; p = 0.018).

Conclusions

Automated image analysis and machine learning could provide an objective, quantitative, reproducible, and high-throughput method of quantifying ICC area. The performance of CAI for grade group 2 cancer suggests that for patients with little Gleason 4 pattern, the ICC fraction has a strong prognostic role.

Patient summary

Machine-based measurement of a specific cell pattern (cribriform; sieve-like, with lots of spaces) in images of prostate specimens could improve risk stratification for patients with prostate cancer. In the future, this could help in expanding the criteria for active surveillance.

Existing tools for post-radical prostatectomy (RP) prostate cancer biochemical recurrence (BCR) prognosis rely on human pathologist-derived parameters such as tumor grade, with the resulting inter-reviewer variability. Genomic companion diagnostic tests such as Decipher tend to be tissue destructive, expensive, and not routinely available in most centers. We present a tissue non-destructive method for automated BCR prognosis, termed "Histotyping", that employs computational image analysis of morphologic patterns of prostate tissue from a single, routinely acquired hematoxylin and eosin slide. Patients from two institutions (n = 214) were used to train Histotyping for identifying high-risk patients based on six features of glandular morphology extracted from RP specimens. Histotyping was validated for post-RP BCR prognosis on a separate set of n = 675 patients from five institutions and compared against Decipher on n = 167 patients. Histotyping was prognostic of BCR in the validation set (p < 0.001, univariable hazard ratio [HR] = 2.83, 95% confidence interval [CI]: 2.03-3.93, concordance index [c-index] = 0.68, median years-to-BCR: 1.7). Histotyping was also prognostic in clinically stratified subsets, such as patients with Gleason grade group 3 (HR = 4.09) and negative surgical margins (HR = 3.26). Histotyping was prognostic independent of grade group, margin status, pathological stage, and preoperative prostate-specific antigen (PSA) (multivariable p < 0.001, HR = 2.09, 95% CI: 1.40-3.10, n = 648). The combination of Histotyping, grade group, and preoperative PSA outperformed Decipher (c-index = 0.75 vs. 0.70, n = 167). These results suggest that a prognostic classifier for prostate cancer based on digital images could serve as an alternative or complement to molecular-based companion diagnostic tests.