Predictors of Stroke Outcome Extracted from Multivariate Linear Discriminant Analysis or Neural Network Analysis

Abstract

Aim: The prediction of functional outcome is essential in the management of acute ischemic stroke patients. We aimed to explore the various prognostic factors with multivariate linear discriminant analysis or neural network analysis and evaluate the associations between candidate factors, baseline characteristics, and outcome. Methods: Acute ischemic stroke patients ( n =1,916) with premorbid modified Rankin Scale (mRS) scores of 0–2 were analyzed. The prediction models with multivariate linear discriminant analysis (quantification theory type II) and neural network analysis (log-linearized Gaussian mixture network) were used to predict poor functional outcome (mRS 3–6 at 3 months) with various prognostic factors added to age, sex, and initial neurological severity at admission. Results: Both models revealed that several nutritional statuses and serum alkaline phosphatase (ALP) levels at admission improved the predictive ability. Of the 1,484 patients without missing data, 560 patients (37.7%) had poor outcomes. The patients with poor outcomes had higher ALP levels than those without (294.3±259.5 vs. 246.3±92.5 U/l, P ＜0.001). Multivariable logistic analyses revealed that higher ALP levels (1-SD increase) were independently associated with poor stroke outcomes after adjusting for several confounding factors, including the neurological severity, malnutrition status, and inflammation (odds ratio 1.21, 95% confidence interval 1.02–1.49). Several nutritional indicators extracted from prediction models were also associated with poor outcome. Conclusion: Both the multivariate linear discriminant and neural network analyses identified the same indicators, such as nutritional status and serum ALP levels. These indicators were independently associated with functional stroke outcome.

The Assessment of the Risk of Malnutrition (Undernutrition) in Stroke Patients

“…The studies that applied GNRI to stroke patients have been carried out (since 2016) in Far Eastern Asian countries [ 7 , 14 , 15 , 16 , 27 , 29 , 30 , 31 , 32 , 34 , 37 , 42 , 43 , 45 , 46 , 47 , 48 , 50 , 53 , 54 , 55 , 57 , 58 , 63 , 64 , 66 , 68 , 70 , 71 ], as shown in Table 1 . A significant risk of malnutrition has usually been defined by a GNRI score <92, with some exceptions (for example, a score <98 [ 7 ] or <100 [ 27 ]).…”

“…All the studies applying the CONUT tool to stroke patients were carried out (since 2018) in Far Eastern Countries, with the exception of one from Spain [ 14 , 15 , 17 , 20 , 22 , 23 , 25 , 26 , 30 , 33 , 34 , 36 , 40 , 41 , 44 , 45 , 46 , 56 , 60 , 61 , 66 , 67 , 68 , 69 , 70 , 71 , 72 ], as reported in Table 1 . Stroke patients were classified according to the original four, but also in three (normal, light, and moderate/severe risk) or in two (absence or presence of risk) categories; a CONUT score ≥5 was commonly defined as the cut-off for a significant risk of malnutrition, but in two papers the cut-off was ≥2 [ 72 ] or ≥4 [ 23 ], respectively.…”

Increased Serum Alkaline Phosphatase and Functional Outcome in Patients with Acute Ischemic Stroke Presenting a Low Ankle–Brachial Index

“…In addition, serum ALP levels are a good predictor of all-cause mortality and functional outcomes of acute stroke 10,11) . We previously reported that serum ALP levels extracted using a neural network analysis were independently associated with poor stroke outcomes at 3 months 12) . Although the association between increased ALP levels and stroke outcomes is not completely clear, we speculated that the effect of PAD is mediated by vascular calcification.…”

Baseline Objective Malnutritional Indices as Immune-Nutritional Predictors of Long-Term Recurrence in Patients with Acute Ischemic Stroke

“…The prevalence of premorbid malnutrition was around 33% to 34.3% for acute ischemic stroke (AIS) patients at admission [ 3 , 4 ]. Recent evidence demonstrated that malnutrition at admission was related to unfavorable stroke outcomes in AIS patients, such as increased mortality and poor neurological function at 90 days of onset [ 5 , 6 , 7 ]. The impact of malnutrition on prognosis after AIS exists not only in the acute stage but also in the chronic phase [ 7 ].…”