Exploring cancer register data to find risk factors for recurrence of breast cancer--application of Canonical Correlation Analysis

Determination of weight loss effectiveness evaluation indexes and establishment of a nomogram for forecasting the probability of effectiveness of weight loss in bariatric surgery: a retrospective cohort

BACKGROUND

The purpose of this research was to determine the index that contributes the most to assessing the effectiveness of weight loss 1 year following bariatric surgery and to implement it as the clinical outcome to develop and confirm a nomogram to predict whether bariatric surgery would be effective.

METHODS

Patient information was extracted from the Chinese Obesity and Metabolic Surgery Database for this retrospective study. The most contributing weight loss effectiveness evaluation index was created using canonical correlation analysis (CCA), and the predictors were screened using logistic regression analysis. A nomogram for estimating the likelihood of effectiveness of weight loss was constructed, and its performance was further verified.

RESULTS

Information was obtained for 540 patients, including 30 variables. According to the CCA, ≥25 percentage total weight loss was found to be the most correlated with patient information and contribute the most as a weight loss effectiveness evaluation index. Logistic regression analysis and nomogram scores identified age, surgical strategy, abdominal circumference, weight loss history, and hyperlipidemia as predictors of effectiveness in weight loss. The prediction model's discrimination, accuracy, and clinical benefit were demonstrated by the consistency index, calibration curve, and decision curve analysis.

CONCLUSIONS

The authors determined a 25 percentage total weight loss as an index for weight loss effectiveness assessment by CCA and next established and validated a nomogram, which demonstrated promising performance in predicting the probability of effectiveness of weight loss in bariatric surgery. The nomogram might be a valuable tool in clinical practice.

A canonical correlation analysis based EMG classification algorithm for eliminating electrode shift effect

Motion classification system based on surface Electromyography (sEMG) pattern recognition has achieved good results in experimental condition. But it is still a challenge for clinical implement and practical application. Many factors contribute to the difficulty of clinical use of the EMG based dexterous control. The most obvious and important is the noise in the EMG signal caused by electrode shift, muscle fatigue, motion artifact, inherent instability of signal and biological signals such as Electrocardiogram. In this paper, a novel method based on Canonical Correlation Analysis (CCA) was developed to eliminate the reduction of classification accuracy caused by electrode shift. The average classification accuracy of our method were above 95% for the healthy subjects. In the process, we validated the influence of electrode shift on motion classification accuracy and discovered the strong correlation with correlation coefficient of >0.9 between shift position data and normal position data.

Relationship between Autonomic Markers of Heart Rate and Subjective Indicators of Recovery Status in Male, Elite Badminton Players

The primary aim of the study was to determine if heart rate variability (HRV), and heart rate recovery (HRR) are related to several subjective indicators of recovery status (muscle soreness, hydration status, sleep quality and quantity as well as pre-competition mood states) for different match periods in male, elite, African, singles badminton players. HRV and HRR were measured in twenty-two badminton players before (pre-match), during (in-match), after (post-match) and during rest periods (in-match rest) of 46 national and international matches. Muscle soreness, hydration status, and sleep quality and quantity were measured on a daily basis whereas mood states were measured just before each match via questionnaires. Prior to each match warm-up, players were fitted with a Fix Polar Heart Rate Transmitter Belt to record heart rate every second during each match and HRR during service breaks and after matches. Kubios HRV software was used for final HRV analyses from the series of R-R-intervals. A strong, significant canonical correlation (Rc = 0.96, p = 0.014) was found between HRV, HRR and subjective indicators of recovery status for the in-match period, but only strong, non-significant relationships were observed for pre-match (Rc = 0.98, p = 0.626) and post-match periods (Rc = 0.98, p = 0.085) and a low non-significant relationship (Rc = 0.69, p = 0.258) for the in-match rest period. Canonical functions accounted for between 47.89% and 96.43% of the total variation between the two canonical variants. Results further revealed that Ln-HFnu, the energy index and vigour were the most prominent variables in the relationship between the autonomic markers of heart rate and recovery-related variables. In conclusion, this study proved that subjective indicators of recovery status influence HRV and HRR measures obtained in a competitive badminton environment and should therefore be incorporated in protocols that evaluate these ANS-related parameters.

Application of Canonical Correlation Analysis for Detecting Risk Factors Leading to Recurrence of Breast Cancer

BACKGROUND

Advances in treatment options of breast cancer and development of cancer research centers have necessitated the collection of many variables about breast cancer patients. Detection of important variables as predictors and outcomes among them, without applying an appropriate statistical method is a very challenging task. Because of recurrent nature of breast cancer occurring in different time intervals, there are usually more than one variable in the outcome set. For the prevention of this problem that causes multicollinearity, a statistical method named canonical correlation analysis (CCA) is a good solution.

OBJECTIVES

The purpose of this study was to analyze the data related to breast cancer recurrence of Iranian females using the CCA method to determine important risk factors.

PATIENTS AND METHODS

In this cross-sectional study, data of 584 female patients (mean age of 45.9 years) referred to Breast Cancer Research Center (Tehran, Iran) were analyzed anonymously. SPSS and NORM softwares (2.03) were used for data transformation, running and interpretation of CCA and replacing missing values, respectively. Data were obtained from Breast Cancer Research Center, Tehran, Iran.

RESULTS

Analysis showed seven important predictors resulting in breast cancer recurrence in different time periods. Family history and loco-regional recurrence more than 5 years after diagnosis were the most important variables among predictors and outcomes sets, respectively.

CONCLUSIONS

Canonical correlation analysis can be used as a useful tool for management and preparing of medical data for discovering of knowledge hidden in them.

Potential risk factors associated with human encephalitis: application of canonical correlation analysis

BACKGROUND

Infection of the CNS is considered to be the major cause of encephalitis and more than 100 different pathogens have been recognized as causative agents. Despite being identified worldwide as an important public health concern, studies on encephalitis are very few and often focus on particular types (with respect to causative agents) of encephalitis (e.g. West Nile, Japanese, etc.). Moreover, a number of other infectious and non-infectious conditions present with similar symptoms, and distinguishing encephalitis from other disguising conditions continues to a challenging task.

METHODS

We used canonical correlation analysis (CCA) to assess associations between set of exposure variable and set of symptom and diagnostic variables in human encephalitis. Data consists of 208 confirmed cases of encephalitis from a prospective multicenter study conducted in the United Kingdom. We used a covariance matrix based on Gini's measure of similarity and used permutation based approaches to test significance of canonical variates.

RESULTS

Results show that weak pair-wise correlation exists between the risk factor (exposure and demographic) and symptom/laboratory variables. However, the first canonical variate from CCA revealed strong multivariate correlation (ρ = 0.71, se = 0.03, p = 0.013) between the two sets. We found a moderate correlation (ρ = 0.54, se = 0.02) between the variables in the second canonical variate, however, the value is not statistically significant (p = 0.68). Our results also show that a very small amount of the variation in the symptom sets is explained by the exposure variables. This indicates that host factors, rather than environmental factors might be important towards understanding the etiology of encephalitis and facilitate early diagnosis and treatment of encephalitis patients.

CONCLUSIONS

There is no standard laboratory diagnostic strategy for investigation of encephalitis and even experienced physicians are often uncertain about the cause, appropriate therapy and prognosis of encephalitis. Exploration of human encephalitis data using advanced multivariate statistical modelling approaches that can capture the inherent complexity in the data is, therefore, crucial in understanding the causes of human encephalitis. Moreover, application of multivariate exploratory techniques will generate clinically important hypotheses and offer useful insight into the number and nature of variables worthy of further consideration in a confirmatory statistical analysis.

FANCD2 mRNA overexpression is a bona fide indicator of lymph node metastasis in human colorectal cancer

BACKGROUND

Lymph node metastasis is widely accepted as one of the most important determinants of prognosis in colorectal cancer (CRC) patients. Therefore, there is an urgent need to identify molecular markers that can be used to predict lymph node metastasis.

MATERIALS AND METHODS

Candidate genes were found using LMD and cDNA microarrays in a large-scale study of CRC, followed by Penalized Canonical Correlation Analysis (PCCA). We focused on the Fanconi anemia, complementation group D2 (FANCD2) gene and evaluated FANCD2 mRNA expression in 133 CRC cases to determine the clinicopathological significance of FANCD2 expression.

RESULTS

The mean level of FANCD2 mRNA expression in tumor tissue specimens was significantly higher than in nontumor tissue. FANCD2 expression was found to be a significant factor affecting lymph node metastasis: the high FANCD2 expression group had a significantly poorer prognosis than the low expression group.

CONCLUSIONS

This study suggests that PCCA can be used to identify genes related to clinicopathological features. Furthermore, high FANCD2 expression was a significant independent factor for lymph node metastasis.

Predicting Metastasis in Breast Cancer: Comparing a Decision Tree with Domain Experts

Breast malignancy is the second most common cause of cancer death among women in Western countries. Identifying high-risk patients is vital in order to provide them with specialized treatment. In some situations, such as when access to experienced oncologists is not possible, decision support methods can be helpful in predicting the recurrence of cancer. Three thousand six hundred ninety-nine breast cancer patients admitted in south-east Sweden from 1986 to 1995 were studied. A decision tree was trained with all patients except for 100 cases and tested with those 100 cases. Two domain experts were asked for their opinions about the probability of recurrence of a certain outcome for these 100 patients. ROC curves, area under the ROC curves, and calibration for predictions were computed and compared. After comparing the predictions from a model built by data mining with predictions made by two domain experts, no significant differences were noted. In situations where experienced oncologists are not available, predictive models created with data mining techniques can be used to support physicians in decision making with acceptable accuracy.

The metabolic signature related to high plant growth rate in Arabidopsis thaliana

The decline of available fossil fuel reserves has triggered world-wide efforts to develop alternative energy sources based on plant biomass. Detailed knowledge of the relations of metabolism and biomass accumulation can be expected to yield powerful novel tools to accelerate and enhance energy plant breeding programs. We used metabolic profiling in the model Arabidopsis to study the relation between biomass and metabolic composition using a recombinant inbred line (RIL) population. A highly significant canonical correlation (0.73) was observed, revealing a close link between biomass and a specific combination of metabolites. Dividing the entire data set into training and test sets resulted in a median correlation between predicted and true biomass of 0.58. The demonstrated high predictive power of metabolic composition for biomass features this composite measure as an excellent biomarker and opens new opportunities to enhance plant breeding specifically in the context of renewable resources.