High-accuracy detection of early Parkinson’s disease through multimodal features and machine learning
Abstract
Early (or preclinical) diagnosis of Parkinson's disease (PD) is crucial for its early management as by the time manifestation of clinical symptoms occur, more than 60% of the dopaminergic neurons have already been lost. It is now established that there exists a premotor stage, before the start of these classic motor symptoms, characterized by a constellation of clinical features, mostly non-motor in nature such as Rapid Eye Movement (REM) sleep Behaviour Disorder (RBD) and olfactory loss. In this paper, we use the non-motor features of RBD and olfactory loss, along with other significant biomarkers such as Cerebrospinal fluid (CSF) measurements and dopaminergic imaging markers from 183 healthy normal and 401 early PD subjects, as obtained from the Parkinson's Progression Markers Initiative (PPMI) database, to classify early PD subjects from normal using Naïve Bayes, Support Vector Machine (SVM), Boosted Trees and Random Forests classifiers. We observe that SVM classifier gave the best performance (96.40% accuracy, 97.03% sensitivity, 95.01% specificity, and 98.88% area under ROC). We infer from the study that a combination of non-motor, CSF and imaging markers may aid in the preclinical diagnosis of PD.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Prashanth et al. (2016) demonstrated accuracy 96.4% and sensitivity 97.03% for prodromal PD detection using SVM integrating nonmotor features, CSF biomarkers, and PET imaging data.
“Prashanth et al. (2016) demonstrated even higher precision (accuracy: 96.4%, sensitivity: 97.03%) by SVM, which integrates nonmotor features (including sleep behaviour disorders and olfactory loss), CSF biomarkers, and PET imaging data”
From Multimodal neuroimaging and AI integration in cognitive disorders: advances, challenges, and future directions for precision medicine (2026) · cites this paper as Prashanth et al., 2016
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · see citing works
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421 · see citing works
LIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918 · see citing works
No free lunch theorems for optimization
Wolpert, D. H., & Macready, W. G. (1997) · IEEE Transactions on Evolutionary Computation · doi:10.1109/4235.585893 · Cited by 14,237 · see citing works
Parkinsonism: onset, progression, and mortality
Hoehn, M. M., & Yahr, M. D. (1967) · Neurology · doi:10.1212/wnl.17.5.427 · Cited by 12,107 · see citing works
A Short Introduction to Boosting
Freund, Y., & Schapire, R. E. (1999) · Cited by 2,991 · see citing works
Uneven Pattern of Dopamine Loss in the Striatum of Patients with Idiopathic Parkinson's Disease
Kish, S. J., Shannak, K. S., & Hornykiewicz, O. (1988) · New England Journal of Medicine · doi:10.1056/nejm198804073181402 · Cited by 1,945 · see citing works
(2001) · Cited by 1,932 · see citing works
The Parkinson Progression Marker Initiative (PPMI)
MAREK, K. L., Jennings, D. L., Lasch, S., Siderowf, A. D., Tanner, C. M., Simuni, T., Coffey, C. S., Kieburtz, K. D., Flagg, E., Chowdhury, S., et al. (2011) · Progress in Neurobiology · doi:10.1016/j.pneurobio.2011.09.005 · Cited by 1,888 · see citing works
Doty, R. L., Shaman, P., & Dann, M. (1984) · Physiology & Behavior · doi:10.1016/0031-9384(84)90269-5 · Cited by 1,854 · see citing works
A brief introduction to boosting
Schapire, R. E. (1999) · Cited by 1,301 · see citing works
The REM sleep behavior disorder screening questionnaire—A new diagnostic instrument
Stiasny‐Kolster, K., Mayer, G., Schäfer, S., Möller, J. C., Heinzel‐Gutenbrunner, M., & Oertel, W. H. (2007) · Movement Disorders · doi:10.1002/mds.21740 · Cited by 1,065 · see citing works
Description of Parkinson's Disease as a Clinical Syndrome
Fahn, S. (2003) · Annals of the New York Academy of Sciences · doi:10.1111/j.1749-6632.2003.tb07458.x · Cited by 979 · see citing works
Iranzo, Á., Molinuevo, J. L., Santamaría, J., Serradell, M., Martı́, M. J., Valldeoriola, F., & Tolosa, E. S. (2006) · The Lancet Neurology · doi:10.1016/s1474-4422(06)70476-8 · Cited by 950 · see citing works
Quantifying the risk of neurodegenerative disease in idiopathic REM sleep behavior disorder
Postuma, R. B., Gagnon, J., Vendette, M., Fantini, M. L., Massicotte-Marquez, J., & Montplaisir, J. Y. (2008) · Neurology · doi:10.1212/01.wnl.0000340980.19702.6e · Cited by 779 · see citing works
Idiopathic hyposmia as a preclinical sign of Parkinson's disease
Ponsen, M. M., Stoffers, D., Booij, J., van Eck‐Smit, B. L. F., Wolters, E. C., & Berendse, H. W. (2004) · Annals of Neurology · doi:10.1002/ana.20160 · Cited by 741 · see citing works
Advances in Neural Information Processing Systems 15 (NIPS 2002)
Williams, C. K. I., & Shawe-Taylor, J. S. (2002) · Cited by 612 · see citing works
Multiple comparison analysis testing in ANOVA
McHugh, M. L. (2011) · Biochemia Medica · doi:10.11613/bm.2011.029 · Cited by 532 · see citing works
Stiasny‐Kolster, K. (2004) · Brain · doi:10.1093/brain/awh322 · Cited by 430 · see citing works
Olsson, A., Vanderstichele, H., Andreasen, N., Meyer, G. D., Wallin, A., Holmberg, B., Rosengren, L., Vanmechelen, E., & Blennow, K. (2004) · Clinical Chemistry · doi:10.1373/clinchem.2004.039347 · Cited by 424 · see citing works
Cerebrospinal fluid biomarkers for Parkinson disease diagnosis and progression
Shi, M. Y., Bradner, J. M., Hancock, A. M., Chung, K. A., Quinn, J. F., Peskind, E. R., Galasko, D., Jankovic, J. J., Zabetian, C. P., Kim, H. M., et al. (2010) · Annals of Neurology · doi:10.1002/ana.22311 · Cited by 418 · see citing works
Piggott, M. A., Marshall, E. F., Thomas, N., Lloyd, S. R., COURT, J. A., Jaros, E., Burn, D. J., Johnson, M. K., Perry, R. H., McKeith, I. G., et al. (1999) · Brain · doi:10.1093/brain/122.8.1449 · Cited by 330 · see citing works
Berendse, H. W., Booij, J., Francot, C. M. J. E., Bergmans, P., Hijman, R., Stoof, J. C., & Wolters, E. C. (2001) · Annals of Neurology · doi:10.1002/ana.1049 · Cited by 298 · see citing works
Biomarkers in Parkinson’s disease (recent update)
Sharma, S. K., Moon, C. S., Khogali, A., Haidous, A., Chabenne, A., Ojo, C., Jelebinkov, M., Kurdi, Y., & Ebadi, M. (2013) · Neurochemistry International · doi:10.1016/j.neuint.2013.06.005 · Cited by 242 · see citing works
Nomura, T., Inoue, Y., Kagimura, T., Uemura, Y., & Nakashima, K. (2011) · Sleep Medicine · doi:10.1016/j.sleep.2011.01.015 · Cited by 233 · see citing works
The role of dopaminergic imaging in patients with symptoms of dopaminergic system neurodegeneration
Cummings, J. L., Henchcliffe, C., Schaier, S., Simuni, T., Waxman, A., & Kemp, P. M. (2011) · Brain · doi:10.1093/brain/awr177 · Cited by 213 · see citing works
Prashanth, R., Roy, S. D., Mandal, P. K., & Ghosh, S. (2013) · Expert Systems with Applications · doi:10.1016/j.eswa.2013.11.031 · Cited by 140 · see citing works
Self-citationThe use of smell identification tests in the diagnosis of Parkinson's disease in Brazil
Silveira‐Moriyama, L., Carvalho, M. D. J., Katzenschlager, R., Petrie, A., Ranvaud, R., Barbosa, E. R., & Lees, A. J. (2008) · Movement Disorders · doi:10.1002/mds.22241 · Cited by 106 · see citing works
Strategies for comparing treatments on a binary response with multi-centre data
Agresti, A., & Hartzel, J. S. (2000) · Statistics in Medicine · doi:10.1002/(sici)1097-0258(20000430)19:8 · Cited by 102 · see citing works
Automatic assistance to Parkinsonˈs disease diagnosis in DaTSCAN SPECT imaging
Illán, I. A., Górriz, J. M., Ramı́rez, J., Segovia, F., Jiménez-Hoyuela, J. M., & Lozano, S. J. O. (2012) · Medical Physics · doi:10.1118/1.4742055 · Cited by 97 · see citing works
Classification of speech intelligibility in Parkinson's disease
Khan, T., Westin, J., & Dougherty, M. S. (2013) · Journal of Applied Biomedicine · doi:10.1016/j.bbe.2013.10.003 · Cited by 84 · see citing works
Improved Parkinsonism diagnosis using a partial least squares based approach
Segovia, F., Górriz, J. M., Ramı́rez, J., Álvarez, I., Jiménez-Hoyuela, J. M., & Ortega, S. J. (2012) · Medical Physics · doi:10.1118/1.4730289 · Cited by 66 · see citing works
Unveiling relevant non-motor Parkinson's disease severity symptoms using a machine learning approach
Armañanzas, R., Bielza, C., Chaudhuri, К. R., Martínez‐Martín, P., & Larrañaga, P. (2013) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2013.04.002 · Cited by 65 · see citing works
Berendse, H. W., & Ponsen, M. M. (2009) · Parkinsonism & Related Disorders · doi:10.1016/s1353-8020(09)70774-6 · Cited by 60 · see citing works
Accurate telemonitoring of Parkinson's disease diagnosis using robust inference system
Mandal, I., & Sairam, N. (2012) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2012.10.006 · Cited by 51 · see citing works
Automatic classification of 123I-FP-CIT (DaTSCAN) SPECT images
Towey, D., Bain, P. G., & Nijran, K. S. (2011) · Nuclear Medicine Communications · doi:10.1097/mnm.0b013e328347cd09 · Cited by 43 · see citing works
Technology Insight: imaging neurodegeneration in Parkinson's disease
Brooks, D. J. (2008) · Nature Clinical Practice Neurology · doi:10.1038/ncpneuro0773 · Cited by 43 · see citing works
The use of a color coded probability scale to interpret smell tests in suspected parkinsonism
Silveira‐Moriyama, L., Petrie, A., Williams, D. R., Evans, A. H., Katzenschlager, R., Barbosa, E. R., & Lees, A. J. (2009) · Movement Disorders · doi:10.1002/mds.22494 · Cited by 37 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Multimodal machine learning in precision health: A scoping review
Kline, A., Wang, H., Li, Y., Dennis, S., Hutch, M., Xu, Z., Wang, F., Cheng, F., & Luo, Y. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00712-8 · Cited by 528 · see citing works
“Of those, most were published using medical imaging and EHR data 34,36,48,53,56,57,60,62 – 64, 68, 71, 73, 75, 85 – 88, 90, 92 – 96 , 98, 100, 104, the time series information using t-SNE plots 58 .”
Machine Learning for the Diagnosis of Parkinson's Disease: A Review of Literature
Mei, J., Desrosiers, C., & Frasnelli, J. (2021) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2021.633752 · Cited by 404 · see citing works
“…method of 8 models (SVM, MLP, logistic regression, random forest, NSVC, decision tree, KNN, QDA) Sensitivity = 96% Specificity = 97% AUC = 0.98 2017 Adams, 2017 Classification of PD, HC and other neurological stance disorders Diagnosis and differential diagnosis Collected from participants 293; 57…”
MethodInfluentialEarly Detection of Parkinson’s Disease Using Deep Learning and Machine Learning
Wang, W., Lee, J., Harrou, F., & Sun, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3016062 · Cited by 400 · see citing works
“To guarantee early detection of PD, the premotor or prodromal stage in PD should be carefully monitored [24], [25].”
BackgroundMethodIntegrated multimodal artificial intelligence framework for healthcare applications
Soenksen, L. R., Ma, Y., Zeng, C., Boussioux, L., Villalobos Carballo, K., Na, L., Wiberg, H. M., Li, M. L., Fuentes, I., & Bertsimas, D. (2022) · npj Digital Medicine · doi:10.1038/s41746-022-00689-4 · Cited by 380 · see citing works
“…domains of cardiology 7 – 9 , dermatology 10 , gastroenterology 11 , gynecology 12 , hematology 13 , immunology 14 , nephrology 15 , neurology 16,17 , oncology 18 – 20 , ophthalmology 21 , psychiatry 22 , radiology 23 – 25 , public health 26 and healthcare operational analytics (i.e.,…”
The role of artificial neural network and machine learning in utilizing spatial information
Goel, A., Kumar, A., & Kumar, A. (2022) · Spatial Information Research · doi:10.1007/s41324-022-00494-x · Cited by 304 · see citing works
Artificial Intelligence in Pharmaceutical and Healthcare Research
Bhattamisra, S. K., Banerjee, P., Gupta, P., Mayuren, J., Patra, S., & Candasamy, M. (2023) · Big Data and Cognitive Computing · doi:10.3390/bdcc7010010 · Cited by 283 · see citing works
“Many studies were performed for the predictive modeling, which was noticeable for predicting early Parkinson’s disease [49].”
BackgroundMirbabaie, M., Stieglitz, S., & Frick, N. (2021) · Health and Technology · doi:10.1007/s12553-021-00555-5 · Cited by 244 · see citing works
“Studies performed predictive modeling via multiple algorithms, that is, logistic regression, random forest, decision tree and support vector machine, for the early detection of Parkinson’s disease [80].”
MethodCloud Computing-Based Framework for Breast Cancer Diagnosis Using Extreme Learning Machine
Lahoura, V., Singh, H., Aggarwal, A., Sharma, B., Mohammed, M. A., Damaševičius, R., Kadry, S., & Cengiz, K. (2021) · Diagnostics · doi:10.3390/diagnostics11020241 · Cited by 185 · see citing works
“[51] Parkinson’s Disease 2016 PPMI database Naïve Bayes, LR, Boosted Tree Random Forest, SVM Random Forest = 96.”
MethodMulti-modality machine learning predicting Parkinson’s disease
Makarious, M. B., Leonard, H. L., Vitale, D., Iwaki, H., Sargent, L. J., Dadu, A., Violich, I., Hutchins, E. D., Saffo, D., Bandrés‐Ciga, S., et al. (2022) · npj Parkinson s Disease · doi:10.1038/s41531-022-00288-w · Cited by 188 · see citing works
“Previous work has identi fi ed UPSIT as a top predictive feature, such as the study done by Prashanth and colleagues training a predictive model on CSF biomarkers 6 .”
BackgroundMachine learning and digital biomarkers can detect early stages of neurodegenerative diseases
Chudzik, A., Śledzianowski, A., & Przybyszewski, A. W. (2024) · Sensors · doi:10.3390/s24051572 · Cited by 122 · see citing works
“This method applies data mining techniques to attributes considered to be early symptoms of PD, such as cognitive disorders, rapid eye movements, sleep behavior disorders, and cerebrospinal fluid measurements [39].”
MethodDentamaro, V., Impedovo, D., Musti, L., Pirlo, G., & Taurisano, P. (2024) · Scientific Reports · doi:10.1038/s41598-024-70165-4 · Cited by 116 · see citing works
“…multimodal data (including imaging and clinical data) through machine learning was helpful in detecting brain abnormalities in PD. Prashanth et al. 49 used a combination of non-motor features of sleep behaviour disorder (RDB) and olfactory loss, cerebrospinal fluid (CSF) measurements, and Single…”
Zhang, J. (2022) · npj Parkinson s Disease · doi:10.1038/s41531-021-00266-8 · Cited by 109 · see citing works
“Later, Prashanth et al. 17 added non-motor clinical data features such as cerebrospinal fl uid (CSF) measurements to further improve the detection rate of early PD. Prashanth et al. 88 further found that shape and surface-fi tting-based features showed higher importance than striatal-binding ratios…”
BackgroundMethodInfluentialClinical applications of artificial intelligence in sleep medicine: A sleep clinician’s perspective
Bandyopadhyay, A., & Goldstein, C. (2023) · Sleep And Breathing · doi:10.1007/s11325-022-02592-4 · Cited by 108 · see citing works
Early detection of Parkinson’s disease through patient questionnaire and predictive modelling
Prashanth, R., & Roy, S. D. (2018) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2018.09.008 · Cited by 101 · see citing works
“To statistically compare the performances from the classifiers, multiple comparison test s were carried out [26, 55].”
MethodSelf-citationJunaid, M., Ali, S., Eid, F., El–Sappagh, S., & Abuhmed, T. (2023) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2023.107495 · Cited by 104 · see citing works
Rana, A., Dumka, A., Singh, R., Panda, M. K., Priyadarshi, N., & Twala, B. (2022) · Diagnostics · doi:10.3390/diagnostics12082003 · Cited by 96 · see citing works
“, 2016 [78] Naïve Bayes, random forest SVM, boosted trees Classification of PD from HC MATLAB PPMI database 584, 401 PD + 183 HC Highest accuracy obtained from SVM with RBF kernel—96.”
MethodSadr, H., Nazari, M., Khodaverdian, Z., Farzan, R., Yousefzadeh-Chabok, S., Ashoobi, M. T., Hemmati, H., Hendi, A., Ashraf, A., Pedram, M. M., et al. (2025) · European journal of medical research · doi:10.1186/s40001-025-02680-7 · Cited by 117 · see citing works
A Comprehensive Review on AI-Enabled Models for Parkinson’s Disease Diagnosis
Dixit, S., Bohre, K., Singh, Y., Himeur, Y., Mansoor, W., Atalla, S., & Srinivasan, K. (2023) · Electronics · doi:10.3390/electronics12040783 · Cited by 91 · see citing works
Predicting Parkinson’s Disease Progression: Evaluation of Ensemble Methods in Machine Learning
Nilashi, M., Abumalloh, R. A., Bidgoli, B. M., Samad, S., Ismail, M. Y., Alhargan, A., & Zogaan, W. A. (2022) · Journal of Healthcare Engineering · doi:10.1155/2022/2793361 · Cited by 86 · see citing works
“Prashanth et al. [68] concentrated on utilizing nonmotor signals in the early diagnosis of PD by deploying NB, SVM, Boosted Trees, and RF. findings indicated that SVM presented the highest accuracy value of 96.40%.”
InfluentialDetection of Parkinson Disease in Brain MRI using Convolutional Neural Network
Shah, P. M., Zeb, A., Shafi, U., Zaidi, S. F. A., & Shah, M. A. (2018) · International Conference on Automation and Computing (ICAC) · doi:10.23919/iconac.2018.8749023 · Cited by 85 · see citing works
Deep learning architectures for Parkinson's disease detection by using multi-modal features
Pahuja, G., & Prasad, B. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.105610 · Cited by 82 · see citing works
Classification of Parkinson's disease based on multi-modal features and stacking ensemble learning
Yang, Y., Wei, L., Hu, Y., Wu, Y. X., Hu, L., & Nie, S. (2020) · Journal of Neuroscience Methods · doi:10.1016/j.jneumeth.2020.109019 · Cited by 80 · see citing works
Machine learning and artificial intelligence in the service of medicine: Necessity or potentiality?
Alsuliman, T., Humaidan, D., & Sliman, L. (2020) · Current Research in Translational Medicine · doi:10.1016/j.retram.2020.01.002 · Cited by 79 · see citing works
“Starting from the early prognosis of PD, a recent work by Prashanth et al. [48] presented an ML system that can accurately predict PD with an accuracy of 96.40 %.”
InfluentialNilashi, M., Ahmadi, H., Sheikhtaheri, A., Naemi, R., Alotaibi, R., Alarood, A. A., Munshi, A. M., Rashid, T. A., & Zhao, J. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113562 · Cited by 74 · see citing works
Paul, S., Maindarkar, M. A., Saxena, S., Saba, L., Turk, M., Kalra, M. K., Krishnan, P. R., & Suri, J. S. (2022) · Diagnostics · doi:10.3390/diagnostics12010166 · Cited by 74 · see citing works
“The Low-Moderate (LM) studies [1,5,9,37,62,65] observations are the articles containing information such as (i) high data count of the PD vs. normal; (ii) performance measures; (iii) comparative analysis with various ML, DL, and HDL algorithms; (iv) explanations of the benchmarking studies.”
BackgroundMethodPaydar, K., Kalhori, S. R. N., Akbarian, M., & Sheikhtaheri, A. (2016) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2016.10.018 · Cited by 74 · see citing works
Machine Learning in Human Olfactory Research
Lötsch, J., Kringel, D., & Hummel, T. (2019) · Chemical Senses · doi:10.1093/chemse/bjy067 · Cited by 71 · see citing works
“Among many machine-learning methods (Murphy 2012; Dhar 2013), a subset has so far been applied to problems related to human olfactory research, of which SVM, regression models and several kinds of decision tree algorithms have so far most frequently been mentioned.”
MethodInfluentialData-driven gait analysis for diagnosis and severity rating of Parkinson’s disease
Balaji, E., Brindha, D., Elumalai, V. K., & Umesh, K. (2021) · Medical Engineering & Physics · doi:10.1016/j.medengphy.2021.03.005 · Cited by 68 · see citing works
Wang, C., Chen, X., Du, L., Zhan, Q., Yang, T., & Fang, Z. (2019) · Computer Methods and Programs in Biomedicine · doi:10.1016/j.cmpb.2019.105267 · Cited by 68 · see citing works
Kang, M. J., Kim, S., Na, D. L., Kim, B. C., Yang, D. W., Kim, E., Na, H. R., Han, H. J., Lee, J., Kim, J. H., et al. (2019) · BMC Medical Informatics and Decision Making · doi:10.1186/s12911-019-0974-x · Cited by 67 · see citing works
Cheng, Z., Zhang, J., He, N., Li, Y., Wen, Y., Xu, H., Tang, R., Jin, Z., Haacke, E. M., Yan, F., et al. (2019) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2019.00167 · Cited by 66 · see citing works
Machine learning algorithms for the diagnosis of Alzheimer and Parkinson disease
S, N. N. R., & J., P. (2022) · Journal of Medical Engineering & Technology · doi:10.1080/03091902.2022.2097326 · Cited by 51 · see citing works
Tang, J., Yang, B., Adams, M. P., Shenkov, N., Klyuzhin, I. S., Fotouhi, S., Davoodi‐Bojd, E., Lu, L., Hamid Soltanian-zadeh, A., Sossi, V., et al. (2019) · Molecular Imaging and Biology · doi:10.1007/s11307-019-01334-5 · Cited by 60 · see citing works
Deep Learning-based Early Parkinson’s Disease Detection from Brain MRI Image
Sangeetha, S., Baskar, K., Kalaivaani, P. C. D., & Kumaravel, T. (2023) · International Conference on Intelligent Computing and Control Systems (ICICCS) · doi:10.1109/iciccs56967.2023.10142754 · Cited by 59 · see citing works
“In the publicat ion [8], Prashanth and others focused on nonmotor factors for the diagnosis of PD.”
BackgroundDolatshahi, M., Pourmirbabaei, S., Kamalian, A., Ashraf‐Ganjouei, A., Yaseri, M., & Aarabi, M. H. (2018) · Frontiers in Neurology · doi:10.3389/fneur.2018.00560 · Cited by 57 · see citing works
“Correlation Between Baseline Clinical Entities of PD Patients and Longitudinal Changes of CSF Markers It has been suggested that Rapid Eye Movement (REM) sleep Behavior Disorder (RBD) can be a clue to early diagnosis of neurodegenerative diseases (42), specifically it can help with early detection of PD (19, 43, 44).”
BackgroundMartinez-Eguiluz, M., Arbelaitz, O., Gurrutxaga, I., Muguerza, J., Perona, I., Murueta‐Goyena, A., Acera, M., Pino, R. D., Tijero, B., Gómez‐Esteban, J. C., et al. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07256-8 · Cited by 54 · see citing works
“[28] obtained high classification accuracy of PD patients and controls with Support Vector Machine (SVM) algorithm using non-motor symptoms, cerebrospinal fluid (CSF) markers and dopamine transporter imaging using SPECT.”
MethodAbirami, L., & Karthikeyan, J. (2023) · IEEE Access · doi:10.1109/access.2023.3312278 · Cited by 53 · see citing works
Sleep quality prediction in caregivers using physiological signals
Sadeghi, R., Banerjee, T., Hughes, J. C., & Lawhorne, L. W. (2019) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2019.05.010 · Cited by 50 · see citing works
“A wide range of studies explore the relationship between sleep and health issues such as obesity [17], weakened immune system [18], Parkinson’s disease [19,20], mortality [5], heart failure [21], and cancer [22].”
BackgroundYousefi, M., Akhbari, M., Mohamadi, Z., Karami, S., Dasoomi, H., Atabi, A., Sarkeshikian, S. A., Dehaki, M. A., Bayati, H., Mashayekhi, N., et al. (2024) · Frontiers in Neurology · doi:10.3389/fneur.2024.1413071 · Cited by 51 · see citing works
Zhang, J., Gao, Y., He, X.-T., Feng, S., Hu, J., Zhang, Q., Zhao, J., Huang, Z., Wang, L., Ma, G., et al. (2021) · European Radiology · doi:10.1007/s00330-020-07575-1 · Cited by 47 · see citing works
“998 AUC) compared to the model with a single feature [36].”
MethodRenner, H., Schöler, H. R., & Bruder, J. M. (2021) · Movement Disorders · doi:10.1002/mds.28775 · Cited by 47 · see citing works
“169 Importantly, Wisely et al and Glaab et al directly compared the performance of models based on multiple versus single data types and found that the combination of multimodal data sets resulted in better predictions.”
BackgroundBhidayasiri, R., Sringean, J., Phumphid, S., Anan, C., Thanawattano, C., Deoisres, S., Panyakaew, P., Phokaewvarangkul, O., Maytharakcheep, S., Buranasrikul, V., et al. (2024) · Frontiers in Neurology · doi:10.3389/fneur.2024.1386608 · Cited by 42 · see citing works
Dennis, A.-G. P., & Strafella, A. P. (2024) · Parkinsonism & Related Disorders · doi:10.1016/j.parkreldis.2024.106986 · Cited by 41 · see citing works
Twala, B. (2025) · Frontiers in Aging Neuroscience · doi:10.3389/fnagi.2025.1638340 · Cited by 47 · see citing works
Parkinson's disease detection using ensemble techniques and genetic algorithm
Fayyazifar, N., & Samadiani, N. (2017) · CSI International Symposium on Artificial Intelligence and Signal Processing · doi:10.1109/aisp.2017.8324074 · Cited by 41 · see citing works
“[10] Boosted Tree + multimodal features 22 95.”
BackgroundMethodA review on multimodal machine learning in medical diagnostics
Yan, K., Li, T., Marques, J. A. L., Gao, J. T., & Fong, S. J. (2023) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2023382 · Cited by 42 · see citing works
Rider, N. L., Miao, D., Dodds, M., Modell, V., Modell, F., Quinn, J., Schwarzwald, H. L., & Orange, J. S. (2019) · Frontiers in Pediatrics · doi:10.3389/fped.2019.00070 · Cited by 39 · see citing works
Huang, G., Li, R., Bai, Q., & Alty, J. (2023) · Health Information Science and Systems · doi:10.1007/s13755-023-00231-0 · Cited by 38 · see citing works
“…cycle, and in sleep behaviours, in both AD and PD. Olfactory (sense of smell) loss is also commonly observed in individuals with AD and PD. Prashanth et al. were able to classify participants into PD and HC groups using sleep behaviour and olfactory function data with an accuracy of 96.40 % [26].”
BackgroundMethodInfluentialPaiva, J. S., Cardoso, J. M. R., & Pereira, T. (2017) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2017.10.011 · Cited by 38 · see citing works
Classification of Parkinson’s Disease in Patch-Based MRI of Substantia Nigra
Hussain, S. S., Xu, D., Shah, P. M., Islam, S. U., Alam, M., Khan, I. A., Awwad, F. A. A., & Ismail, E. A. A. (2023) · Diagnostics · doi:10.3390/diagnostics13172827 · Cited by 36 · see citing works
“In [20], the authors used non-motor features for diagnosis purposes of PD.”
Artificial Intelligence Meets Neuro-Ophthalmology
Leong, Y.-Y., Vasseneix, C., Finkelstein, M. T., Miléa, D., & Najjar, R. P. (2022) · Asia-Pacific Journal of Ophthalmology · doi:10.1097/apo.0000000000000512 · Cited by 36 · see citing works
“Briefly, ML techniques have been evaluated in gaze parameters for neurodegenerative diseases 80 (Parkinson disease, 81,82 Alzheimer disease 83 ) and neuro-psychi-atric diseases.”
MethodSar, A., Puri, P. S., Naz, H. U., Aich, S., Choudhury, T., & Gabralla, L. A. (2025) · Scientific Reports · doi:10.1038/s41598-025-21407-6 · Cited by 35 · see citing works
Jayaram, R., & Prabakaran, S. (2020) · Egyptian Informatics Journal · doi:10.1016/j.eij.2020.12.003 · Cited by 37 · see citing works
Federated learning for multi-omics: A performance evaluation in Parkinson’s disease
Danek, B. P., Makarious, M. B., Dadu, A., Vitale, D., Lee, P. S., Singleton, A., Nalls, M. A., Sun, J., & Faghri, F. (2024) · Patterns · doi:10.1016/j.patter.2024.100945 · Cited by 34 · see citing works
“Concretely, the adoption of sophisticated ML models can aid in tasks such as biomarker detection, disease subtyping, 1 disease identification, 2,3,4 and the development of novel medical interventions.”
End-to-End Deep Learning Method for Detection of Invasive Parkinson’s Disease
Mahmood, A., Khan, M. M., Imran, M. A., Alhajlah, O., Dhahri, H., & Karamat, T. (2023) · Diagnostics · doi:10.3390/diagnostics13061088 · Cited by 34 · see citing works
RETRACTED ARTICLE: Machine learning ensemble for neurological disorders
Kaur, H., Malhi, A. K., & Pannu, H. S. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04720-1 · Cited by 33 · see citing works
“[33] used boosted tree with multimodel feature selection technique and achieve 95.”
MethodRetractedShen, Z., Huang, J., Wei, H., Niu, H., Li, B., Li, R., & Liu, G. (2020) · Bioelectrochemistry · doi:10.1016/j.bioelechem.2020.107532 · Cited by 33 · see citing works
Corridon, P. R., Wang, X., Shakeel, A., & Chan, V. (2022) · Biomedicines · doi:10.3390/biomedicines10102445 · Cited by 31 · see citing works
“Several years ago, predictive modeling via multiple algorithms showed promise for early disease detection [46].”
MethodFolador, J. P., Santos, M. C. S., Luiz, L. M. D., de Souza, L. A. P. S., Vieira, M. F., Pereira, A. A., & Andrade, A. D. O. (2021) · Medical & Biological Engineering & Computing · doi:10.1007/s11517-020-02303-9 · Cited by 30 · see citing works
Salari, N., Kazeminia, M., Sagha, H., Daneshkhah, A., Ahmadi, A., & Mohammadi, M. (2022) · Current Psychology · doi:10.1007/s12144-022-02949-8 · Cited by 32 · see citing works
“In four studies, the categorization was between PD patients and healthy population (Magesh et al., 2020; Hsu et al., 2019; Prashanth et al., 2016a).”
BackgroundMethodResultInfluentialHayashi, Y., Oishi, T., Shirotori, K., Marumo, Y., Kosugi, A., Kumada, S., Hirai, D., Takayama, K., & Onuki, Y. (2018) · Drug Development and Industrial Pharmacy · doi:10.1080/03639045.2018.1434195 · Cited by 30 · see citing works
“Several studies have reported that objective variables could be predicted from explanatory variables using BT, such as the prediction of human intestinal absorption [10], detection of early Parkinson’s disease [11], and prediction of gene–disease associations [13].”
BackgroundMachine Learning Based Automatic Prediction of Parkinson’s Disease Using Speech Features
Jain, D., Mishra, A. K., & Das, S. K. (2020) · Advances in intelligent systems and computing · doi:10.1007/978-981-15-4992-2_33 · Cited by 29 · see citing works
Detection of cognitive impairment using a machine-learning algorithm
Youn, Y. C., Choi, S. H., Shin, H., Kim, K. W., Jang, J., Jung, J. J., Hsiung, G. R., & Kim, S. (2018) · Neuropsychiatric Disease and Treatment · doi:10.2147/ndt.s171950 · Cited by 28 · see citing works
“27 However, the sensitivity of the algorithm using the KDSQ to detect the CI was 91.5%, which is good for a screening tool.”
Influentialdos Santos, D. P., Scheibl, S., Arnhold, G., Mähringer‐Kunz, A., Düber, C., Mildenberger, P., & Kloeckner, R. (2018) · British Journal of Radiology · doi:10.1259/bjr.20170564 · Cited by 28 · see citing works
Zhang, J., Chen, X., Song, A., & Li, X. (2023) · International Journal of Medical Informatics · doi:10.1016/j.ijmedinf.2023.105024 · Cited by 26 · see citing works
Miah, A. S. M., Suzuki, T., & Shin, J. (2025) · IEEE Access · doi:10.1109/access.2025.3575023 · Cited by 25 · see citing works
Early and High‐Accuracy Diagnosis of Parkinson’s Disease: Outcomes of a New Model
Doumari, S. A., Berahmand, K., & Ebadi, M. J. (2023) · Computational and Mathematical Methods in Medicine · doi:10.1155/2023/1493676 · Cited by 25 · see citing works
Artificial Intelligence in Ophthalmology: Advantages and Limits
Costin, H. N., Fira, M., & Goraş, L. (2025) · Applied Sciences · doi:10.3390/app15041913 · Cited by 28 · see citing works
Decoding Intracranial EEG With Machine Learning: A Systematic Review
Mirchi, N., Warsi, N. M., Zhang, F., Wong, S. M., Suresh, H., Mithani, K., Erdman, L., & Ibrahim, G. M. (2022) · Frontiers in Human Neuroscience · doi:10.3389/fnhum.2022.913777 · Cited by 25 · see citing works
“This type of approach has also been applied for other applications relevant to neurology such as early detection of Parkinson’s disease (Prashanth et al., 2016), falls (Nahiduzzaman et al., 2020) and identification of cortical dysplasia (Mo et al., 2019).”
MethodPDD-ET: Parkinson’s Disease Detection Using ML Ensemble Techniques and Customized Big Dataset
Chatterjee, K., Kumar, R. P., Bandyopadhyay, A., Swain, S., Mallik, S., Li, A., & Ray, K. (2023) · Information · doi:10.3390/info14090502 · Cited by 24 · see citing works
Islam, N., Turza, M. S. A., Fahim, S. I., & Rahman, R. M. (2024) · International Journal of Cognitive Computing in Engineering · doi:10.1016/j.ijcce.2024.05.001 · Cited by 22 · see citing works
Esan, A. O., Olawade, D. B., Soladoye, A. A., Omodunbi, B. A., Adeyanju, I., & Aderinto, N. (2025) · Current Research in Translational Medicine · doi:10.1016/j.retram.2025.103541 · Cited by 22 · see citing works
PARNet: Deep neural network for the diagnosis of parkinson's disease
Keleş, A., Keles, M. B., Keles, M. B., & Okatan, A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16940-3 · Cited by 21 · see citing works
“Support vector machine (SVM) [9], decision tree, and linear regression classifiers are used in these studies where a person mainly extracts the features [10–12].”
Ketkar, Y., & Gawade, S. D. (2022) · Healthcare Analytics · doi:10.1016/j.health.2022.100117 · Cited by 20 · see citing works
Zhang, Q., Xiong, J., Cai, Y., Shi, J., Xu, S., & Zhang, Q. (2019) · Biomedizinische Technik/Biomedical Engineering · doi:10.1515/bmt-2018-0136 · Cited by 20 · see citing works
“Prashanth et al. [13] showed that a combination of cerebrospinal fluid, non-motor and imaging markers may aid in the diagnosis of preclinical Parkinson’s disease.”
BackgroundEnhancing clinical trial outcome prediction with artificial intelligence: a systematic review
Qian, L., Lu, X., Haris, P. I., Zhu, J., Li, S., & Yang, Y. (2025) · Drug Discovery Today · doi:10.1016/j.drudis.2025.104332 · Cited by 23 · see citing works
Predictive analytics and machine learning for medical informatics: A survey of tasks and techniques
Lamba, D., Hsu, W. H., & Alsadhan, M. (2021) · Elsevier eBooks · doi:10.1016/b978-0-12-821777-1.00023-9 · Cited by 21 · see citing works
“(2016), who discuss experimental Parkinson’s treatments [242]; Kolachalama and Garg (2018) survey machine learning as a subarea of artificial intelligence (AI), particularly in medical education [243]; and BannachBrown et al.”
BackgroundMachine learning Ensemble for the Parkinson’s disease using protein sequences
Arora, P., Mishra, A., & Malhi, A. K. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12960-7 · Cited by 19 · see citing works
“Chen et al. [9] proposed a method using fuzzy k-nearest neighbour (FKNN) to diagnose PD and comparison has been conducted between SVM and FKNN. Prashanth et al. [38] applied SVM, Naive Bayes, Random Forests and Boosted Trees classifiers for early diagnosis of PD.”
Methoddos Santos, M. C. T., Bell, R., & da Costa, A. N. (2016) · Bioanalysis · doi:10.4155/bio-2016-0166 · Cited by 19 · see citing works
Palumbo, B., Bianconi, F., Nuvoli, S. M. F., Spanu, A., & Fravolini, M. L. (2020) · Clinical and Translational Imaging · doi:10.1007/s40336-020-00404-x · Cited by 19 · see citing works
Zhu, S. (2022) · International Conference on Bioinformatics and Computational Biology (ICBCB) · doi:10.1109/icbcb55259.2022.9802132 · Cited by 17 · see citing works
“Furthermore, some studies have used only patient scores or symptom-based assessments (Prashanth et al. 2016), along with other biomarkers.”
Gatti, R., Atum, Y., Schiaffino, L., Jochumsen, M., & Manresa, J. B. B. (2020) · European Journal of Neuroscience · doi:10.1111/ejn.14936 · Cited by 5 · see citing works
Parkinson’s disease detection based on dysphonia measurements
Lahmiri, S. (2016) · Physica A Statistical Mechanics and its Applications · doi:10.1016/j.physa.2016.12.009 · Cited by 16 · see citing works
Applications of Machine Learning to Diagnosis of Parkinson’s Disease
Lai, H., Li, X., Xu, F., Zhu, J., Li, X., Yang, S. T., Wang, X., Wang, Z., & Wang, C. (2023) · Brain Sciences · doi:10.3390/brainsci13111546 · Cited by 15 · see citing works
“…Prashanth et al. utilized a combination of NMS features, cerebrospinal fluid (CSF), and imaging markers to differentiate early PD subjects from normal individuals using the naïve Bayes, SVM, boosted trees, and RF methods, observing that the SVM classifier delivered the most optimal performance [38].”
BackgroundMethodAggarwal, N., Saini, B. S., & Gupta, S. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106008 · Cited by 15 · see citing works
Vitale, A., Villa, R., Ugga, L., Romeo, V., Stanzione, A., & Cuocolo, R. (2021) · Mathematical Biosciences & Engineering · doi:10.3934/mbe.2021091 · Cited by 15 · see citing works
“Using PPMI dataset, Prashanth et al. [34] tried to find the best ML approach to identify early PD patients through the use of multimodal features such as non-motor features of RBD and olfactory loss, along with CSF measurements and dopaminergic imaging markers.”
Distribution of non-motor symptoms in idiopathic Parkinson’s disease and secondary Parkinsonism
Skogar, Ö., & Nilsson, M. (2018) · Journal of Multidisciplinary Healthcare · doi:10.2147/jmdh.s170307 · Cited by 14 · see citing works
“31 However, these are not available in everyday practice and the clinicians often have to rely on their clinical skills to deal with the diagnostic challenges.”
Ahmed, S., Komeili, M., & Park, J. (2022) · Scientific Reports · doi:10.1038/s41598-022-25454-1 · Cited by 13 · see citing works
Explainable AI approach for early detection of Parkinson’s disease using PPMI Online data
Aggarwal, N., Saxena, G. J., Singh, S., & Pundir, A. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-10127-z · Cited by 13 · see citing works
Cieri, F., Giriprakash, P. P., Nandy, R. R., Zhuang, X., Doty, R. L., Caldwell, J., & Cordes, D. (2024) · Neuroscience · doi:10.1016/j.neuroscience.2024.08.031 · Cited by 13 · see citing works
“These include preclinical diagnosis of PD using multimodal features including olfaction, cerebrospinal fluid (CSF), and imaging markers (Prashanth et al., 2016); identifying a specific pattern within the University of Pennsylvania Smell Identification Test (UPSIT) score (Doty & Kamath, 2014) that…”
A Smart Wearable Ring Device for Sensing Hand Tremor of Parkinson’s Patients
Yang, H., Shen, Y., Zhuang, W., Gao, C., Dai, D., & Zhang, W. (2021) · Computer Modeling in Engineering & Sciences · doi:10.32604/cmes.2021.014558 · Cited by 13 · see citing works
Harimoorthy, K., & Menakadevi, T. (2021) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.6419 · Cited by 13 · see citing works
Talai, A. S., Ismail, Z., Sedlacik, J., Boelmans, K., & Forkert, N. D. (2018) · Clinical Neuroradiology · doi:10.1007/s00062-018-0727-8 · Cited by 13 · see citing works
Yoon, S., Kim, M., & Lee, W. (2023) · Journal of Clinical Neurology · doi:10.3988/jcn.2022.0160 · Cited by 12 · see citing works
“…tree and medium Gaussian SVM Gait impairments and tremor occurrences X Zeng et al. (2016) 14 Radial basis function neural networks Gait patterns X Prashanth et al. (2016) 15 SVM, naïve Bayes, boosted trees, and RF Nonmotor symptoms and biomarkers (PPMI) X Wang et al. (2020) 16 Three deep…”
Leger, C. S., Herbert, M., & DeSouza, J. F. X. (2020) · Frontiers in Neurology · doi:10.3389/fneur.2020.00364 · Cited by 12 · see citing works
“Hyposmia and RBD are not specific to PD, yet hyposmia in particular has been the predictor of greatest import in early PD predictive modeling (43), the dominant predictive model driver for those with genetic risk (41), and of secondary import only to imaging in other early PD predictive modeling research (42).”
BackgroundShaffi, N., Viswan, V., Mahmud, M., Hajamohideen, F., & Subramanian, K. (2023) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci52147.2023.10371926 · Cited by 11 · see citing works
“Prasanth et al. [15] used RBD alongside other biomarkers, such as cerebrospinal fluid measurements and dopaminergic image markers, to distinguish PD from normal subjects.”
BackgroundDeveloping a Model for Parkinson’s Disease Detection Using Machine Learning Algorithms
Mudawi, N. A. (2024) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2024.048967 · Cited by 11 · see citing works
“Research by Prashantha et al. [13] distinguishes early PD patients from healthy controls.”
Wang, X., Fan, L., Li, H., Bi, X., Jiang, W., & Ma, X. (2024) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2024.106862 · Cited by 11 · see citing works
Blood SSR1: A Possible Biomarker for Early Prediction of Parkinson’s Disease
Zhang, W., Shen, J., Wang, Y., Cai, K., Zhang, Q., & Cao, M. (2022) · Frontiers in Molecular Neuroscience · doi:10.3389/fnmol.2022.762544 · Cited by 11 · see citing works
Nabizadeh, F., Pirahesh, K., & Valizadeh, P. (2022) · Journal of Neurology · doi:10.1007/s00415-022-11120-z · Cited by 11 · see citing works
- Authors
- Prashanth, R., Dutta Roy, S., Mandal, P. K., & Ghosh, S.
- Affiliations
- Indian Institute of Technology Delhi (IN)
- Johns Hopkins University (US)
- Harvard University (US)
- Corresponding author
- Prashanth, R.
- Venue
- International Journal of Medical Informatics
- Publisher
- Elsevier BV
- Published
- 2016-06
- Volume
- 90
- Pages
- 13-21
- ISSN
- 1386-5056 (ISSN-L)
- OpenAlex
- W2290432223
- Cited by
- 244
- References
- 39
- Citations by year
- 2026: 28 · 2025: 40 · 2024: 31 · 2023: 36 · 2022: 37 · 2021: 21 · 2020: 20 · 2019: 10 · 2018: 12 · 2017: 6 · 2016: 3
- FWCI
- 7.77
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- International Journal of Medical Informatics (publishedVersion)
- PubMed (publishedVersion)
- Funders
- Michael J
- Topics
- Health Sciences › Medicine › Neurology › Parkinson's Disease Mechanisms and Treatments
- Health Sciences › Health Professions › Health Information Management › Artificial Intelligence in Healthcare
- Health Sciences › Medicine › Psychiatry and Mental health › Dementia and Cognitive Impairment Research
- Keywords
- Parkinson's disease, early diagnosis, preclinical diagnosis, REM sleep behavior disorder, olfactory loss, non-motor symptoms, cerebrospinal fluid biomarkers, multimodal fusion, Parkinson's Progression Markers Initiative, support vector machine, classifier comparison
- MeSH terms
- Machine Learning, Olfaction Disorders, Humans, Parkinson Disease, Models, Statistical, Tomography, Emission-Computed, Single-Photon, Databases, Factual, REM Sleep Behavior Disorder, Early Diagnosis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
