Artificial Intelligence Approaches for the Detection of Normal Pressure Hydrocephalus: A Systematic Review
Normal pressure hydrocephalus (NPH) is a neurological disorder characterized by altered cerebrospinal fluid accumulation in the brain’s ventricles, leading to symptoms such as gait disturbance and cognitive impairment. Artificial intelligence (AI), including machine learning (ML) and deep learning (...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Applied Sciences |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2076-3417/15/7/3653 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850188213439692800 |
|---|---|
| author | Luis R. Mercado-Diaz Neha Prakash Gary X. Gong Hugo F. Posada-Quintero |
| author_facet | Luis R. Mercado-Diaz Neha Prakash Gary X. Gong Hugo F. Posada-Quintero |
| author_sort | Luis R. Mercado-Diaz |
| collection | DOAJ |
| description | Normal pressure hydrocephalus (NPH) is a neurological disorder characterized by altered cerebrospinal fluid accumulation in the brain’s ventricles, leading to symptoms such as gait disturbance and cognitive impairment. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), shows promise in diagnosing NPH using medical images. In this systematic review, we examined 21 papers on the use of AI in detecting NPH. The studies primarily focused on differentiating NPH from other neurodegenerative disorders, such as Parkinson’s disease and Alzheimer’s disease. We found that traditional ML methods like Support Vector Machines, Random Forest, and Logistic Regression were commonly used, while DL methods, particularly Deep Convolutional Neural Networks, were also widely employed. The accuracy of these approaches varied, ranging from 70% to 95% in differentiating NPH from other conditions. Feature selection techniques were used to identify relevant parameters for diagnosis. MRI scans were more frequently used than CT scans, but both modalities showed promise. Evaluation metrics like Dice similarity coefficients and ROC-AUC were the most typical metrics of model performance. Challenges in implementing AI in clinical practice were identified, and the authors suggested that a hybrid deep-traditional ML framework could enhance NPH diagnosis. Further research is needed to maximize the benefits of AI while addressing limitations. |
| format | Article |
| id | doaj-art-d0ede9a0077347afaa888f2ff984ccbe |
| institution | OA Journals |
| issn | 2076-3417 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Applied Sciences |
| spelling | doaj-art-d0ede9a0077347afaa888f2ff984ccbe2025-08-20T02:15:55ZengMDPI AGApplied Sciences2076-34172025-03-01157365310.3390/app15073653Artificial Intelligence Approaches for the Detection of Normal Pressure Hydrocephalus: A Systematic ReviewLuis R. Mercado-Diaz0Neha Prakash1Gary X. Gong2Hugo F. Posada-Quintero3Department of Biomedical Engineering, University of Connecticut, Storrs, CT 06269, USAParkinson’s Disease and Movement Disorders Center, Department of Neurology, University of Connecticut Health Center, Farmington, CT 06269, USADivision of Neuroradiology, Department of Radiology, University of Connecticut Health Center, Farmington, CT 06269, USADepartment of Biomedical Engineering, University of Connecticut, Storrs, CT 06269, USANormal pressure hydrocephalus (NPH) is a neurological disorder characterized by altered cerebrospinal fluid accumulation in the brain’s ventricles, leading to symptoms such as gait disturbance and cognitive impairment. Artificial intelligence (AI), including machine learning (ML) and deep learning (DL), shows promise in diagnosing NPH using medical images. In this systematic review, we examined 21 papers on the use of AI in detecting NPH. The studies primarily focused on differentiating NPH from other neurodegenerative disorders, such as Parkinson’s disease and Alzheimer’s disease. We found that traditional ML methods like Support Vector Machines, Random Forest, and Logistic Regression were commonly used, while DL methods, particularly Deep Convolutional Neural Networks, were also widely employed. The accuracy of these approaches varied, ranging from 70% to 95% in differentiating NPH from other conditions. Feature selection techniques were used to identify relevant parameters for diagnosis. MRI scans were more frequently used than CT scans, but both modalities showed promise. Evaluation metrics like Dice similarity coefficients and ROC-AUC were the most typical metrics of model performance. Challenges in implementing AI in clinical practice were identified, and the authors suggested that a hybrid deep-traditional ML framework could enhance NPH diagnosis. Further research is needed to maximize the benefits of AI while addressing limitations.https://www.mdpi.com/2076-3417/15/7/3653deep learningmachine learningnormal pressure hydrocephalus |
| spellingShingle | Luis R. Mercado-Diaz Neha Prakash Gary X. Gong Hugo F. Posada-Quintero Artificial Intelligence Approaches for the Detection of Normal Pressure Hydrocephalus: A Systematic Review Applied Sciences deep learning machine learning normal pressure hydrocephalus |
| title | Artificial Intelligence Approaches for the Detection of Normal Pressure Hydrocephalus: A Systematic Review |
| title_full | Artificial Intelligence Approaches for the Detection of Normal Pressure Hydrocephalus: A Systematic Review |
| title_fullStr | Artificial Intelligence Approaches for the Detection of Normal Pressure Hydrocephalus: A Systematic Review |
| title_full_unstemmed | Artificial Intelligence Approaches for the Detection of Normal Pressure Hydrocephalus: A Systematic Review |
| title_short | Artificial Intelligence Approaches for the Detection of Normal Pressure Hydrocephalus: A Systematic Review |
| title_sort | artificial intelligence approaches for the detection of normal pressure hydrocephalus a systematic review |
| topic | deep learning machine learning normal pressure hydrocephalus |
| url | https://www.mdpi.com/2076-3417/15/7/3653 |
| work_keys_str_mv | AT luisrmercadodiaz artificialintelligenceapproachesforthedetectionofnormalpressurehydrocephalusasystematicreview AT nehaprakash artificialintelligenceapproachesforthedetectionofnormalpressurehydrocephalusasystematicreview AT garyxgong artificialintelligenceapproachesforthedetectionofnormalpressurehydrocephalusasystematicreview AT hugofposadaquintero artificialintelligenceapproachesforthedetectionofnormalpressurehydrocephalusasystematicreview |