Application of machine learning to predict reduction in total PANSS score and enrich enrollment in schizophrenia clinical trials.

Clinical trial efficiency, defined as facilitating patient enrollment, and reducing the time to reach safety and efficacy decision points, is a critical driving factor for making improvements in therapeutic development. The present work evaluated a machine learning (ML) approach to improve phase II or proof-of-concept trials designed to address unmet medical needs in treating schizophrenia. Diagnostic data from the Clinical Antipsychotic Trials of Intervention Effectiveness (CATIE) trial were used to develop a binary classification ML model predicting individual patient response as either "improvement," defined as greater than 20% reduction in total Positive and Negative Syndrome Scale (PANSS) score, or "no improvement," defined as an inadequate treatment response (<20% reduction in total PANSS). A random forest algorithm performed best relative to other tree-based approaches in model ability to classify patients after 6 months of treatment. Although model ability to identify true positives, a measure of model sensitivity, was poor (<0.2), its specificity, true negative rate, was high (0.948). A second model, adapted from the first, was subsequently applied as a proof-of-concept for the ML approach to supplement trial enrollment by identifying patients not expected to improve based on their baseline diagnostic scores. In three virtual trials applying this screening approach, the percentage of patients predicted to improve ranged from 46% to 48%, consistently approximately double the CATIE response rate of 22%. These results show the promising application of ML to improve clinical trial efficiency and, as such, ML models merit further consideration and development.

Preoperative anemia and transfusion in cardiac surgery: a single-centre retrospective study.

BACKGROUND: Preoperative anemia and transfusion are associated with worse outcomes. This study aims to identify the prevalence of preoperative anemia, transfusion rates on surgery day, and predictors of transfusion in elective cardiac surgery patients at our centre. We also aim to evaluate our preoperative intervention program, and examine the intervention window for anemia before surgery. METHODS: This study included 797 adult patients who underwent elective cardiac surgery at a tertiary hospital. Multivariable logistic regression analysis was used to identify predictors of transfusion on surgery day. RESULTS: Preoperative anemia was present in 15% of patients. Anemic patients had a significantly higher transfusion rate at 53% compared to 10% in non-anemic patients. Hemoglobin concentration, estimated glomerular filtration rate (eGFR), body surface area (BSA), and total cardiopulmonary bypass time were predictive of transfusion on surgery day. Patients had a median of 7 days between initial visit and surgery day, however, referral to the blood conservation clinic was only done for 8% of anemic patients and treatment was initiated in 3% of anemic patients. Among the 3 anemic patients who received treatment, 2 did not require blood transfusion on surgery day. CONCLUSIONS: Preoperative anemia is present in 15% of patients at our centre and these patients have 53% transfusion rates on surgery day. Hemoglobin concentration, eGFR, BSA, and total cardiopulmonary bypass time were predictors of transfusion on surgery day. Patients had a median of 7 days between initial visit and surgery day. Referral and anemia treatment were infrequently initiated in preoperative anemic patient.

Inhibitory Effects of Probenecid on Pharmacokinetics of Tenofovir Disoproxil Fumarate and Emtricitabine for On-Demand HIV Preexposure Prophylaxis.

In a randomized, crossover pharmacokinetic study in healthy volunteers (N = 14), a single dose of 2 g probenecid (PRO)-boosted 600 mg tenofovir disoproxil fumarate (TDF)/400 mg emtricitabine (FTC) (test (T) +PRO) was compared with the current on-demand HIV preexposure prophylaxis from the IPERGAY study (a 600 mg TDF/400 mg FTC on day 1 and 300 mg TDF/200 mg FTC on days 2 and 3) (control, C IPERGAY). PRO increased mean single-dose area under the plasma concentration-time curve extrapolated to infinity (AUC0-∞,SD ) of tenofovir (TFV) and FTC by 61% and 68%, respectively. The TFV-diphosphate (TFV-DP) concentrations in peripheral blood mononuclear cells were higher (~30%) at 24 hours in T +PRO but then fell significantly lower (~40%) at 72 hours compared with C IPERGAY. The interaction between FTC and PRO was unexpected and novel. Further study is needed to determine if this PRO-boosted TDF/FTC regimen would be clinically effective.

Prediction of Nephropathy in Type 2 Diabetes: An Analysis of the ACCORD Trial Applying Machine Learning Techniques.

Applying data mining and machine learning (ML) techniques to clinical data might identify predictive biomarkers for diabetic nephropathy (DN), a common complication of type 2 diabetes mellitus (T2DM). A retrospective analysis of the Action to Control Cardiovascular Risk in Diabetes (ACCORD) trial was intended to identify such factors using ML. The longitudinal data were stratified by time after patient enrollment to differentiate early and late predictors. Our results showed that Random Forest and Simple Logistic Regression methods exhibited the best performance among the evaluated algorithms. Baseline values for glomerular filtration rate (GFR), urinary creatinine, urinary albumin, potassium, cholesterol, low-density lipoprotein, and urinary albumin to creatinine ratio were identified as DN predictors. Early predictors were the baseline values of GFR, systolic blood pressure, as well as fasting plasma glucose (FPG) and potassium at month 4. Changes per year in GFR, FPG, and triglycerides were recognized as predictors of late development. In conclusion, ML-based methods successfully identified predictive factors for DN among patients with T2DM.

All-Cause Mortality for Life Insurance Applicants with a History of Breast Cancer.

Breast cancer is the most commonly diagnosed cancer worldwide. Breast cancer is also the second leading cause of cancer death among women in the United States after lung cancer with over 40,000 breast cancer deaths occurring each year. The purpose of this research was to determine the all-cause mortality of applicants diagnosed with breast cancer currently or at some time in the past. Life insurance applicants with reported breast cancer were extracted from data covering United States residents between November 2007 and November 2014. Information about these applicants was matched to the Social Security Death Master (SSDMF) file for deaths occurring from 2007 to 2011 and to another commercially available death source file (Other Death Source, ODS) for deaths occurring from 2007 to 2014 to determine vital status. If there was a death from the other death source, then the SSDMF was searched to verify the death. The study had approximately 561,000 person-years of exposure. Actual-to-expected (A/E) mortality ratios were calculated using the Society of Actuaries 2008 Valuation Basic Table (2008VBT), select and ultimate table (age last birthday) and the 2010 US population as expected mortality ratios. Since the A/Es presented in this paper were known to be an underestimate due to the exclusion of the recent SSDMF deaths, comparative analysis of the mortality ratios was done. Since there was no smoking status information in this study, all expected bases were not smoker distinct. Overall, the 35-44 age group had 6.3 times the relative mortality ratio than those in the 65-75 age group. The relative mortality ratio for the 35-44 age group applicants, when cancer severity was accounted for in combination with 3 or more nodes of cancer involvement, was 29.3 times that when compared to those in the 65-75 age group having localized cancer, where no nodes are involved. The 35-44 age group applicants who were diagnosed with cancer within the last year had over 10-fold increase in relative mortality ratios compared to the 65-75 age group, who were over 10 years from diagnosis. Taking the severity of cancer along with time from diagnosis showed over a 12 times relative mortality ratio between the low rate of over 10 years from diagnosis and localized involvement to those diagnosed within the last year having 3 or more nodes with cancer. Applicant age, time since diagnosis and cancer severity were the most significant variables to predict the relative mortality ratios.

All-Cause Mortality for Life Insurance Applicants with a History of Prostate Cancer.

OBJECTIVE: - To determine the all-cause mortality of life insurance applicants diagnosed with prostate cancer currently or at some time in the past. BACKGROUND: - Prostate cancer is common and a frequent cause of cancer death. Both the frequency of prostate cancer in men and its propensity for causing premature mortality require insurance company medical directors and underwriters to have a good understanding of prostate cancer-related mortality trends, patterns, and outcomes in the insured population. METHODOLOGY: - Life insurance applicants with reported prostate cancer were extracted from data covering United States residents between November 2007 and November 2014. Information about these applicants was matched to the Social Security Death Master (SSDMF) file for deaths occurring from 2007 to 2011 and to another commercially available death source file (Other Death Source, ODS) for deaths occurring from 2007 to 2014 to determine vital status. Actual to Expected (A/E) mortality ratios were calculated using the Society of Actuaries 2015 Valuation Basic Table (2015VBT), select and ultimate table (age last birthday) and the 2013 US population as expected mortality ratios. All expected bases were not smoker distinct. RESULTS: - The study covered applicants between the ages of 45 and 75 and had approximately 405,000 person-years of exposure. Older aged applicants had a lower mortality ratio than those who were younger. Applicants 45 to 54 had the highest mortality ratios in the first year after diagnosis which steadily decreased in years 6 to 10 with an increase in the mortality ratio for those over 10 years from diagnosis. Relative mortality rate was close to unity for those with localized cancer across all age groups. The mortality ratio was 2 to 4 times greater for those with cancer in 1 positive node, and much greater with 3 positive nodes. For each time-from-diagnosis category, the relative mortality ratios compared to age were highest in the 45-54 age group. The A/E mortality ratios based on the 2015VBT were consistently 3 to 4 times that of the mortality ratios based on the 2013 US population. CONCLUSION: - The mortality patterns of insurance applicants with prostate cancer were similar to that observed in individuals with prostate cancer in the general population. Applicant age, time to diagnosis and cancer severity were the most significant variables to predict mortality.

All-Cause Mortality for Diabetics or Individuals with Hyperglycemia Applying for Life Insurance.

Diabetics and individuals with lab results consistent with a diagnosis of diabetes or hyperglycemia were extracted from data covering US residents who applied for life insurance between January 2007 and January 2014. Information about these applicants was matched to the Social Security Death Master File (SSDMF) and another commercially available death source file to determine vital status. Due to the inconsistencies of reporting within the death files, there were two cohorts of death cases, one including the imputed year of birth (full cohort of deaths), and the second where the date of birth was known (reduced cohort of deaths). The study had approximately 8.5 million person-years of exposure. Actual to expected (A/E) mortality ratios were calculated using the Society of Actuaries 2008 Valuation Basic Table (2008VBT) select table, age last birthday and the 2010 US population as expected mortality rates. With the 2008VBT as an expected basis, the overall A/E mortality ratio was 3.15 for the full cohort of deaths and 2.56 for the reduced cohort of deaths. Using the US population as the expected basis, the overall A/E mortality ratio was 0.98 for the full cohort of deaths and 0.79 for the reduced cohort. Since there was no smoking status information in this study, all expected bases were not smoker distinct. A/E mortality ratios varied by disease treatment category and were considerably higher in individuals using insulin. A/E mortality ratios decreased with increasing age and took on a J-shaped distribution with increasing BMI (Body Mass Index). The lowest mortality ratios were observed for overweight and obese individuals. The A/E mortality ratio based on the 2008VBT decreased with the increase in applicant duration, which was defined as the time since initial life insurance application.

Medicines Adaptive Pathways to Patients (MAPPs): A Story of International Collaboration Leading to Implementation.

After nearly a decade of discussion, analysis, and development, the Medicines Adaptive Pathways to Patients (MAPPs) initiative is beginning to see acceptance from regulators, industry, patients, and payers, with the first live pilot project initiated under the guidance of the European Medicines Agency in 2014. Although it is a significant achievement to see the first asset being placed into human trials under an adaptive pathway, there is much to be learned regarding the multinational and multi-stakeholder effort that has driven the growing acceptance of MAPPs as a methodology and concept, as well as the need for continued and increasing international collaboration to foster the wider adoption of MAPPs. Changes in available science and technology, as well as a number of challenges in the current system, outlined in this paper, are transforming approaches to medicines development and approval. It is these challenges that have led directly to the groundbreaking MAPPs collaboration between the Massachusetts Institute of Technology Center for Biomedical Innovation's New Drug Development Paradigms Initiative, the EMA, patient, payer and health technology assessment groups, the European Federation of Pharmaceutical Industries and Associations, and the Innovative Medicines Initiative-a European public-private partnership. This article examines the development of MAPPs, from inception of the concept, to the establishment of this trans-Atlantic initiative, and examines challenges for the future.

Pharmacokinetics of olanzapine long-acting injection: the clinical perspective.

Olanzapine long-acting injection (OLAI) is a sustained-release depot antipsychotic for the treatment of schizophrenia in adults. Our objective was to explain the pharmacokinetics of OLAI to provide clinical insight. Simulation models and data from clinical trials are presented. Olanzapine concentrations were observed immediately upon injection. Half-life was ∼30 days, controlled by the slow rate of intramuscular absorption rather than the 30-h elimination rate-based half-life of oral olanzapine. As each injection builds on the drug still being released from previous injections, concentrations increase gradually until a steady state is reached after ∼3 months. Concentrations were similar to oral olanzapine and proportional to the dose; the average steady-state concentrations (10th-90th percentile) for the 150, 210, and 300 mg/2-week doses were 16-32, 15-55, and 20-67 ng/ml, respectively, and those for the 300 and 405 mg/4-week doses were 19-48 and 19-62 ng/ml, respectively. Peak concentrations most often occurred at 2-4 days after injection. Peak-to-trough fluctuation was greater for the 4-week dosing interval than the 2-week one, with no apparent clinical ramifications for these differences. Trough concentrations were above the lower end of the therapeutic range, even at the first injection. Long-term use up to 6 years indicated no additional accumulation. The impact of smoking and sex was similar, but less pronounced than for oral olanzapine.

Single- and multiple-dose pharmacokinetic, safety, and tolerability profiles of olanzapine long-acting injection: an open-label, multicenter, nonrandomized study in patients with schizophrenia.

BACKGROUND: This was the first study, to our knowledge, in patients with schizophrenia in which olanzapine long-acting injection (LAI) was used to attempt delivery of depot formulation in multiple therapeutic doses. OBJECTIVE: This study assessed the safety profile, tolerability, and pharmacokinetic (PK) properties of olanzapine after single and multiple administrations of olanzapine LAI and evaluated maintenance of symptom control. METHODS: This was an open-label, multicenter, nonrandomized study of olanzapine LAI in patients with schizophrenia stabilized with oral olanzapine. Key inclusion criteria included well-tolerated and efficacious treatment with daily olanzapine. Patients were required to be receiving a stable oral dose for 4 weeks before study entry with no requirement for as-needed additional antipsychotic medication within 2 weeks before entry. Exclusion criteria included serious unstable illnesses, unresolved seizures, pregnancy or breastfeeding, hypothyroidism, hyperthyroidism, narrow-angle glaucoma, or serious suicidal risk. Initially, 34 patients received olanzapine LAI as a single injection of 50 to 450 mg, and as the study progressed, 247 patients received consecutive injections of 100 to 405 mg olanzapine LAI administered every 2, 3, or 4 weeks for 3 to 6 months. Spontaneously reported adverse events were recorded at each visit. Analyses of efficacy and safety profile parameters were performed on an intent-to-treat basis. All hypotheses were tested at a 2-sided significance level of P < 0.05. RESULTS: Study participants had a mean age of 39 years and were primarily white men. The PK properties suggested prolonged release providing sustained olanzapine plasma concentrations and supporting a dosing interval ≤4 weeks. Olanzapine LAI doses of 150 or 300 mg every 2 weeks and 210 or 405 mg every 4 weeks provide mean steady-state olanzapine concentrations similar to those after oral administration of 5 to 20 mg/d. The mean baseline Brief Psychiatric Rating Scale score of 17.27 decreased by 2.68 points, and the mean baseline Clinical Global Impression-Severity score of 3.39 decreased by 0.23 points, indicating that patients' psychiatric health was maintained or slightly improved. Significant mean weight gain (P < 0.001) and treatment-emergent changes in nonfasting glucose were observed. Incidence of weight gain ≥7% of baseline was observed in 17.8% of patients. The common adverse events were injection site pain, anxiety, sedation, insomnia, somnolence, and headache, and the safety profile for olanzapine LAI was comparable to that of oral olanzapine, except for injection site-related adverse events. CONCLUSION: The safety profile and PK data from this study support continued clinical development of olanzapine LAI in controlled efficacy studies at doses ≤300 mg every 2 weeks or 405 mg every 4 weeks. Clinical trial registry ID: 4535 http://www.lillytrials.com/results/ZyprexaLAI.pdf.

Antibiotic resistance-the need for global solutions.

The causes of antibiotic resistance are complex and include human behaviour at many levels of society; the consequences affect everybody in the world. Similarities with climate change are evident. Many efforts have been made to describe the many different facets of antibiotic resistance and the interventions needed to meet the challenge. However, coordinated action is largely absent, especially at the political level, both nationally and internationally. Antibiotics paved the way for unprecedented medical and societal developments, and are today indispensible in all health systems. Achievements in modern medicine, such as major surgery, organ transplantation, treatment of preterm babies, and cancer chemotherapy, which we today take for granted, would not be possible without access to effective treatment for bacterial infections. Within just a few years, we might be faced with dire setbacks, medically, socially, and economically, unless real and unprecedented global coordinated actions are immediately taken. Here, we describe the global situation of antibiotic resistance, its major causes and consequences, and identify key areas in which action is urgently needed.

Morphotropic phase boundaries in ferromagnets: Tb(1-x)Dy(x)Fe2 alloys.

The structure and properties of the ferromagnet Tb(1-x)Dy(x)Fe(2) are explored through the morphotropic phase boundary (MPB) separating ferroic phases of differing symmetry. Our synchrotron data support a first order structural transition, with a broadening MPB width at higher temperatures. The optimal point for magnetomechanical applications is not centered on the MPB but lies on the rhombohedral side, where the high striction of the rhombohedral majority phase combines with the softened anisotropy of the MPB. We compare our findings with single ion crystal field theory and with ferroelectric MPBs, where the controlling energies are different.

The role of the pharmaceutical industry in meeting the public health threat of antibacterial resistance.

The established market model for pharmaceutical products, as for most other products, is heavily dependent on sales volumes. Thus, it is a primary interest of the producer to sell large quantities. This may be questionable for medicinal products and probably most questionable for antibacterial remedies. For these products, treatment indications are very complex and encompass both potential patient benefits, possible adverse effects in the actual patient and, which is unique for this therapeutic class, consideration about what effects the drug use will have on the future therapeutic value of the drug. This is because bacteria are sure to develop resistance. The European Federation of Pharmaceutical Industries and Associations (EFPIA) agrees with the general description of the antibacterial resistance problem and wants to participate in measures to counteract antibacterial resistance. Stakeholders should forge an alliance that will address the need for and prudent use of new antibiotics. A variety of incentives probably have to be applied, but having all in common that the financial return has to be separated from the use of the product.