Identification of clinical disease trajectories in neurodegenerative disorders with natural language processing.

Neurodegenerative disorders exhibit considerable clinical heterogeneity and are frequently misdiagnosed. This heterogeneity is often neglected and difficult to study. Therefore, innovative data-driven approaches utilizing substantial autopsy cohorts are needed to address this complexity and improve diagnosis, prognosis and fundamental research. We present clinical disease trajectories from 3,042 Netherlands Brain Bank donors, encompassing 84 neuropsychiatric signs and symptoms identified through natural language processing. This unique resource provides valuable new insights into neurodegenerative disorder symptomatology. To illustrate, we identified signs and symptoms that differed between frequently misdiagnosed disorders. In addition, we performed predictive modeling and identified clinical subtypes of various brain disorders, indicative of neural substructures being differently affected. Finally, integrating clinical diagnosis information revealed a substantial proportion of inaccurately diagnosed donors that masquerade as another disorder. The unique datasets allow researchers to study the clinical manifestation of signs and symptoms across neurodegenerative disorders, and identify associated molecular and cellular features.

Optimization of portal placement for endoscopic calcaneoplasty.

PURPOSE: The purpose of our study was to determine an anatomic landmark to help locate portals in endoscopic calcaneoplasty. METHODS: The device for optimal portal placement (DOPP) was developed to measure the distance from the distal fibula tip to the calcaneus (DFC) in 28 volunteers to determine the location of the posterosuperior calcaneal border in relation to this line. RESULTS: The DOPP showed an interobserver reliability of 0.99 (95% confidence interval, 0.97 to 0.99). We found that portals should be placed at a mean of 15 mm (SD, 4.5 mm) distal to the tip of the fibula in patients with flat feet, at a mean of 20 mm (SD, 4.8 mm) in normal feet, and at a mean of 22 mm (SD, 5.4 mm) in cavus feet. The difference in the DFC within the 3 different foot type groups was significant (P < .05). CONCLUSIONS: The DOPP was shown to be highly reliable in measuring the DFC (intraclass coefficient, 0.99). A numeric distance scale for use in all different foot morphologies could not be constructed. There is a direct relation between portal location and foot morphology (P < .05): in flat feet the portal location is significantly more proximal (15 mm) to the tip of the fibula when compared with cavus feet (22 mm). CLINICAL RELEVANCE: These results may help with portal placement in endoscopic calcaneoplasty for all different foot morphologies.