Economic Control of Quality of Manufactured Product.

Machine learning is a branch of artificial intelligence that employs a variety of statistical, probabilistic and optimization techniques that allows computers to “learn” from past examples and to detect hard-to-discern patterns from large, noisy or complex data sets. This capability is particularly well-suited to medical applications, especially those that depend on complex proteomic and genomic measurements. As a result, machine learning is frequently used in cancer diagnosis and detection. More recently machine learning has been applied to cancer prognosis and prediction. This latter approach is particularly interesting as it is part of a growing trend towards personalized, predictive medicine. In assembling this review we conducted a broad survey of the different types of machine learning methods being used, the types of data being integrated and the performance of these methods in cancer prediction and prognosis. A number of trends are noted, including a growing dependence on protein biomarkers and mi...

/pdf/applications-of-machine-learning-in-cancer-prediction-and-2oti5pk54y.pdf

Applications of Machine Learning in Cancer Prediction and Prognosis

justed HR, 1.7 [95% CI, 0.9-3.2]), and the absolute risk of childhood autism was 2.95% (95% CI, 1.42%-6.11%) (adjusted HR, 2.9 [95% CI, 1.4-6.0]) vs 2.44% (95% CI, 1.88%-3.16%) for autism spectrum disorder and 1.02% (95% CI, 0.70%-1.49%) for childhood autism among 6152 children not exposed to valproate. Conclusions and Relevance Maternal use of valproate during pregnancy was associated with a significantly increased risk of autism spectrum disorder and childhood autism in the offspring, even after adjusting for maternal epilepsy. For women of childbearing potential who use antiepileptic medications, these findings must be balanced against the treatment benefits for women who require valproate for epilepsy control.

/pdf/prenatal-valproate-exposure-and-risk-of-autism-spectrum-1y76x1mhtu.pdf

Prenatal valproate exposure and risk of autism spectrum disorders and childhood autism.

Autism spectrum disorder (ASD) is a complex neurodevelopmental condition with lifelong impacts. Genetic and environmental factors contribute to ASD etiology, which remains incompletely understood. Research on ASD epidemiology has made significant advances in the past decade. Current prevalence is estimated to be at least 1.5% in developed countries, with recent increases primarily among those without comorbid intellectual disability. Genetic studies have identified a number of rare de novo mutations and gained footing in the areas of polygenic risk, epigenetics, and gene-by-environment interaction. Epidemiologic investigations focused on nongenetic factors have established advanced parental age and preterm birth as ASD risk factors, indicated that prenatal exposure to air pollution and short interpregnancy interval are potential risk factors, and suggested the need for further exploration of certain prenatal nutrients, metabolic conditions, and exposure to endocrine-disrupting chemicals. We discuss future...

The Changing Epidemiology of Autism Spectrum Disorders

Cyclophosphamide is an extensively used anticancer and immunosuppressive agent. It is a prodrug undergoing a complicated process of metabolic activation and inactivation. Technical difficulties in the accurate determination of the cyclophosphamide metabolites have long hampered the assessment of the clinical pharmacology of this drug. As these techniques are becoming increasingly available, adequate description of the pharmacokinetics of cyclophosphamide and its metabolites has become possible. There is incomplete understanding on the role of cyclophosphamide metabolites in the efficacy and toxicity of cyclophosphamide therapy. However, relationships between toxicity (cardiotoxicity, veno-occlusive disease) and exposure to cyclophosphamide and its metabolites have been established. Variations in the balance between metabolic activation and inactivation of cyclophosphamide owing to autoinduction, dose escalation, drug-drug interactions and individual differences have been reported, suggesting possibilities for optimisation of cyclophosphamide therapy. Knowledge of the pharmacokinetics of cyclophosphamide, and possibly monitoring the pharmacokinetics of cyclophosphamide in individuals, may be useful for improving its therapeutic index.

Clinical Pharmacokinetics of Cyclophosphamide

The aim of this study was to compare the prevalence of diagnosed neurodevelopmental disorders in children exposed, in utero, to different antiepileptic drug treatments. A prospective cohort of women with epilepsy and a control group of women without epilepsy were recruited from antenatal clinics. The children of this cohort were followed longitudinally until 6 years of age (n=415). Diagnosis of a neurodevelopmental disorder was made independently of the research team. Multiple logistic regression analysis revealed an increase in risk of neurodevelopmental disorders in children exposed to monotherapy sodium valproate (VPA) (6/50, 12.0%; aOR 6.05, 95%CI 1.65 to 24.53, p=0.007) and in those exposed to polytherapy with sodium VPA (3/20, 15.0%; aOR 9.97, 95% CI 1.82 to 49.40, p=0.005) compared with control children (4/214; 1.87%). Autistic spectrum disorder was the most frequent diagnosis. No significant increase was found among children exposed to carbamazepine (1/50) or lamotrigine (2/30). An accumulation of evidence demonstrates that the risks associated with prenatal sodium VPA exposure include an increased prevalence of neurodevelopmental disorders. Whether such disorders are discrete or represent the severe end of a continuum of altered neurodevelopmental functioning requires further investigation. Replication and extension of this research is required to investigate the mechanism(s) underpinning the relationship. Finally, the increased likelihood of neurodevelopmental disorders should be communicated to women for whom sodium VPA is a treatment option.

/pdf/the-prevalence-of-neurodevelopmental-disorders-in-children-3xo9k18fmt.pdf

The prevalence of neurodevelopmental disorders in children prenatally exposed to antiepileptic drugs

BACKGROUND

Neural networks have been used to predict outcome in cancer patients. Their accuracy compared with standard statistical methods has not been fully assessed.



METHODS

In this study, the authors examined the ability to predict the outcome of surgery in 620 patients with nonsmall cell lung carcinoma (NSCLC) by a genetic algorithm neural network (GANN) using Bayes' theorem compared with logistic regression, and the predictive value of tumor volume measures in addition to standard indices such as histologic type and stage. Predictive methods were compared by examining accuracy of classifying target outcome of patients living or dead at 6, 12, 18, and 24 months after surgery.



RESULTS

GANN was a significantly better predictor of outcome than logistic regression at all time points (McNemar, P < 0.01). Measures of tumor volume produced significant improvement in the prediction of 12-, 18-, and 24-month time points with GANN, and at 18- and 24-month time points with logistic regression (Wilcoxon matched pairs signed rank test, P < 0.02).



CONCLUSIONS

In this study of surgically treated NSCLC patients, outcome predictions were significantly improved by including measures of tumor volume. For predicting individual patient outcome, GANN was found to be highly accurate and significantly better than logistic regression. Cancer 1997; 79:1338-42. © 1997 American Cancer Society.

Comparison of a genetic algorithm neural network with logistic regression for predicting outcome after surgery for patients with nonsmall cell lung carcinoma.

The clinical pharmacology of 4-demethoxydaunorubicin (4-DMDNR) was studied in 28 patients with advanced breast cancer, using a sensitive reverse-phase HPLC technique. All patients had normal renal and hepatic function. The serum levels of 4-DMDNR after a single i.v. bolus injection followed a triple exponential decay curve (T1/2α=9.6 min, T1/2β=3.2 h and T1/2γ=34.7 h) and conformed to a three-compartment model. Comparison of the area under the curve (AUC) and urinary excretion for the oral and i.v routes suggests an oral bioavailability of approximately 24%. In patients treated with a schedule of weekly oral administration for periods of up to 12 months there was no significant alteration in either AUC or elimination half-life for the parent drug or its principal metabolite 13-OH4DMDNR. Moreover, there was no evidence of accumulation of the metabolite although measurable amounts were present 7 days after administration of 4-DMDNR.

Clinical pharmacology of oral and intravenous 4-demethoxydaunorubicin.

Evolution of artificial neural network architecture: prediction of depression after mania. -

Evolution of artificial neural network architecture: prediction of depression after mania

Recombinant human granulocyte colony-stimulating factor (G-CSF) has been shown to reduce neutropenia following cytotoxic therapy, thereby enabling dose escalation to improve the response rate. It is important to know whether drug kinetics change as doses are increased. Doxorubicin was selected because of its broad spectrum of activity and its known efficacy in metastatic breast cancer. Doses of 75, 100, 125 and 150 mg/m2 were given to 11 patients with metastatic breast cancer by infusion over 30 min. Serum concentrations of parent drug and metabolites were determined during the first 48 h following the infusion by high-performance liquid chromatography (HPLC). The serum concentration vs time curve decayed as a triple exponential function in four patients and as a double exponential function in seven. A four-compartment model, one central and three peripheral, would predict concentrations to within 1 SE of the observed values. Doxorubicinol was the principal metabolite, and doxorubicinone and 7-deoxydoxorubicinone were clearly identified. There was a linear increase in the AUC∞ with dose. In addition, a small and transient increase in circulating levels of doxorubicinol and other important metabolites was observed 6 h following the administration of doxorubicin, which suggests the existence of an enterohepatic, or other, re-circulation mechanism. We conclude that in the dose range selected the kinetics of doxorubicin are linear and that the increase in toxicities seen with the higher doses of doxorubicin, following the second and third fortnightly administration, may be due to intracellular drug accumulation in tissues.

S. B. Lucas

Papers

The prevalence of neurodevelopmental disorders in children prenatally exposed to antiepileptic drugs

Comparison of a genetic algorithm neural network with logistic regression for predicting outcome after surgery for patients with nonsmall cell lung carcinoma.

Clinical pharmacology of oral and intravenous 4-demethoxydaunorubicin.

Evolution of artificial neural network architecture: prediction of depression after mania

Comparative pharmacokinetics of escalating doses of doxorubicin in patients with metastatic breast cancer.