PMC:4718081 / 13128-19201 JSONTXT

{"target":"https://pubannotation.org/docs/sourcedb/PMC/sourceid/4718081","sourcedb":"PMC","sourceid":"4718081","source_url":"https://www.ncbi.nlm.nih.gov/pmc/4718081","text":"Result\n\nModel performance\nFigure 4 indicates that mini network disorder probability has good linear relationship with MMSE suggesting that mini network disorder may be a good proxy for disease progression. Figure 5 shows that our model may improve the classification accuracy and specificity of AD vs. normal and MCI vs. normal. Our model may enhance the classification sensitivity of MCI vs. normal.\nFigure 4 The relationship and correlation analysis between estimated mini network disruption probability and MMSE. As plot AD, MCI, and normal shown, mini network disruption probability coincides with 1/MMSE. In plot regression, least squares regression is used to analyze the correlation between mini network disruption probability and MMSE.\nFigure 5 Model performance in classification of AD vs. normal and MCI vs. normal.\n\nEvaluation of mini network balance\nMini network balance map (see Figure 6) is used to describe mini network imbalance visually. The closer to equilateral triangle the shape is, the less serious the mini network imbalance is. The results (Figure 6B) show that mini network imbalance deteriorates rapidly from 12 to 24 and 36 to 48 months while there is a plateau between the above two periods in both AD and MCI group, which coincide with the changes of MMSE.\nFigure 6 Mini network balance map of AD based on CSF biomarkers panel. (A) Mini network balance maps for the three groups at different time points. (B) Longitudinal mini network balance maps for the three groups. In normal state, the shape of mini network balance map is equilateral triangle. With the shape deformation, the mini network imbalance gets serious. The results of mini network disruption probability and MMSE are shown in the Figure 4. In AD group and MCI group, the mini network disruption probability increases rapidly between 12 and 24 months and there is a platform period from 24 to 36 months, then the disease progression turn into a rapid deterioration period until 48 months. In the normal control group, the mini network disruption probability keeps fluctuating during this study.\n\nSignificance of mini network disruption parameters\nThe mini network disruption parameters U, K, and φ can be used to evaluate mini network imbalance integrally. According to Equations (1–3), with the mini network variation gets smaller, the K-value gets closer to 1 whereas the values of U and φ get closer to 0.\nThe simulation experiment result is presented in the Table 2. The results of single marker changing simulation indicate that the parameters U and φ are related to the variation of single marker. The results of multi-marker changing simulation 1 suggest that parameter K is related to the consistency multi-marker changing and U is sensitive to the great consistency variation of multi-marker. The results of multi-marker changing simulation 2 indicate that parameters U and φ are related to the multi-marker inconsistency variation. We summarize physiological significance of U, K, and φ with the simulation experiment evidence. U is responses to both consistency variation and inconsistency variation comprehensively. K responds to multi-marker consistency variation. φ is response to the multi-marker inconsistency variation.\nTable 2 The mini network integral disruption parameters changes in simulation experiment.\nGradient (%) K (%) φ (%) U (%)\nSituation: single marker simulation 10 3.78 12.88 11.09\n20 7.77 25.07 23.45\n50 20.77 57.21 65.17\nSituation: multi-markers simulation 1 10 10.00 0.00 0.27\n20 20.00 0.00 6.82\n50 50.00 0.00 57.85\nSituation: multi-markers simulation 2 10 2.19 27.68 25.30\n20 3.38 57.21 51.38\n50 0.82 147.97 131.69 The boxplot of mini network disruption parameters (Figure 7A) shows that these three parameters in both AD and MCI groups are significantly greater than those in normal group (P \u003c 0.01, based on One-way ANOVA, Table 3) which suggests that if mini network disruption parameters U, K, and φ are higher than the upper whisker of normal group, the patient may have high disease risk. Moreover, the trajectory figure (Figure 7B) shows that the variation of parameter U is similar to the disease progression.\nFigure 7 (A) Box plot of mini network integral disruption parameters. “+” represents data points beyond the whiskers. (B) The trajectory figure of the mini network integral disruption parameter U. The different colors of the area under the curve indicate different time period. With the curves of U farther to the center, mini network imbalance gets worse. **P \u003c 0.01 vs. normal.\nTable 3 Estimation of disruption parameters U, K, and φ.\nU K φ\nAD 118.84 ± 87.12** 0.9684 ± 87 0.4484 ± 87**\nMCI 103.80 ± 72.64** 0.9480 ± 72 0.3980 ± 72**\nNormal 72.43 ± 30.35 0.923 ± 30 0.263 ± 30\nThe data are presented as mean ± SD.\n** P \u003c 0.01 vs. Normal. The contribution of the mini network integral disruption parameters are shown in the Figure 8. The SVM based on all three parameters has the best classification performance compared with the other SVMs. The SVM without parameter U has the poorest performance which is same as the SVM based on CSF markers.\nFigure 8 Mini network integral disruption parameters' contribution to the performance in classification.\n\nContribution of biomarkers to mini network disruption\nThe biomarker contribution to the mini network disruption is given in the Figure 9. For the single marker, P-tau is the major contributor to the mini network in the disease progression in both AD and MCI. However, effects of other two markers Aβ and tau on aggravating mini network disruption cannot be neglected at the end stage (at 48 month). The joint contribution of P-tau and Aβ may play a more important role in the deterioration of the disease.\nFigure 9 The percentage contribution to mini network disruption of the markers. Color-coded scale is used to present the percentage contribution to mini network disruption of the markers in this plot. The joint contribution of tau and P-tau as well as P-tau and Aβ both are potential vital factors of disease.","divisions":[{"label":"title","span":{"begin":0,"end":6}},{"label":"sec","span":{"begin":8,"end":827}},{"label":"title","span":{"begin":8,"end":25}},{"label":"p","span":{"begin":26,"end":400}},{"label":"figure","span":{"begin":401,"end":744}},{"label":"label","span":{"begin":401,"end":409}},{"label":"caption","span":{"begin":411,"end":744}},{"label":"p","span":{"begin":411,"end":744}},{"label":"figure","span":{"begin":745,"end":827}},{"label":"label","span":{"begin":745,"end":753}},{"label":"caption","span":{"begin":755,"end":827}},{"label":"p","span":{"begin":755,"end":827}},{"label":"sec","span":{"begin":829,"end":2091}},{"label":"title","span":{"begin":829,"end":863}},{"label":"p","span":{"begin":864,"end":1287}},{"label":"figure","span":{"begin":1288,"end":1650}},{"label":"label","span":{"begin":1288,"end":1296}},{"label":"caption","span":{"begin":1298,"end":1650}},{"label":"p","span":{"begin":1298,"end":1650}},{"label":"p","span":{"begin":1651,"end":2091}},{"label":"sec","span":{"begin":2093,"end":5255}},{"label":"title","span":{"begin":2093,"end":2143}},{"label":"p","span":{"begin":2144,"end":2405}},{"label":"p","span":{"begin":2406,"end":3233}},{"label":"table-wrap","span":{"begin":3234,"end":3684}},{"label":"label","span":{"begin":3234,"end":3241}},{"label":"caption","span":{"begin":3243,"end":3324}},{"label":"p","span":{"begin":3243,"end":3324}},{"label":"table","span":{"begin":3325,"end":3684}},{"label":"tr","span":{"begin":3325,"end":3361}},{"label":"th","span":{"begin":3325,"end":3338}},{"label":"th","span":{"begin":3339,"end":3345}},{"label":"th","span":{"begin":3347,"end":3353}},{"label":"th","span":{"begin":3355,"end":3361}},{"label":"tr","span":{"begin":3362,"end":3421}},{"label":"td","span":{"begin":3362,"end":3397}},{"label":"td","span":{"begin":3399,"end":3401}},{"label":"td","span":{"begin":3403,"end":3407}},{"label":"td","span":{"begin":3409,"end":3414}},{"label":"td","span":{"begin":3416,"end":3421}},{"label":"tr","span":{"begin":3422,"end":3444}},{"label":"td","span":{"begin":3422,"end":3424}},{"label":"td","span":{"begin":3426,"end":3430}},{"label":"td","span":{"begin":3432,"end":3437}},{"label":"td","span":{"begin":3439,"end":3444}},{"label":"tr","span":{"begin":3445,"end":3468}},{"label":"td","span":{"begin":3445,"end":3447}},{"label":"td","span":{"begin":3449,"end":3454}},{"label":"td","span":{"begin":3456,"end":3461}},{"label":"td","span":{"begin":3463,"end":3468}},{"label":"tr","span":{"begin":3469,"end":3529}},{"label":"td","span":{"begin":3469,"end":3506}},{"label":"td","span":{"begin":3508,"end":3510}},{"label":"td","span":{"begin":3512,"end":3517}},{"label":"td","span":{"begin":3519,"end":3523}},{"label":"td","span":{"begin":3525,"end":3529}},{"label":"tr","span":{"begin":3530,"end":3551}},{"label":"td","span":{"begin":3530,"end":3532}},{"label":"td","span":{"begin":3534,"end":3539}},{"label":"td","span":{"begin":3541,"end":3545}},{"label":"td","span":{"begin":3547,"end":3551}},{"label":"tr","span":{"begin":3552,"end":3574}},{"label":"td","span":{"begin":3552,"end":3554}},{"label":"td","span":{"begin":3556,"end":3561}},{"label":"td","span":{"begin":3563,"end":3567}},{"label":"td","span":{"begin":3569,"end":3574}},{"label":"tr","span":{"begin":3575,"end":3636}},{"label":"td","span":{"begin":3575,"end":3612}},{"label":"td","span":{"begin":3614,"end":3616}},{"label":"td","span":{"begin":3618,"end":3622}},{"label":"td","span":{"begin":3624,"end":3629}},{"label":"td","span":{"begin":3631,"end":3636}},{"label":"tr","span":{"begin":3637,"end":3659}},{"label":"td","span":{"begin":3637,"end":3639}},{"label":"td","span":{"begin":3641,"end":3645}},{"label":"td","span":{"begin":3647,"end":3652}},{"label":"td","span":{"begin":3654,"end":3659}},{"label":"tr","span":{"begin":3660,"end":3684}},{"label":"td","span":{"begin":3660,"end":3662}},{"label":"td","span":{"begin":3664,"end":3668}},{"label":"td","span":{"begin":3670,"end":3676}},{"label":"td","span":{"begin":3678,"end":3684}},{"label":"p","span":{"begin":3685,"end":4187}},{"label":"figure","span":{"begin":4188,"end":4568}},{"label":"label","span":{"begin":4188,"end":4196}},{"label":"caption","span":{"begin":4198,"end":4568}},{"label":"p","span":{"begin":4198,"end":4568}},{"label":"table-wrap","span":{"begin":4569,"end":4843}},{"label":"label","span":{"begin":4569,"end":4576}},{"label":"caption","span":{"begin":4578,"end":4626}},{"label":"p","span":{"begin":4578,"end":4626}},{"label":"table","span":{"begin":4627,"end":4781}},{"label":"tr","span":{"begin":4627,"end":4636}},{"label":"th","span":{"begin":4627,"end":4629}},{"label":"th","span":{"begin":4630,"end":4632}},{"label":"th","span":{"begin":4634,"end":4636}},{"label":"tr","span":{"begin":4637,"end":4685}},{"label":"td","span":{"begin":4637,"end":4639}},{"label":"td","span":{"begin":4641,"end":4657}},{"label":"td","span":{"begin":4659,"end":4670}},{"label":"td","span":{"begin":4672,"end":4685}},{"label":"tr","span":{"begin":4686,"end":4735}},{"label":"td","span":{"begin":4686,"end":4689}},{"label":"td","span":{"begin":4691,"end":4707}},{"label":"td","span":{"begin":4709,"end":4720}},{"label":"td","span":{"begin":4722,"end":4735}},{"label":"tr","span":{"begin":4736,"end":4781}},{"label":"td","span":{"begin":4736,"end":4742}},{"label":"td","span":{"begin":4744,"end":4757}},{"label":"td","span":{"begin":4759,"end":4769}},{"label":"td","span":{"begin":4771,"end":4781}},{"label":"table-wrap-foot","span":{"begin":4782,"end":4843}},{"label":"p","span":{"begin":4782,"end":4818}},{"label":"footnote","span":{"begin":4819,"end":4843}},{"label":"label","span":{"begin":4819,"end":4821}},{"label":"p","span":{"begin":4823,"end":4843}},{"label":"p","span":{"begin":4844,"end":5149}},{"label":"figure","span":{"begin":5150,"end":5255}},{"label":"label","span":{"begin":5150,"end":5158}},{"label":"caption","span":{"begin":5160,"end":5255}},{"label":"p","span":{"begin":5160,"end":5255}},{"label":"title","span":{"begin":5257,"end":5310}},{"label":"p","span":{"begin":5311,"end":5762}},{"label":"label","span":{"begin":5763,"end":5771}}],"tracks":[]}