1
|
Rykov YG, Patterson MD, Gangwar BA, Jabar SB, Leonardo J, Ng KP, Kandiah N. Predicting cognitive scores from wearable-based digital physiological features using machine learning: data from a clinical trial in mild cognitive impairment. BMC Med 2024; 22:36. [PMID: 38273340 PMCID: PMC10809621 DOI: 10.1186/s12916-024-03252-y] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/25/2023] [Accepted: 01/09/2024] [Indexed: 01/27/2024] Open
Abstract
BACKGROUND Continuous assessment and remote monitoring of cognitive function in individuals with mild cognitive impairment (MCI) enables tracking therapeutic effects and modifying treatment to achieve better clinical outcomes. While standardized neuropsychological tests are inconvenient for this purpose, wearable sensor technology collecting physiological and behavioral data looks promising to provide proxy measures of cognitive function. The objective of this study was to evaluate the predictive ability of digital physiological features, based on sensor data from wrist-worn wearables, in determining neuropsychological test scores in individuals with MCI. METHODS We used the dataset collected from a 10-week single-arm clinical trial in older adults (50-70 years old) diagnosed with amnestic MCI (N = 30) who received a digitally delivered multidomain therapeutic intervention. Cognitive performance was assessed before and after the intervention using the Neuropsychological Test Battery (NTB) from which composite scores were calculated (executive function, processing speed, immediate memory, delayed memory and global cognition). The Empatica E4, a wrist-wearable medical-grade device, was used to collect physiological data including blood volume pulse, electrodermal activity, and skin temperature. We processed sensors' data and extracted a range of physiological features. We used interpolated NTB scores for 10-day intervals to test predictability of scores over short periods and to leverage the maximum of wearable data available. In addition, we used individually centered data which represents deviations from personal baselines. Supervised machine learning was used to train models predicting NTB scores from digital physiological features and demographics. Performance was evaluated using "leave-one-subject-out" and "leave-one-interval-out" cross-validation. RESULTS The final sample included 96 aggregated data intervals from 17 individuals. In total, 106 digital physiological features were extracted. We found that physiological features, especially measures of heart rate variability, correlated most strongly to the executive function compared to other cognitive composites. The model predicted the actual executive function scores with correlation r = 0.69 and intra-individual changes in executive function scores with r = 0.61. CONCLUSIONS Our findings demonstrated that wearable-based physiological measures, primarily HRV, have potential to be used for the continuous assessments of cognitive function in individuals with MCI.
Collapse
Affiliation(s)
| | | | | | | | - Jacklyn Leonardo
- Dementia Research Centre, Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore
| | - Kok Pin Ng
- Department of Neurology, National Neuroscience Institute, Singapore, Singapore
- Duke-NUS Medical School, Singapore, Singapore
| | - Nagaendran Kandiah
- Dementia Research Centre, Lee Kong Chian School of Medicine, Nanyang Technological University, Singapore, Singapore
| |
Collapse
|
2
|
Gradwell MA, Boyle KA, Browne TJ, Bell AM, Leonardo J, Peralta Reyes FS, Dickie AC, Smith KM, Callister RJ, Dayas CV, Hughes DI, Graham BA. Diversity of inhibitory and excitatory parvalbumin interneuron circuits in the dorsal horn. Pain 2022; 163:e432-e452. [PMID: 34326298 PMCID: PMC8832545 DOI: 10.1097/j.pain.0000000000002422] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/04/2021] [Revised: 07/13/2021] [Accepted: 07/14/2021] [Indexed: 12/03/2022]
Abstract
ABSTRACT Parvalbumin-expressing interneurons (PVINs) in the spinal dorsal horn are found primarily in laminae II inner and III. Inhibitory PVINs play an important role in segregating innocuous tactile input from pain-processing circuits through presynaptic inhibition of myelinated low-threshold mechanoreceptors and postsynaptic inhibition of distinct spinal circuits. By comparison, relatively little is known of the role of excitatory PVINs (ePVINs) in sensory processing. Here, we use neuroanatomical and optogenetic approaches to show that ePVINs comprise a larger proportion of the PVIN population than previously reported and that both ePVIN and inhibitory PVIN populations form synaptic connections among (and between) themselves. We find that these cells contribute to neuronal networks that influence activity within several functionally distinct circuits and that aberrant activity of ePVINs under pathological conditions is well placed to contribute to the development of mechanical hypersensitivity.
Collapse
Affiliation(s)
- Mark A. Gradwell
- Faculty of Health, School of Biomedical Sciences & Pharmacy, University of Newcastle, Callaghan, Australia
- Hunter Medical Research Institute (HMRI), New Lambton Heights, New South Wales, Australia
- Department of Cell Biology and Neuroscience, Rutgers, The State University of New Jersey, Piscataway, NJ, United States
- W.M. Keck Center for Collaborative Neuroscience, Rutgers, The State University of New Jersey, Piscataway, NJ, United States
| | - Kieran A. Boyle
- Institute of Neuroscience Psychology, College of Medical, Veterinary & Life Sciences, University of Glasgow, Glasgow, United Kingdom
| | - Tyler J. Browne
- Faculty of Health, School of Biomedical Sciences & Pharmacy, University of Newcastle, Callaghan, Australia
- Hunter Medical Research Institute (HMRI), New Lambton Heights, New South Wales, Australia
| | - Andrew M. Bell
- Institute of Neuroscience Psychology, College of Medical, Veterinary & Life Sciences, University of Glasgow, Glasgow, United Kingdom
| | - Jacklyn Leonardo
- Institute of Neuroscience Psychology, College of Medical, Veterinary & Life Sciences, University of Glasgow, Glasgow, United Kingdom
| | - Fernanda S. Peralta Reyes
- Institute of Neuroscience Psychology, College of Medical, Veterinary & Life Sciences, University of Glasgow, Glasgow, United Kingdom
| | - Allen C. Dickie
- Institute of Neuroscience Psychology, College of Medical, Veterinary & Life Sciences, University of Glasgow, Glasgow, United Kingdom
| | - Kelly M. Smith
- Faculty of Health, School of Biomedical Sciences & Pharmacy, University of Newcastle, Callaghan, Australia
- Hunter Medical Research Institute (HMRI), New Lambton Heights, New South Wales, Australia
- Department of Neurobiology and the Pittsburgh Center for Pain Research, University of Pittsburgh, Pittsburgh, PA, United States
| | - Robert J. Callister
- Faculty of Health, School of Biomedical Sciences & Pharmacy, University of Newcastle, Callaghan, Australia
- Hunter Medical Research Institute (HMRI), New Lambton Heights, New South Wales, Australia
| | - Christopher V. Dayas
- Faculty of Health, School of Biomedical Sciences & Pharmacy, University of Newcastle, Callaghan, Australia
- Hunter Medical Research Institute (HMRI), New Lambton Heights, New South Wales, Australia
| | - David I. Hughes
- Institute of Neuroscience Psychology, College of Medical, Veterinary & Life Sciences, University of Glasgow, Glasgow, United Kingdom
| | - Brett A. Graham
- Faculty of Health, School of Biomedical Sciences & Pharmacy, University of Newcastle, Callaghan, Australia
- Hunter Medical Research Institute (HMRI), New Lambton Heights, New South Wales, Australia
| |
Collapse
|
3
|
Mangan KF, Leonardo J, Mullaney MT, Terstappen LW, Rao C, Liberti P. A rapid two-step method for elimination of bcl-2/IgH positive non-Hodgkin's lymphoma cells from human blood or marrow stem cells, employing immunomagnetic purging with streptavidin-coated ferrofluids. Cytotherapy 2010; 1:287-93. [PMID: 20426554 DOI: 10.1080/0032472031000141264] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/26/2022]
Abstract
BACKGROUND Follicular lymphoma cells may contaminate blood or BM stem cell collections used for autologous transplants and contribute to relapse. We report on the development of a B-cell lymphoma-purging technique, using streptavidin-coated ferrofluids (SAFF) and a high-gradient magnetic-separation device (HGMSD). METHODS Blood or BM samples were spiked with bcl-2 positive lymphoma cells, labeled with biotinylated B cell MAb (CD19, CD20, CD37) then purged by positive selection of CD34(+) cells, followed by negative selection with SAFF and a high HGMSD. Purging efficiency was judged by dual-labeled flow cytometry and by PCR analysis of bcl-2. RESULTS A 6 log purge of bcl-2 lymphoma cells could be achieved by first enriching for CD34(+) cells, followed by negative selection with SAFF and HGMSD. The use of SAFF with HGMSD alone could only accomplish a 2-3 log purge. DISCUSSION CD34 selection from blood or BM of follicular lymphoma patients, followed by negative selection of MAb-labeled cells with SAFF could achieve a 6 log purge. However, cell yields were low (10%) and purging efficacy was limited to low starting concentration of lymphoma cells (< or = 1.0%). This technique, however, may be useful for full-scale clinical purging of minimal residual disease following debulking with a cyclophosphamide or other agents.
Collapse
Affiliation(s)
- K F Mangan
- Bone Marrow Transplant Program, Department of Medicine, Temple University School of Medicine, Philadelphia, USA
| | | | | | | | | | | |
Collapse
|
5
|
DiCarlo S, Leonardo J. Hemodynamic and energy cost responses to changes in arm exercise technique. Phys Ther 1983; 63:1585-92. [PMID: 6622533 DOI: 10.1093/ptj/63.10.1585] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 01/21/2023]
Abstract
The purpose of this investigation was to determine heart rate, blood pressure, rate pressure product, and oxygen consumption responses to variations in arm exercise technique of a specific calisthenics for cardiac rehabilitation. Eight subjects performed the following four variations of an arm calisthenics: slow paused, slow continuous, fast paused, and fast continuous. Heart rate, blood pressure, and metabolic cost were measured during the last minute of each variation. An analysis of variance revealed significant differences between exercise variations (p less than .05) across means in heart rate, blood pressure, rate pressure product, and metabolic equivalent terms. Post hoc analysis revealed that changes in technique caused significantly large differences (p less than .05) in heart rate, blood pressure, and rate pressure product, but metabolic equivalent term levels did not change significantly. Changes in arm exercise technique result in significant changes in heart rate, blood pressure, and rate pressure product with little or no changes in metabolic equivalent terms. This finding suggests that prescribing exercise based on metabolic equivalent terms may not be indicative of cardiac stress unless the technique of exercise is carefully monitored and controlled.
Collapse
|