Background: Dysphagia is a common functional impairment in elderly populations, often leading to severe complications such as malnutrition and aspiration pneumonia, significantly increasing healthcare burdens. Currently, effective prognostic assessment tools are lacking. The absolute lymphocyte count (ALC), a biomarker reflecting immune-nutritional status, has potential predictive value in this context, though its role in dysphagia prognosis remains unclear. Methods: This retrospective cohort study included 253 dysphagic patients who received percutaneous endoscopic gastrostomy (PEG) or total parenteral nutrition (TPN) between 2014 and 2017. Five patients with missing ALC were excluded. Cox regression models assessed the association between ALC and mortality. ALC was analyzed as both continuous variable (using restriocted cubic splines) and categorical tertiles, with additional threshold analyses to assess non-linearity. Kaplan–Meier survival curves and subgroup analyses were also performed. Results: Lower ALC was associated with poorer nutritional status, higher inflammatory markers, and greater comorbidity burden. Higher ALC was independently associated with reduced mortality (adjusted HR: 0.60; 95% CI: 0.44–0.83; p = 0.002). Patients in the highest tertile had significantly better survival than those in the lowest (HR: 0.37; 95% CI: 0.23–0.59; P < 0.001). A non-linear threshold effect was identified at ALC = 1.899×10⁹/L (p for non-linearity = 0.009). Kaplan–Meier analysis confirmed improved survival with higher ALC (p < 0.0001). Subgroup analyses showed the protective effect of higher ALC was consistent across age, sex, BMI, PEG use, and comorbidity strata, with no significant interactions. Conclusions: ALC is an independent, non-linear predictor of mortality in older dysphagic patients and may aid clinical risk stratification across diverse patient subgroups.

Spline smoothing is a technique used to filter out noise in time series observations when predicting nonparametric regression models. Its performance depends on the choice of the smoothing parameter. Most of the existing smoothing methods applied to time series data tend to over fit in the presence of autocorrelated errors. This study aims to determine the optimum performance value, goodness of fit and model overfitting properties of the proposed Smoothing Method (PSM), Generalized Maximum Likelihood (GML), Generalized Cross-Validation (GCV), and Unbiased Risk (UBR) smoothing parameter selection methods. A Monte Carlo experiment of 1,000 trials was carried out at three different sample sizes (20, 60, and 100) and three levels of autocorrelation (0.2, 05, and 0.8). The four smoothing methods' performances were estimated and compared using the Predictive Mean Squared Error (PMSE) criterion. The findings of the study revealed that: for a time series observation with autocorrelated errors, provides the best-fit smoothing method for the model, the PSM does not over-fit data at all the autocorrelation levels considered ( the optimum value of the PSM was at the weighted value of 0.04 when there is autocorrelation in the error term, PSM performed better than the GCV, GML, and UBR smoothing methods were considered at all-time series sizes (T = 20, 60 and 100). For the real-life data employed in the study, PSM proved to be the most efficient among the GCV, GML, PSM, and UBR smoothing methods compared. The study concluded that the PSM method provides the best fit as a smoothing method, works well at autocorrelation levels (ρ=0.2, 0.5, and 0.8), and does not over fit time-series observations. The study recommended that the proposed smoothing is appropriate for time series observations with autocorrelation in the error term and econometrics real-life data. This study can be applied to; non – parametric regression, non – parametric forecasting, spatial, survival, and econometrics observations.