Optimization of number and range of shunt valve performance levels in infant hydrocephalus: a machine learning analysis

Waterstraat, Mark Graham; Dehghan, Arshia; Gholampour, Seifollah

doi:10.3389/fbioe.2024.1352490

Cited by 2 publications

(3 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The distribution patterns observed in the PCA graphs for other medical datasets, focusing on hydrocephalus [7,[46][47][48][49], cerebral aneurysms [50,51], orthopedic drilling [52], and Chiari malformation I [53,54], also bore striking similarities to those noted in this The distribution patterns observed in the PCA graphs for other medical datasets, focusing on hydrocephalus [7,[46][47][48][49], cerebral aneurysms [50,51], orthopedic drilling [52], and Chiari malformation I [53,54], also bore striking similarities to those noted in this cerebral stroke dataset. In all instances, the data distribution across classes was dispersed, non-concentrated, and homogeneously distributed among the other classes.…”

Section: Discussionsupporting

confidence: 69%

“…Such imbalances present unique challenges in machine and deep learning, as standard algorithms optimized for balanced datasets may not perform effectively, often overlooking the minority class, which usually represents the most crucial information to be predicted [5,6]. Besides the hurdles in predicting minority classes in supervised learning scenarios, our recent study has brought to the forefront the intricate challenges associated with minority classes in unsupervised learning within the medical field [7]. Two approaches to tackling imbalanced datasets in classification include resampling data points and modifying the classification algorithm [8].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Impact of Nature of Medical Data on Machine and Deep Learning for Imbalanced Datasets: Clinical Validity of SMOTE Is Questionable

Gholampour

2024

MAKE

Self Cite

View full text Add to dashboard Cite

Dataset imbalances pose a significant challenge to predictive modeling in both medical and financial domains, where conventional strategies, including resampling and algorithmic modifications, often fail to adequately address minority class underrepresentation. This study theoretically and practically investigates how the inherent nature of medical data affects the classification of minority classes. It employs ten machine and deep learning classifiers, ranging from ensemble learners to cost-sensitive algorithms, across comparably sized medical and financial datasets. Despite these efforts, none of the classifiers achieved effective classification of the minority class in the medical dataset, with sensitivity below 5.0% and area under the curve (AUC) below 57.0%. In contrast, the similar classifiers applied to the financial dataset demonstrated strong discriminative power, with overall accuracy exceeding 95.0%, sensitivity over 73.0%, and AUC above 96.0%. This disparity underscores the unpredictable variability inherent in the nature of medical data, as exemplified by the dispersed and homogeneous distribution of the minority class among other classes in principal component analysis (PCA) graphs. The application of the synthetic minority oversampling technique (SMOTE) introduced 62 synthetic patients based on merely 20 original cases, casting doubt on its clinical validity and the representation of real-world patient variability. Furthermore, post-SMOTE feature importance analysis, utilizing SHapley Additive exPlanations (SHAP) and tree-based methods, contradicted established cerebral stroke parameters, further questioning the clinical coherence of synthetic dataset augmentation. These findings call into question the clinical validity of the SMOTE technique and underscore the urgent need for advanced modeling techniques and algorithmic innovations for predicting minority-class outcomes in medical datasets without depending on resampling strategies. This approach underscores the importance of developing methods that are not only theoretically robust but also clinically relevant and applicable to real-world clinical scenarios. Consequently, this study underscores the importance of future research efforts to bridge the gap between theoretical advancements and the practical, clinical applications of models like SMOTE in healthcare.

show abstract

Section: Discussionsupporting

confidence: 69%

Section: Introductionmentioning

confidence: 99%

Impact of Nature of Medical Data on Machine and Deep Learning for Imbalanced Datasets: Clinical Validity of SMOTE Is Questionable

Gholampour

2024

MAKE

Self Cite

View full text Add to dashboard Cite

show abstract

“…The resulting graphical panels highlight variations in the distribution of industries, categorized by industry subsectors and market capitalization tiers. This method of dimensionality reduction effectively preserves the inherent variance within the dataset, facilitating a more nuanced examination of the complex attributes of the industries [59]. Within the derived three-dimensional space, individual industries are represented as points, with their positions reflecting the synthesized financial ratios.…”

Section: Resultsmentioning

confidence: 99%

Risk Analysis of Bankruptcy in the U.S. Healthcare Industries Based on Financial Ratios: A Machine Learning Analysis

Gholampoor,

Asadi

2024

JTAER

View full text Add to dashboard Cite

The prediction of bankruptcy risk poses a formidable challenge in the fields of economics and finance, particularly within the healthcare industry, where it carries significant economic implications. The burgeoning field of healthcare electronic commerce, continuously evolving through technological advancements and changing regulations, introduces additional layers of complexity. We collected financial data from 1265 U.S. healthcare industries to predict bankruptcy based on 40 financial ratios using multi-class classification machine learning models across various industry subsectors and market capitalizations. The exceptionally high post-tuning accuracy rates, exceeding 90%, along with high-performance metrics solidified the robustness and exceptional predictive capability of the gradient boosting model in bankruptcy prediction. The results also demonstrate the power and sensitivity of financial ratios in predicting bankruptcy based on financial ratios. The Altman models highlight the return on investment (ROI) as the most important parameter for predicting bankruptcy risk in healthcare industries. The Ohlson model identifies return on assets (ROA) as an important ratio specifically for predicting bankruptcy risk within industry subsectors. Furthermore, it underscores the significance of both ROA and the enterprise value to earnings before interest and taxes (EV/EBIT) ratios as important parameters for predicting bankruptcy based on market capitalization. Recognizing these ratios enables proactive decision making that enhances resilience. Our findings contribute to informed risk management strategies, allowing for better management of healthcare industries in crises like those experienced in 2022 and even on a global scale.

show abstract

Optimization of number and range of shunt valve performance levels in infant hydrocephalus: a machine learning analysis

Cited by 2 publications

References 45 publications

Impact of Nature of Medical Data on Machine and Deep Learning for Imbalanced Datasets: Clinical Validity of SMOTE Is Questionable

Impact of Nature of Medical Data on Machine and Deep Learning for Imbalanced Datasets: Clinical Validity of SMOTE Is Questionable

Risk Analysis of Bankruptcy in the U.S. Healthcare Industries Based on Financial Ratios: A Machine Learning Analysis

Contact Info

Product

Resources

About