Is use of a long-term proton pump inhibitor or histamine-2 receptor antagonist a risk factor for iron-deficiency anaemia in Taiwan? A neglected clinical drug-drug interaction.

BACKGROUND: Proton pump inhibitors (PPIs) and histamine-2 receptor (H2) antagonists change the gastric pH and reduce the intestinal absorption of nonheme iron. Case reports and case-control studies have demonstrated that absorption of iron is affected by gastric acidity, but the clinical importance of these drug-drug interactions has remained uncertain. OBJECTIVES: The present case-control study employed 2 million longitudinal claims in 2011-2018 in the Taiwan National Health Insurance Research Database to investigate the impact of PPIs/H2 antagonists on the occurrence of iron-deficiency anaemia (IDA). METHODS: The present study retrospectively compared exposure to PPIs/H2 antagonists for 1 year among 5,326 cases with IDA and 21,304 matched controls. The postdiagnosis prescribing pattern was also calculated to understand current practice. RESULTS: Long-term (≥2 month) use of PPIs/H2 antagonists resulted in a higher risk of developing IDA than noncontinuous use/nonuse of those drugs (adjusted odds ratio [aOR] = 2.36, 95% confidence interval [CI] = 1.94-2.86, P < 0.001). There were significant changes in the postdiagnosis prescribing patterns of PPIs/H2 antagonists. The risk of developing IDA remained significant in the female subgroup (aOR = 2.16, 95% CI = 1.73-2.70, P < 0.001) and was even more prominent in those aged ≥ 50 years (aOR = 2.68, 95% CI = 1.94-3.70, P < 0.05). CONCLUSIONS: This study found that long-term use of PPIs/H2 antagonists increased the risk of developing IDA, and there was strong evidence of prescription pattern adjustments postdiagnosis. Physicians and pharmacists should be aware of this risk when patients are expected to take or have been taking PPIs/H2 antagonists for the long term.

Proton pump inhibitors (PPIs) and histamine-2 receptor (H2) antagonists, 2 kinds of gastric suppressants commonly used for gastroesophageal reflux disease, decrease iron absorption in the gut and thus increase the risk of developing iron-deficiency anaemia (IDA). We constructed a retrospective matched case-control study within the Taiwan National Health Insurance Research Database. The longer period of PPIs/H2 antagonists used, the higher risk of IDA was, with the highest risk in female elderly groups (adjusted odds ratio = 2.68 in females aged ≥ 50). PPI users had a higher risk than H2 antagonist users during the 1-year follow-up. The prescription patterns postdiagnosis of IDA witnessed considerable drops for both groups, with less than a 10th of original users remaining the usages (1.72% and 9.85% taking PPIs and H2 antagonists within 90 days after receiving a diagnosis, respectively). Physicians and pharmacists should be aware of the risk of developing IDA in patients currently undergoing or expected to take long-term gastric acid suppressants.

Can machine learning predict pharmacotherapy outcomes? An application study in osteoporosis.

BACKGROUND AND OBJECTIVE: The specific aim of this study is to develop machine learning models as a clinical approach for personalized treatment of osteoporosis. The model performance on outcome prediction was compared between four machine learning algorithms. METHODS: Retrospective, electronic clinical data for patients with suspected or confirmed osteoporosis treated at Wan Fang Hospital between 2011 to 2018 were used as inputs for building the following predictive machine learning models,i.e., artificial neural network (ANN), random forest (RF), support vector machine (SVM) and logistic regression (LR) models. The predicted outcome was defined as an increase/decrease in T-score after treatment. A genetic algorithm was employed to select relevant variables as input features for each model; the leave-one-out method was applied for model building and internal validation. The model with best performance was selected by a separate set of testing. Area under the receiver operating characteristic curve, accuracy, precision, sensitivity and F1 score were calculated to evaluate model performance. Main analysis for all the patients with subclinical or confirmed osteoporosis and subgroup analysis for the patients with confirmed osteoporosis (T score < -2.5) were carried out in this study. RESULTS: A genetic algorithm was employed to select 12 to 18 features from all 33 variables for the four models. No difference was found in accuracy (ANN, 71.7%; LR, 70.0%; RF, 75.0%; SVM, 66.7%), precision (ANN, 80.0%; LR, 59.3%; RF, 70.0%; SVM, 63.6%), and AUC (ANN, 0.709; LR, 0.731; RF, 0.719; SVM, 0.702) among the ANN, LR, RF and SVM models. Main analysis in performance revealed significant recall in the LR model, as compared to ANN and SVM model; while subgroup revealed significant recall in ANN model, compared to LR and SVM model. CONCLUSIONS: Machine learning-based models hold potential in forecasting the outcomes of treatment for osteoporosis via early initiation of first-line therapy for patients with subclinical disease; or a switch to second-line treatment for patients with a high risk of impending treatment failure. This convenient approach can assist clinicians in adjusting treatment tailored to individual patient for prevention of disease progression or ineffective therapy.

How platinum-induced nephrotoxicity occurs? Machine learning prediction in non-small cell lung cancer patients.

BACKGROUND AND OBJECTIVE: Platinum-induced nephrotoxicity is a severe and unexpected adverse drug reaction that could lead to treatment failure in non-small cell lung cancer patients. Better prediction and management of this nephrotoxicity can increase patient survival. Our study aimed to build up and compare the best machine learning models with clinical and genomic features to predict platinum-induced nephrotoxicity in non-small cell lung cancer patients. METHODS: Clinical and genomic data of patients undergoing platinum chemotherapy at Wan Fang Hospital were collected after they were recruited. Twelve models were established by artificial neural network, logistic regression, random forest, and support vector machine with integrated, clinical, and genomic modes. Grid search and genetic algorithm were applied to construct the fine-tuned model with the best combination of predictive hyperparameters and features. Accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve were calculated to compare the performance of the 12 models. RESULTS: In total, 118 patients were recruited for this study, among which 28 (23.73%) were experiencing nephrotoxicity. Machine learning models with clinical and genomic features achieved better prediction performances than clinical or genomic features alone. Artificial neural network with clinical and genomic features demonstrated the best predictive outcomes among all 12 models. The average accuracy, precision, recall, F1 score and area under the receiver operating characteristic curve of the artificial neural network with integrated mode were 0.923, 0.950, 0.713, 0.808 and 0.900, respectively. CONCLUSIONS: Machine learning models with clinical and genomic features can be a preliminary tool for oncologists to predict platinum-induced nephrotoxicity and provide preventive strategies in advance.

Long working range light field microscope with fast scanning multifocal liquid crystal microlens array.

The light field microscope has the potential of recording the 3D information of biological specimens in real time with a conventional light source. To further extend the depth of field to broaden its applications, in this paper, we proposed a multifocal high-resistance liquid crystal microlens array instead of the fixed microlens array. The developed multifocal liquid crystal microlens array can provide high quality point spread function in multiple focal lengths. By adjusting the focal length of the liquid crystal microlens array sequentially, the total working range of the light field microscope can be much extended. Furthermore, in our proposed system, the intermediate image was placed in the virtual image space of the microlens array, where the condition of the lenslets numerical aperture was considerably smaller. Consequently, a thin-cell-gap liquid crystal microlens array with fast response time can be implemented for time-multiplexed scanning.