Luca Lonini
Rehabilitation Institute of Chicago
27 Papers
81 Citations
Luca Lonini is an academic researcher from Rehabilitation Institute of Chicago. The author has contributed to research in topics: Computer science & Motor learning. The author has an hindex of 14, co-authored 24 publications. Previous affiliations of Luca Lonini include Frankfurt Institute for Advanced Studies & Università Campus Bio-Medico.
Chat about Author
Papers
The need to approximate the use-case in clinical machine learning.
TL;DR: It is found that record-wise CV often massively overestimates the prediction accuracy of the algorithms, and this overly optimistic method was used by almost half of the retrieved studies that used accelerometers, wearable sensors, or smartphones to predict clinical outcomes.
Wearable sensors for Parkinson’s disease: which data are worth collecting for training symptom detection models
Luca Lonini,Luca Lonini,Andrew M. Dai,Andrew M. Dai,Nicholas Shawen,Nicholas Shawen,Tatyana Simuni,Cynthia Poon,Leo Shimanovich,Margaret Daeschler,Roozbeh Ghaffari,John A. Rogers,John A. Rogers,Arun Jayaraman,Arun Jayaraman +14 more
- 23 Nov 2018
TL;DR: The results suggest that PD symptoms can be detected during a variety of activities and are best modeled by a dataset incorporating many individuals, whereas using sensors on both sides does not improve performance.
Using and understanding cross-validation strategies. Perspectives on Saeb et al.
Max A. Little,Gaël Varoquaux,Sohrab Saeb,Luca Lonini,Arun Jayaraman,David C. Mohr,Konrad P. Kording,Konrad P. Kording +7 more
TL;DR: A detailed look at the complexities of cross-validation, fostered by the peer review of Saeb et al.
156
Role of data measurement characteristics in the accurate detection of Parkinson’s disease symptoms using wearable sensors
Nicholas Shawen,Nicholas Shawen,Megan K. O’Brien,Megan K. O’Brien,Sanjeev Venkatesan,Sanjeev Venkatesan,Luca Lonini,Luca Lonini,Tanya Simuni,Jamie L. Hamilton,Roozbeh Ghaffari,John A. Rogers,Arun Jayaraman,Arun Jayaraman +13 more
TL;DR: The ability to simplify measurement characteristics from body-worn sensors while maintaining performance in PD symptom detection is demonstrated, and this approach may improve the feasibility of long-term, continuous, and real-time monitoring of PD symptoms by reducing computational burden on wearable devices.
Video-Based Pose Estimation for Gait Analysis in Stroke Survivors during Clinical Assessments: A Proof-of-Concept Study
Luca Lonini,Yaejin Moon,Kyle R. Embry,R. James Cotton,K. McKenzie,Sophia Jenz,Arun Jayaraman +6 more
TL;DR: The preliminary results suggest that single camera videos and pose estimation models based on deep networks could be used to quantify clinically relevant gait metrics in individuals poststroke, even while using assistive devices in uncontrolled environments.