Predicting Early Stage Drug Induced Parkinsonism using Unsupervised and Supervised Machine Learning

Nair, Parvathy G.; Trisno, Roth; Baghini, Maryam Shojaei; Pendharkar, Gita; Chung, Hoam

doi:10.1109/embc44109.2020.9175343

Cited by 6 publications

(4 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Noteworthy that myoclonus related to FQNs could have a dose-dependent effect, but there is no report in the literature about myoclonus frequency and FQN dosage. In this way, we can postulate that FQN-induced DKN is more likely to be a threshold effect rather than a linear dose-dependent adverse effect, in which, when the critical level is achieved, there will be an all-or-none process [ 86 ]. Interestingly, a similar hypothesis was proposed for movement disorders secondary to pregabalin [ 87 ].…”

Section: Discussionmentioning

confidence: 99%

Fluoroquinolone-Associated Movement Disorder: A Literature Review

Rissardo

Caprara

2023

Medicines

View full text Add to dashboard Cite

Background: Fluoroquinolones (FQNs) are related to several central nervous system side effects. This review aims to evaluate the clinical-epidemiological profile, pathophysiological mechanisms, and management of FQNs-associated movement disorders (MDs). Methods: Two reviewers identified and assessed relevant reports in six databases without language restriction between 1988 and 2022. Results: A total of 45 reports containing 51 cases who developed MDs secondary to FQNs were reported. The MDs included 25 myoclonus, 13 dyskinesias, 7 dystonias, 2 cerebellar syndromes, 1 ataxia, 1 tic, and 2 undefined cases. The FQNs reported were ciprofloxacin, ofloxacin, gatifloxacin, moxifloxacin, levofloxacin, gemifloxacin, and pefloxacin. The mean and median age were 64.54 (SD: 15.45) and 67 years (range: 25–87 years). The predominant sex was male (54.16%). The mean and median time of MD onset were 6.02 (SD: 10.87) and 3 days (range: 1–68 days). The mean and median recovery time after MD treatment was 5.71 (SD: 9.01) and 3 days (range: 1–56 days). A complete recovery was achieved within one week of drug withdrawal in 80.95% of the patients. Overall, 95.83% of the individuals fully recovered after management. Conclusions: Future cases need to describe the long-term follow-up of the individuals. Additionally, FQN-induced myoclonus should include electrodiagnostic studies.

show abstract

Section: Discussionmentioning

confidence: 99%

Fluoroquinolone-Associated Movement Disorder: A Literature Review

Rissardo

Caprara

2023

Medicines

View full text Add to dashboard Cite

show abstract

“…We therefore have not specifically included unsupervised learning in this review, which can provide additional insights into tremor data. 88…”

Section: Discussionmentioning

confidence: 99%

“…The identified studies ultimately implemented supervised learning (although unsupervised ML, such as dimensionality reduction, was sometimes used as a precursor step). We therefore have not specifically included unsupervised learning in this review, which can provide additional insights into tremor data 88 …”

Section: Discussionmentioning

confidence: 99%

Machine Learning in Tremor Analysis: Critique and Directions

Bhatia²,

Volkmann

et al. 2023

Movement Disorders

View full text Add to dashboard Cite

A BS TRACT: Tremor is the most frequent human movement disorder, and its diagnosis is based on clinical assessment. Yet finding the accurate clinical diagnosis is not always straightforward. Fine-tuning of clinical diagnostic criteria over the past few decades, as well as devicebased qualitative analysis, has resulted in incremental improvements to diagnostic accuracy. Accelerometric assessments are commonplace, enabling clinicians to capture high-resolution oscillatory properties of tremor, which recently have been the focus of various machine-learning (ML) studies. In this context, the application of ML models to accelerometric recordings provides the potential for less-biased classification and quantification of tremor disorders. However, if implemented incorrectly, ML can result in spurious or nongeneralizable results and misguided conclusions. This work summarizes and highlights recent developments in ML tools for tremor research, with a focus on supervised ML. We aim to highlight the opportunities and limitations of such approaches and provide future directions while simultaneously guiding the reader through the process of applying ML to analyze tremor data. We identify the need for the movement disorder community to take a more proactive role in the application of these novel analytical technologies, which so far have been predominantly pursued by the engineering and data analysis field. Ultimately, big-data approaches offer the possibility to identify generalizable patterns but warrant meaningful translation into clinical practice.

show abstract

“…Proposed method also detected mild cases of DIP obtained from accelerometer gait data successfully. 34 Since the methods are generic, they may potentially be utilized to track early-stage motor symptoms of other neurodegenerative diseases.…”

Section: Discussionmentioning

confidence: 99%

Detecting early-stage Parkinson’s disease from gait data

Nair,

Shojaei Baghini,

Pendharkar

et al. 2023

Proc Inst Mech Eng H

View full text Add to dashboard Cite

Parkinson’s disease is a chronic and progressive neurodegenerative disorder with an estimated 10 million people worldwide living with PD. Since early signs are benign, many patients go undiagnosed until the symptoms get severe and the treatment becomes more difficult. The symptoms start intermittently and gradually become continuous as the disease progresses. In order to detect and classify these minute differences between gaits in early PD patients, we propose to use dynamic time warping (DTW). For a given set of gait data from a patient, the DTW algorithm computes the difference between any two gait cycles in the form of a warping path, which reveals small time differences between gait cycles. Once the time-warping information between all possible pairs of gait cycles is used as the main source of gait features, K-means clustering is used to extract the final features. These final features are fed to a simple logistic regression to easily and successfully detect early PD symptoms, which was reported as challenging using conventional statistical features. In addition, the use of DTW ensures that the obtained results are not affected by the differences in the style and speed of walking of a subject. Our approach is validated for the gait data from 83 subjects at early stages of PD, 10 subjects at moderate stages of PD, and 73 controls using the Leave-One-Out and N-fold cross-validation techniques, with a detection accuracy of over 98%. The high classification accuracy validated from a large data set suggests that these new features from DTW can be effectively used to help clinicians diagnose the disease at the earliest. Even though PD is not completely curable, early diagnosis would help clinicians to start the treatment from the beginning thereby reducing the intensity of symptoms at later stages.

show abstract

Predicting Early Stage Drug Induced Parkinsonism using Unsupervised and Supervised Machine Learning

Cited by 6 publications

References 9 publications

Fluoroquinolone-Associated Movement Disorder: A Literature Review

Fluoroquinolone-Associated Movement Disorder: A Literature Review

Machine Learning in Tremor Analysis: Critique and Directions

Detecting early-stage Parkinson’s disease from gait data

Contact Info

Product

Resources

About