Functional link hybrid artificial neural network for predicting continuous biohydrogen production in dynamic membrane bioreactor.

Conventional machine learning approaches have shown limited predictive power when applied to continuous biohydrogen production due to nonlinearity and instability. This study was aimed at forecasting the dynamic membrane reactor performance in terms of the hydrogen production rate (HPR) and hydrogen yield (HY) using laboratory-based daily operation datapoints for twelve input variables. Hybrid algorithms were developed by integrating particle swarm optimized with functional link artificial neural network (PSO-FLN) which outperformed other hybrid algorithms for both HPR and HY, with determination coefficients (R2) of 0.97 and 0.80 and mean absolute percentage errors of 0.014 % and 0.023 %, respectively. Shapley additive explanations (SHAP) explained the two positive-influencing parameters, OLR_added (1.1-1.3 mol/L/d) and butyric acid (7.5-16.5 g COD/L) supports the highest HPR (40-60 L/L/d). This research indicates that PSO-FLN model are capable of handling complicated datasets with high precision in less computational timeat 9.8 sec for HPR and 10.0 sec for HY prediction.

Proliferative Index in Invasive Tumor Front of Oral Squamous Cell Carcinoma: A Potential Prognostic Indicator.

AIM: The aim of the study was to evaluate the proliferative index (PI) at their invasive front of oral cancer and their association with Bryne's grades of oral squamous cell carcinoma (OSCC) and compare the PI with lymph node metastasis, site of involvement, and habits. MATERIALS AND METHODS: The Ki-67 antigen expression was immunohistochemically evaluated in a total of 102 cases that included the histopathologically diagnosed archival specimens of OSCCs. They were subdivided by Bryne's histopathological grading into grade I (40 cases), grade II (32 cases), and grade III (30 cases). The nucleus with brown stain was considered positive. Cells were counted under 400× magnification. The proliferative activity thus determined was then expressed as a percentage of Ki-67 labeling index (Ki-67 LI) positive cells. RESULTS: A stepwise increase in the mean Ki-67 LI was found from grade I to III squamous cell carcinoma, thus correlating with the histological grading. In addition, there was a higher PI seen in cases associated with metastatic lymph node, which concords with the higher biologic aggressiveness and poor prognosis of the lesion. CONCLUSION: The present study shows a definitive correlation of Ki-67 antigen with the Bryne's histological grading, all the parameters of Bryne's grading for OSCC and lymph node status of the patient proving its association as an effective tool to grade the tumors and finally read the prognosis of the tumor. CLINICAL SIGNIFICANCE: Cell proliferation is regarded as one of the most important biologic mechanisms in oncogenesis. The role of cell proliferation in tumor progression has been inferred in studies concerned with human cancer by comparing the PI of normal tissue, preneoplastic and neoplastic lesions. The Ki-67 antigen-labeled cells can prove to be an effective aid to grade the tumors. It might be possible to standardize and objectify tumor grading among pathology laboratories.

Oral manifestations of human immunodeficiency virus/acquired immunodeficiency syndrome and their correlation to cluster of differentiation lymphocyte count in population of North-East India in highly active antiretroviral therapy era.

BACKGROUND: The human immunodeficiency virus (HIV) infection which manifests as acquired immunodeficiency syndrome (AIDS) is a disease involving the defects of the T-lymphocyte arm of the immune system. Certain laboratory parameters such as the cluster of differentiation (CD4) count and clinical parameters have long been used as markers of disease progression. In industrialized countries, many studies show a highly correlation between the incidence of oral lesions and immunosuppression and hence, can be used as a marker of immunosuppression. This might not be applicable to a developing country like India. In this study, efforts have been made to supplement the present knowledge on various aspects of oral manifestations in HIV patients in the Indian subcontinent. AIMS: To correlate the oral manifestations in HIV/AIDS patients to the level of circulating CD4+ T-lymphocyte count and their effect in anti-retroviral therapy (ART). SUBJECTS AND METHODS: A total of 104 HIV positive patients were examined for oral lesions. The CD4 count estimated on the same day by fluorescent activated cell sort count machine was then correlated with various oral lesions. RESULTS: Oral manifestations appeared when CD4 count decreased below 500 cells/mm3. Moreover, oral lesions found at different stages showed very strong correlation to their respective CD4 count. Furthermore, there was considerable decline in the incidence of oral manifestations in patients undergoing highly active ART. CONCLUSIONS: Oral manifestations are highly predictive markers of severe immune deterioration and disease progression in HIV patients.