Predictive Value of Machine Learning Based on Retinal Structural Changes for Early Parkinson's Disease Diagnosis

Abstract

Background The diagnosis of Parkinson disease (PD) is mainly based on clinical symptoms, and there is a lack of objective methods for correct diagnosis. At present, there have been studies on retinal structural changes as a biomark for early diagnosis of PD, but machine learning based on retinal structural changes for predicting early PD has not yet been studied. Objective To construct a machine learning model based on the characteristics of retinal structural changes, explore its value in early PD diagnosis, and the accuracy of different machine learning algorithms for early PD diagnosis. Methods From October 2021 to September 2022, 49 PD patients aged 40 to 70 years old (PD group) who attended outpatient clinics and were hospitalized in the department of neurology of Henan Provincial People's Hospital (PD group) and 39 healthy people with matching age and sex (healthy control group) who came to the hospital for physical examination were collected. All study subjects underwent swept-source optical coherence tomography and swept-source optical coherence tomography angiography, the thickness and vessel density of the macular retina were also quantitatively analyzed. The 88 subjects were randomly divided into the 62 training sets and 26 validation set according to the ratio of 7∶3. Variables with significant differences between the PD group and healthy control group were selected as the characteristic variables for inclusion in the machine learning model, and Logistic regression (LR) , K-nearest neighbor algorithm (KNN) , decision tree (DT) , random forest (RF) and extreme gradient boosting (XGboost) models were constructed in the training set. The area under the curve (AUC) , accuracy, sensitivity and specificity of the receiver operating characteristic (ROC) curve were used to evaluate the predictive value of the machine learning model based on retinal structural changes for early PD. Results Compared with the healthy control group, the density of the upper outer ring (A6) , the outer temporal outer ring (A7) , the lower outer ring (A8) and the outer nasal ring (A9) of the superficial capillaries in the PD group were reduced, the thickness of the upper inner ring (A2) , the inner temporal inner ring (A3) , the inferior inner ring (A4) , the inner ring of the nasal side (A5) of the retinal layer, A6, A7, A8 and A9, the thickness of A6 of the ganglion cell complex layer, the thickness of A7 of the nerve fiber layer, A2 and A4, A5, A6, A7, A8, A9 became thinner (P<0.05) . The reductions in A2 thickness of the retinal layer (OR=0.781, 95%CI=0.659-0.926) , A3 thickness of the retinal layer (OR=1.190, 95%CI=1.019-1.390) , A2 thickness of the outer retina (OR=0.748, 95%CI=0.603-0.929) , A6 thickness of the outer retina (OR=2.264, 95%CI=1.469-3.490) , A8 thickness of the outer retina (OR=0.723, 95%CI=0.576-0.906) , and A7 thickness of the nerve fiber layer (OR=0.592, 95%CI=0.454-0.773) , and the decrease in A7 density of the superficial capillaries (OR=1.966, 95%CI=1.399-2.765) were independent risk factors for the occurrence of early PD (P<0.05) . The above variables were involved to construct the machine learning model, the results showed that among the five models constructed, the LR model had the highest overall performance, with an AUC of 0.841, while the DT model has the highest accuracy at 0.846. Conclusion Machine learning model based on retinal features can accurately predict early PD, among which the DT model has high accuracy for early PD diagnosis.

Keywords

• parkinson disease|scan source optical coherence tomography|retina|machine learning|diagnosis, differential