AbstractMachine learning plays a key role in the aid of cancer diagnosis and detection. The researcher has implemented different techniques of machine learning for the detection of breast cancer. Some researchers claim that their algorithms are more accurate, faster, and easier than others. My study relies on recently developed machine learning algorithms like genetic algorithms and deep belief nets. I’m interested to construct a system to accurately differentiate between benign and malignant breast tumors. We’ve optimized the training algorithm. During this unique circumstance, we applied the genetic programming procedure to settle on the main genuine highlights and perfect boundary estimations of the AI classifiers. The examinations rely upon affectability, cross-validation, precision, and ROC curve. Among all the varying kinds of classifiers used in this paper genetic programming is the premier viable model for highlight determination and classifier.

Background: By 2040, the predicted global cancer burden is expected to be more than 27 million new cancer cases per year. Understanding primary health care workers’ (HCWs) perception on cancer can highlight new ways in which cancer advocacy can be increased. This study aimed to explore the perceptions of primary HCWs in Lautoka, Fiji, towards common cancers with focus on knowledge, risk perceptions, barriers and preventive approaches. Methods: The study used a qualitative method approach. The study was conducted among primary HCWs at four purposively selected health centres in Lautoka Subdivision, Fiji, from 1 March 2021 to 1 April 2021. Focus group discussions (FGDs) were conducted with primary HCWs. A semi-structured open-ended questionnaire was used to collect data, and the FGDs were audio-recorded. These audio recordings were transcribed and analysed using thematic analysis. Results: The responses from the four FGDs with six primary HCWs in each group emerged four major themes. These themes were cancer knowledge, health professional training, barriers and challenges and awareness strategies. Primary HCWs were not fully aware about common cancers and were not confident to discuss about cancer with their patients which is an important role of primary HCWs in cancer management. This lack of knowledge was attributed to less training received in primary care setting. Barriers to accessing cancer screening included misconceptions about cancer, negative attitudes from patients, stigmatization, lack of resources at health facility and less informed health staff. Community outreach programmes, opportunistic screening, community HCWs and the concept of a cancer hub centre were awareness strategies highlighted by primary HCWs. Conclusions: Lack of knowledge about common cancers among primary HCWs is a concern that is depicted well in this study. This low knowledge was attributed to lack of training on cancers received by primary HCWs. Guidelines on cancer screening and diagnosis can be developed by the health ministry to assist primary HCWs in detecting patients at pre-cancerous stage.

We examine the applicability of time-series forecasting techniques to model and predict chickenpox incidence rates using publicly available epidemiological data from Rozemberczki et al. [1]. Analyzing data across both time and location is crucial in understanding disease dynamics, allowing for the identification of patterns such as temporal clustering, detection of high-incidence areas, characterization of disease spread, measurement of temporal synchrony, and forecasting future incidence rates. The primary objective of this study is to evaluate the effectiveness of neural networks in addressing this problem. Reservoir Computing, ARIMA, and various types of Recurrent Neural Networks (RNNs) have demonstrated success in tackling complex time-series issues. We assess several models based on different RNN architectures, including Long Short-Term Memory (LSTM), Bidirectional LSTM (BLSTM), Gated Recurrent Unit (GRU), Bidirectional GRU (BGRU), and compare their performance. We use a deep learning approach based on Reservoir Computing to predict chickenpox counts based on past incidence rates. We implement all the aforementioned neural network architectures for fore- casting chickenpox incidence rates and compare their prediction accuracy. Our results indicate that Reservoir Computing prediction models outperform all other models trained on the same data. Furthermore, we demonstrate that Reservoir Computing prediction models are more efficient and quicker to train and deploy in epidemiology.

No abstract

Background Understanding patients’ perspective to get an insight into cancer, and how best the public health systems can battle with this disease is the way forward in this current world. This study aimed to explore patients’ knowledge about common cancers, barriers to assessing cancer information and cancer preventative approaches in Fiji. Methods The study used a qualitative method approach that was conducted among patients who attended Special Outpatients (SOPD) at the four selected health centres in Lautoka Subdivision, Fiji from 1st March to 30th April 2021. A semi-structured open-ended questionnaire was used to guide in-depth interviews. These audio recordings were transcribed and analysed using thematic analysis. All interview transcripts were read and similar words and phrases were assigned numbers which were grouped together to identify themes and sub themes. Results Twenty-eight patients took part in the in-depth interview and the responses were grouped into four themes including; cancer knowledge, diagnosis of cancer in a close friend/family, barriers of communication and optimizing cancer awareness. Patients’ awareness about common cancers and cancer risk factors was low. Many barriers for cancer screening were highlighted including stigmatization, fear, worry, death, lack of information, herbal medicine use, lack of resources and delay in diagnosis. Awareness strategies highlighted by participants included community outreach programs, house to house visits, opportunistic screening, engagement of community health care workers and the concept of a cancer hub centre. Conclusion It is evident that there is a range of views from patients towards cancer and it is important to understand these perceptions to better guide public health interventions concerning cancer. This puts more focus on the need to invest more in information, education, and communication material for public campaigns that target a variety of people for a wider reach.