Non-Invasive Estimation of Hemoglobin Using a Multi-Model Stacking Regressor.

OBJECTIVE: We describe a novel machine-learning based method to estimate total Hemoglobin (Hb) using photoplethysmograms (PPGs) acquired non-invasively. METHODS: In a study conducted in Karnataka, India, 1583 women (pregnant and non-pregnant) of childbearing age, with Hb values ranging between 1.6 to 14.8 g/dL, had their Hb values estimated using intravenous blood samples and concurrently by a finger sensor custom designed and prototyped for this study. The finger sensor collected PPG signals at four wavelengths: 590 nm, 660 nm, 810 nm, and 940 nm. A novel feature vector was derived from these PPGs. A machine learning model comprising of a two-layer stack of regressors including Least Absolute Shrinkage and Selection Operator (LASSO), Ridge, Elastic Net, Adaptive (Ada) Boost and Support Vector Regressors (SVR) was designed and tested. RESULTS: We report a statistically significant Pearson's correlation coefficient (PCC) of 0.81 (p < 0.01) between the Hb value estimated by the proposed methodology and gold standard values of Hb, with a Root Mean Square Error (RMSE) of 1.353 ± 0.042 g/dL. The performance of the stacked regressor model was significantly better than the performance of individual regressors (low RMSE, and better CC; p < 0.05). Post-hoc analysis showed that including pregnant women in the training data set significantly improved the performance of the algorithm. CONCLUSION: This article demonstrates the feasibility of a machine learning based non-invasive hemoglobin measurement system, especially for maternal anemia detection. SIGNIFICANCE: By developing and demonstrating a machine learning approach on a large data set, we have demonstrated that such an approach could become the basis for a public health screening tool to detect and treat maternal anemia and could supplement global health intervention strategies.

Novel Validated RP-HPLC Method for Bendamustine Hydrochloride Based on Ion-pair Chromatography: Application in Determining Infusion Stability and Pharmacokinetics.

Ion pair chromatography was used for quantifying bendamustine hydrochloride (BH) in its marketed vial. The permissive objective was to investigate time duration for which highly susceptible drug content of the marketed vial remained stable after reconstitution. However, the method could also be used to measure extremely low levels of drug in rat plasma and a pharmacokinetic study was accordingly conducted to further showcase method's applicability. Optimized separation was achieved on C-18 Purospher®STAR (250 mm × 4.6 mm, 5 µm particle size) column. Mobile phase flowing at 1.5 mL/min consisted of 5 mM sodium salt of octane sulfonic acid dissolved in methanol, water and glacial acetic acid (55:45:0.075) maintained at pH 6. Detection was carried out at 233 nm with BH eluting after 7.8 min. Validation parameters were determined as per ICH guidelines. Limit of detection and limit of quantification were found to be 0.1 µg/mL and 0.33 µg/mL, respectively. The recoveries were 98-102% in bulk and 85-91% in plasma. The developed method was specific for BH, and utilized for assessing its short-term stability in physiologic solvents and forced degradation products in acid, base, oxidative, light and temperature induced stress environments.