0000000000214723
AUTHOR
N. Víctor Jiménez-torres
Validation of a Reinforcement Learning Policy for Dosage Optimization of Erythropoietin
This paper deals with the validation of a Reinforcement Learning (RL) policy for dosage optimization of Erythropoietin (EPO). This policy was obtained using data from patients in a haemodialysis program during the year 2005. The goal of this policy was to maintain patients' Haemoglobin (Hb) level between 11.5 g/dl and 12.5 g/dl. An individual management was needed, as each patient usually presents a different response to the treatment. RL provides an attractive and satisfactory solution, showing that a policy based on RL would be much more successful in achieving the goal of maintaining patients within the desired target of Hb than the policy followed by the hospital so far. In this work, t…
Impact of nutritional status on the oral bioavailability of leucine administered to rats as part of a standard enteral diet.
Summary Background To investigate the absorption and relative bioavailability of leucine administered orally as part of an enteral diet in well and malnourished animals. Methods Two groups – RN (regular nutrition) and PCR (protein-calorie restricted) – were fed with different diets for 23–25 days. Rats from each group were assigned randomly to one of three treatments (water, T-Diet Plus Standard ® (problem) or Isosource ST ® (reference)) administered in single ( N = 76) or multiple ( N = 39) doses. Blood samples were assayed for leucine content. Area under the curve (AUC) was calculated by non-compartmental analysis. Log-transformed AUC(s) were statistically compared by analysis of varian…
Quantitative and qualitative control of antineoplastic preparations: Gravimetry versus HPLC.
This article compares gravimetry vs. high-performance liquid chromatography (HPLC) as quality control (QC) methods for paclitaxel, docetaxel and oxaliplatin preparations. We aimed at assessing the preparation method reliability in our hospital, evaluating compounding accuracy and estimating the influence of personnel training and standardized homogenization on compounding accuracy. Agreement, correlation, concordance, accuracy and precision between methods were evaluated for each drug. Conforming preparation percentages (CPs) at different tolerance limits (TLs) and compounding accuracy were calculated for each method and drug. Compounding accuracy was compared before and after personnel tra…
Effect of Age on Systemic Exposure and Haematological Toxicity of Carboplatin in Advanced Non-Small Cell Lung Cancer Patients
The aim of this study was to evaluate systemic exposure to carboplatin and its haematological toxicity in patients with advanced non-small cell lung cancer both older and younger than 70 years when the target area under the curve (AUC) in elderly patients was reduced by 20%. For this purpose, a population pharmacokinetic model was developed and the haema- tological toxicity of the drug was assessed. A total of 33 patients received carboplatin on day 1 and gemcitabine (1250 mg ⁄ m 2 ) on days 1 and 8. This schedule was repeated every 21 days. The Calvert-Crokcoft-Gault formula was employed to calculate a dose of carboplatin with a target AUC of 5 mg ⁄ min. ⁄ mL in patients under 70 years and…
A reinforcement learning approach for individualizing erythropoietin dosages in hemodialysis patients
This paper presents a reinforcement learning (RL) approach for anemia management in patients undergoing chronic renal failure. Erythropoietin (EPO) is the treatment of choice for this kind of anemia but it is an expensive drug and with some dangerous side-effects that should be considered especially for patients who do not respond to the treatment. Therefore, an individualized treatment appears to be necessary. RL is a suitable approach to tackle this problem. Moreover, resulting policies are similar to medical protocols, and hence, they can easily be transferred to daily practice. A cohort of 64 patients are included in the study. An implementation of the Q-learning algorithm based on a st…
Multidisciplinary system for detecting medication errors in antineoplastic chemotherapy.
Objective. To analyze medication errors (MEs) in a multidisciplinary system with a Computerized Pharmacotherapy Process (CPP) in cancer patients. Design. A longitudinal, prospective 2-year (January 2003 —to December 2004) cohort study was made in adult patients administered antineoplastic treatment in Services of Oncology and Haematology. MEs were identified by double cross-validation of each stage of the pharmacotherapeutic process (prescription, preparation, dispensing, administration, and follow-up) carried out by the multidisciplinary team (physician, pharmacist, nurse) with CPP assistance. Variables. Number of MEs per 1000 patient-days, percentage according to the stage of the pharmac…