Epidemiology of lung cancer and approaches for its prediction: a systematic review and analysis

Background

Owing to the use of tobacco and the consumption of alcohol and adulterated food, worldwide cancer incidence is increasing at an alarming and frightening rate. Since the last decade of the twentieth century, lung cancer has been the most common cancer type. This study aimed to determine the global status of lung cancer and to evaluate the use of computational methods in the early detection of lung cancer.

Methods

We used lung cancer data from the United Kingdom (UK), the United States (US), India, and Egypt. For statistical analysis, we used incidence and mortality as well as survival rates to better understand the critical state of lung cancer.

Results

In the UK and the US, we found a significant decrease in lung cancer mortalities in the period of 1990–2014, whereas, in India and Egypt, such a decrease was not much promising. Additionally, we observed that, in the UK and the US, the survival rates of women with lung cancer were higher than those of men. We observed that the data mining and evolutionary algorithms were efficient in lung cancer detection.

Conclusions

Our findings provide an inclusive understanding of the incidences, mortalities, and survival rates of lung cancer in the UK, the US, India, and Egypt. The combined use of data mining and evolutionary algorithm can be efficient in lung cancer detection.

Analysis of k-means clustering approach on the breast cancer Wisconsin dataset

PURPOSE

Breast cancer is one of the most common cancers found worldwide and most frequently found in women. An early detection of breast cancer provides the possibility of its cure; therefore, a large number of studies are currently going on to identify methods that can detect breast cancer in its early stages. This study was aimed to find the effects of k-means clustering algorithm with different computation measures like centroid, distance, split method, epoch, attribute, and iteration and to carefully consider and identify the combination of measures that has potential of highly accurate clustering accuracy.

METHODS

K-means algorithm was used to evaluate the impact of clustering using centroid initialization, distance measures, and split methods. The experiments were performed using breast cancer Wisconsin (BCW) diagnostic dataset. Foggy and random centroids were used for the centroid initialization. In foggy centroid, based on random values, the first centroid was calculated. For random centroid, the initial centroid was considered as (0, 0).

RESULTS

The results were obtained by employing k-means algorithm and are discussed with different cases considering variable parameters. The calculations were based on the centroid (foggy/random), distance (Euclidean/Manhattan/Pearson), split (simple/variance), threshold (constant epoch/same centroid), attribute (2-9), and iteration (4-10). Approximately, 92 % average positive prediction accuracy was obtained with this approach. Better results were found for the same centroid and the highest variance. The results achieved using Euclidean and Manhattan were better than the Pearson correlation.

CONCLUSIONS

The findings of this work provided extensive understanding of the computational parameters that can be used with k-means. The results indicated that k-means has a potential to classify BCW dataset.

Breast cancer statistics and prediction methodology: a systematic review and analysis

Breast cancer is a menacing cancer, primarily affecting women. Continuous research is going on for detecting breast cancer in the early stage as the possibility of cure in early stages is bright. There are two main objectives of this current study, first establish statistics for breast cancer and second to find methodologies which can be helpful in the early stage detection of the breast cancer based on previous studies. The breast cancer statistics for incidence and mortality of the UK, US, India and Egypt were considered for this study. The finding of this study proved that the overall mortality rates of the UK and US have been improved because of awareness, improved medical technology and screening, but in case of India and Egypt the condition is less positive because of lack of awareness. The methodological findings of this study suggest a combined framework based on data mining and evolutionary algorithms. It provides a strong bridge in improving the classification and detection accuracy of breast cancer data.