Identification and classification of neuro-degenerative diseases using feature selection through PCA-LD

Amin, Sobia; Singhal, Abhishek

doi:10.1109/upcon.2017.8251114

Cited by 10 publications

(9 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1). The latter value is still higher than other studies [15], [17] but aligns with the work of Xia et al [20], where this binary task showed the lowest accuracy among the others (91.18%). The TDARFS appears as the best feature set for PD-AS (100% accuracy) and HD-AS (98.49%) classification, both with kNN (Fig.…”

Section: A Experimentssupporting

confidence: 89%

“…It should be noted that in those studies where all the binary comparisons have been investigated, features related to nonlinear dynamics of the gait timeseries were considered [17], [20], [21]. In both cases, it is required to set a series of computational parameters, such as the embedding dimension and the similarity threshold, which might result group-specific [41], being in general heavily data-dependent [25].…”

Section: B Experimentsmentioning

confidence: 99%

“…The auto-correlation decay time, with the stride time and the fluctuation variation, was used in [7] for developing a wearable NDD detection system. The effectiveness of the Shannon entropy and statistical descriptors was evaluated in [17], whereas the conditional entropy, together with a phase synchronization analysis, based on the Hilbert transform, was employed in [18]. The use of texture-based features was investigated in [19], by using the fuzzy recurrence plot for converting gait timeseries into grayscale images.…”

mentioning

confidence: 99%

“…In the latter field, TD features found an extensive employment [28], [29], showing in many cases higher performances with respect to features belonging to other domains [30], [31], for classification tasks which often involve several classes [29], [32]. It is noteworthy that different features computed in TD and used in myoelectric pattern recognition have been also successfully employed for gait rhythm analysis [13], [17], [20], [21], [27], [31]. This kind of features proved to be effective for NDD identification or when employed to boost the performances of more complex feature sets [2], [20], [21], [33].…”

mentioning

confidence: 99%

See 3 more Smart Citations

Identification of Neurodegenerative Diseases From Gait Rhythm Through Time Domain and Time-Dependent Spectral Descriptors

Mengarelli

Tigrini

Fioretti

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

The analysis of gait rhythm by pattern recognition can support the state-of-the-art clinical methods for the identification of neurodegenerative diseases (NDD). In this study, we investigated the use of time domain (TD) and time-dependent spectral features (PSDTD) for detecting NDD sub-types. Also, we proposed two classification pathways for supporting NDD diagnosis, the first one made by a two-step learning phase, whereas the second one encompasses a single learning model. We considered strideto-stride fluctuation data of healthy controls (CN), patients affected by Parkinson's disease (PD), Huntington's disease (HD), and amyotrophic lateral sclerosis (AS). TD feature set provided good results to distinguish between CN and NDDs, while performances lowered for specific NDD identification. PSDTD features boosted the accuracy of each binary identification task. With k-nearest neighbor classifier, the first diagnosis pathway reached 98.76% accuracy to distinguish between CN and NDD and 94.56% accuracy for NDDs sub-types, whereas the second pathway offered an overall accuracy of 94.84% for a 4-class classification task. Outcomes of this study indicate that the use of TD and PSDTD features, simple to extract and with a low computational load, provides reliable results in terms of NDD identification, being also useful for the development of gait rhythm computer-aided NDD detection systems.

show abstract

Section: A Experimentssupporting

confidence: 89%

Section: B Experimentsmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 2 more Smart Citations

Identification of Neurodegenerative Diseases From Gait Rhythm Through Time Domain and Time-Dependent Spectral Descriptors

Mengarelli

Tigrini

Fioretti

et al. 2022

IEEE J. Biomed. Health Inform.

View full text Add to dashboard Cite

show abstract

“…ENT is a widely used statistical parameter in many fields, especially in signal processing. Shannon ENT values were used in the current study with different types such as norm, log, and sure as [35,36] ENT…”

Section: Entropy (Ent)mentioning

confidence: 99%

Comparison of different regression models to estimate fault location on hybrid power systems

Ekici

Ünal

Ozleyen

2019

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

Emerging Role of Combination Immunotherapy in the First-line Treatment of Advanced Renal Cell Carcinoma

George

Rini

Hammers³

2019

JAMA Oncol

View full text Add to dashboard Cite

ystemic therapy with antiangiogenic treatments targeting vascular endothelial growth factor (VEGF) is the current firstline standard of care for advanced renal cell carcinoma (RCC). Although antiangiogenic therapies can provide significant shortterm clinical benefits, including an enhanced objective response rate (ORR) and prolonged progression-free survival (PFS), they typically result in treatment resistance and thus rarely produce durable long-term response or survival. 1 New therapeutic approaches are needed that can provide enduring responses and improve survival in the first-line treatment setting.There is a clear rationale for the use of immunotherapy for RCC. The association between the immune system and RCC has long been known, with an abundance of evidence suggesting that RCC is an immunogenic tumor 2 and is associated with an innate hostmediated immune response. 3 In 1992, the US Food and Drug Administration approved high-dose intravenous interleukin 2 (IL-2) therapy for advanced RCC; this treatment was associated with durable responses and prolonged survival in a small proportion of patients, 4-6 but the toxic effects and the inability to identify which patients are likely to respond have precluded its widespread use.Remarkable progress has been made recently in the clinical application of newer immunotherapies, of which the most notable are immune checkpoint inhibitors (ICIs) that increase antitumor immunity by blocking native immune regulators such as cytotoxic T lymphocyte antigen 4 (CTLA-4) and programmed cell death 1 (PD-1). The anti-PD-1 monoclonal antibody nivolumab was approved, based on results from the CheckMate 025 phase 3 trial, by the US Food and Drug Administration in 2015 for treatment of advanced RCC in patients who have received prior antiangiogenic therapy. 7 However, current evidence indicates that not all patients may find singleagent immunotherapy advantageous, underscoring the unmet need for combination treatment strategies that can improve efficacy in a broader patient population without exacerbating toxic effects.In this review, we discuss the rationale and evidence for using immunotherapy-based combination regimens as first-line treatment of advanced RCC and highlight the associated challenges for practicing physicians. Discussion Rationale for Immunotherapy-Based Combination TherapyThe standard approach for combination therapy is to use 2 or more active agents with distinct and complementary mechanisms of IMPORTANCE Novel immunotherapies, notably the immune checkpoint inhibitors, have been shown to be efficacious in patients with advanced renal cell carcinoma, but innate or adaptive resistance is observed with single-agent immunotherapy. New combination treatment strategies are needed that can improve efficacy in a broader patient population, without exacerbating the toxic effects.OBSERVATIONS Numerous late-phase trials are ongoing to investigate (1) dual immune checkpoint inhibition or (2) combined inhibition of immune checkpoints and vascular endothelial growth factor. Init...

show abstract

Identification and classification of neuro-degenerative diseases using feature selection through PCA-LD

Cited by 10 publications

References 13 publications

Identification of Neurodegenerative Diseases From Gait Rhythm Through Time Domain and Time-Dependent Spectral Descriptors

Identification of Neurodegenerative Diseases From Gait Rhythm Through Time Domain and Time-Dependent Spectral Descriptors

Comparison of different regression models to estimate fault location on hybrid power systems

Emerging Role of Combination Immunotherapy in the First-line Treatment of Advanced Renal Cell Carcinoma

Contact Info

Product

Resources

About