Machine Learning-Enabled NIR Spectroscopy in Assessing Powder Blend Uniformity: Clear-Up Disparities and Biases Induced by Physical Artefacts.

NIR spectroscopy is a non-destructive characterization tool for the blend uniformity (BU) assessment. However, NIR spectra of powder blends often contain overlapping physical and chemical information of the samples. Deconvoluting the information related to chemical properties from that associated with the physical effects is one of the major objectives of this work. We achieve this aim in two ways. Firstly, we identified various sources of variability that might affect the BU results. Secondly, we leverage the machine learning-based sophisticated data analytics processes. To accomplish the aforementioned objectives, calibration samples of amlodipine as an active pharmaceutical ingredient (API) with the concentrations ranging between 67 and 133% w/w (dose ~ 3.6% w/w), in powder blends containing excipients, were prepared using a gravimetric approach and assessed using NIR spectroscopic analysis, followed by HPLC measurements. The bias in NIR results was investigated by employing data quality metrics (DQM) and bias-variance decomposition (BVD). To overcome the bias, the clustered regression (non-parametric and linear) was applied. We assessed the model's performance by employing the hold-out and k-fold internal cross-validation (CV). NIR-based blend homogeneity with low mean absolute error and an interval estimates of 0.674 (mean) ± 0.218 (standard deviation) w/w was established. Additionally, bootstrapping-based CV was leveraged as part of the NIR method lifecycle management that demonstrated the mean absolute error (MAE) of BU ± 3.5% w/w and BU ± 1.5% w/w for model generalizability and model transferability, respectively. A workflow integrating machine learning to NIR spectral analysis was established and implemented. Impact of various data learning approaches on NIR spectral data.

Blockade of glial-derived neurotrophic factor in laryngeal muscles promotes appropriate reinnervation.

OBJECTIVES/HYPOTHESIS: Synkinetic reinnervation of the laryngeal muscles is one of the causes of the poor functional recovery after a recurrent laryngeal nerve (RLN) injury. Glial-derived neurotrophic factor (GDNF) is elevated in rat laryngeal muscles during RLN reinnervation. The specific aim of this investigation was to evaluate the effect of anti-GDNF on RLN reinnervation. METHODS: Anti-GDNF antibody was injected into the posterior cricoarytenoid (PCA) 3 days following RLN transection and anastomosis. Larynges were harvested at 7, 14, 28, 56, and 112 days post injury (DPI). Prior to sacrifice, the vocal fold mobility was assessed. Immunostaining to identify neuromuscular junctions was used to evaluate the extent of axonal reinnervation of the PCA, lateral thyroarytenoid (LTA), and medial thyroarytenoid (MTA). RESULTS: After anti-GDNF injection into PCA, RLN reinnervation in all muscles was altered when compared to the controls. PCA innervation was delayed. At 7 DPI, only a few axons made synapses in the PCA. In contrast, axons prematurely innervated the LTA and MTA when compared to controls. Innervation was similar to controls at 56 and 112 DPI. Vocal fold motion was enhanced in 10 of 24 animals studied. CONCLUSIONS: After injection of anti-GDNF into the PCA, early arriving axons bypass the PCA and enter the LTA. Later arriving axons innervate the PCA and MTA. Vocal fold function is improved as compared to controls. Anti-GDNF injection into the PCA influences the pattern of reinnervation and may result in less synkinetic, more functional innervation. LEVEL OF EVIDENCE: NA Laryngoscope, 126:E337-E342, 2016.