Prediction of drinking water quality with machine learning models: A public health nursing approach.

OBJECTIVE: The aim of this study is to use machine learning models to predict drinking water quality from a public health nursing approach. DESIGN: Machine learning study. SAMPLE: "Water Quality Dataset" was used in the study. The dataset contains physical and chemical measurements of water quality for 2400 different water bodies. The process consists of four stages: Data processing with Synthetic Minority Oversampling Technique, hyperparameter tuning with 10-fold cross-validation, modeling and comparative analysis. 80% of the dataset is allocated as training data and 20% as test data. ML models logistic regression, K-nearest neighbor, support vector machine, random forest, XGBoost, AdaBoost Classifier, Decision Tree algorithms were used for water quality prediction. Accuracy, precision, recall, F1 score and AUC performance metrics of ML models were compared. To evaluate the performance of the models, 10-fold cross-validation was used and a comparative analysis was performed. The p-values of the models were also compared. RESULTS: N this study, where drinking water quality was predicted with seven different ML algorithms, it can be said that XGBoost and Random Forest are the best classification models in all performance metrics. There is a significant difference in all ML algorithms according to the p-value. The H0 hypothesis is accepted for these algorithms. According to the H0 hypothesis, there is no difference between actual values and predicted values. CONCLUSION: In conclusion, the use of ML models in the prediction of drinking water quality can help nurses greatly improve access to clean water, a human right, be more knowledgeable about water quality, and protect the health of individuals.

Discussions About COVID-19 Vaccination on Twitter in Turkey: Sentiment Analysis.

OBJECTIVES: The present study aims to examine coronavirus disease 2019 (COVID-19) vaccination discussions on Twitter in Turkey and conduct sentiment analysis. METHODS: The current study performed sentiment analysis of Twitter data with the artificial intelligence (AI) Natural Language Processing (NLP) method. The tweets were retrieved retrospectively from March 10, 2020, when the first COVID-19 case was seen in Turkey, to April 18, 2022. A total of 10,308 tweets accessed. The data were filtered before analysis due to excessive noise. First, the text is tokenized. Many steps were applied in normalizing texts. Tweets about the COVID-19 vaccines were classified according to basic emotion categories using sentiment analysis. The resulting dataset was used for training and testing ML (ML) classifiers. RESULTS: It was determined that 7.50% of the tweeters had positive, 0.59% negative, and 91.91% neutral opinions about the COVID-19 vaccination. When the accuracy values of the ML algorithms used in this study were examined, it was seen that the XGBoost (XGB) algorithm had higher scores. CONCLUSIONS: Three of 4 tweets consist of negative and neutral emotions. The responsibility of professional chambers and the public is essential in transforming these neutral and negative feelings into positive ones.

Midwifery Students' Perceptions of Spirituality and Spiritual Care: An Example from Western Turkey.

This cross-sectional study aimed to explore Turkish midwifery students' perceptions of spirituality and spiritual care and to investigate the factors affecting them. Data were collected from 271 students of the Midwifery Department of the High School of Health of a state university in the west of Turkey using the Spirituality and Spiritual Care Rating Scale. A significant difference was found between belief in the need for spiritual care and the practice of spiritual care during midwifery training and the total score on the Spirituality and Spiritual Care Rating Scale, but no significant difference was found between the students' year of class, whether they had heard about spiritual care, and their state of knowledge concerning spiritual care. An increase in awareness, knowledge and skills relating to spirituality and spiritual care on the part of midwifery students, who are the midwives of the future, will allow students to provide spiritual care to their patients after they qualify. For this reason, the education program of midwifery students should be seen from a holistic standpoint in order to develop spiritual care.

The evaluation of the education for earthquake preparation addressed to middle school students.

OBJECTIVE: To investigate the effectiveness of the 'Are We Prepared for an Earthquake?' education provided bynurses to students of sixth and seventh grades. METHODS: The quasi-experimental study was conducted in Kemalpasa district of Izmir, Turkey, from October 2015 to May 2016, and comprised students of sixth and seventh grades at six middle schools in the 2015-16 academic year. Data was collected using 'Are We Prepared for an Earthquake?' questionnaire that included questions about socio-demographic variables, earthquake knowledge test, and family disaster preparation plans checklist. The score ranged from 0 to 20. An interactive packet education programme consisting of class presentation, game and animated videos was delivered and post-intervention scores were compared with baseline. RESULTS: Of 1151 students, 559(48.5%) were in the sixth grade, and 592(51.4%) were in the seventh. The overall mean earthquake knowledge and family disaster preparedness scores increased significantly post-intervention (p-0.001).. CONCLUSIONS: Targetted training created a significant change in both the knowledge level regarding earthquakes and the family disaster preparedness plans.

Prevalence of Tobacco Use among School Teachers and Effect of Training on Tobacco Use in Western Turkey.

BACKGROUND: Tobacco consumption is still a prevalent issue. Given that teachers are respected in society, they have a great responsibility for tobacco control. This study examines, using the Transtheoretical Model (TTM), the prevalence of tobacco use among teachers and their different stages of tobacco use. It also evaluates teachers' views on smoking and the effectiveness of training on tobacco use. METHODS: This study is quasi-experimental. Pre-test and post-test were used first with a cross-sectional group, then with a single group to determine the frequency of tobacco use. The research participation complied with the voluntary principles and the participation rate was 84.9%. The research sample comprised 450 teachers working at schools (N=17) under the Kemalpasa Directorate of Education. The data form contained 29 questions about socio-demographic characteristics and smoking habits. The Fagerstrom Test for Nicotine Dependence (FTND), Smoking Decisional Balance Scale (SDBS), and the Stage of Change were used. A pre-test was also administered, and training was given between January 13 and March 4, 2014. After the training sessions, two short messages (SMS) were sent on March 12 and March 19, 2014. A post-test was administered between April 1 and May 21, 2014. The relevant institutions and participants gave the requisite permission for the data used in this study. Percentage distribution, dependent t-tests and chi-square tests were used to evaluate the research data. RESULTS: The median age of the teachers was 37.49±7.84. The teachers' mean score for the pre-test of FTND was 5.7±2.03, and their mean score for the post-test was 3.25±2.07. Post-test scores were remarkably lower than the pre-test scores. It was found that teachers' mean scores for SDBS were different before and after training. After training, anti-smoking attitudes increased (pros-cons scores: pre-test: -3.64±4.68, post-test: -11.25±5.48). The training helped the entire group to make progress in the process change. CONCLUSION: After training on "the health effects of smoking", teachers' anti-smoking attitudes rose on the smoking decision balance scale, their nicotine dependency was reduced, and they were able to move forward in a positive direction.

Social Perceptions of Breast Cancer by Women Still Undergoing or Having Completed Therapy: a Qualitative Study.

BACKGROUND: Diagnosis and treatment of breast cancer is a crisis situation which effects women's lives physically, socially and spiritually. Investigating women's perceptions of this disease is crucially important for treatment decisions. We therefore determined social perceptions and interpretations of women diagnosed with breast cancer during therapy and in the post-treatment period. MATERIALS AND METHODS: In the study, focus group and in-depth interviews were made with women still undergoing or having completed breast cancer treatment. Some 25 women were included in the research. Content analysis was used in the analysis of the qualitative data obtained after the focus group and in-depth interviews. RESULTS: Some of the women demonstrated positive perceptions towards accepting the disease, whereas others had emotions such as rebellion and anger. The loss of a breast is important with different interpretations. CONCLUSIONS: Women's acceptance or rebellion against the disease varies within their social interpretations after the treatment, as at the stage of diagnosis/treatment. All stages of breast cancer negatively affect the social life of the affected individual as much as her body. Nurses assume crucial roles in coping with these negative effects. Thus, it is necessary to know, and sociologically interpret, what is indicated by the information on what the negative effects concerning the disease are and how they are interpreted.

Barriers on Breast Cancer Early Detection Methods.

OBJECTIVE: Breast cancer is the most common type of cancer in women throughout the world. It is the second leading cause of cancer related deaths, after lung cancer. Breast cancer is the most common cancer in women in Turkey with a rate of 23,4%. One out of every four women has breast cancer. This study was conducted to determine the barriers on methods of early diagnosis of breast cancer. MATERIALS AND METHODS: The research population consisted of women over the age of 40 years who live in the neighborhood of Doganlar (N=2404). The sample size was determined (n=251) with Epi Info Statcalc account program with 95% confidence interval, with the incidence of breast cancer accepted as 24%. Women over the age of 40 years who agreed to participate were included in the study. In order to collect the necessary data, a 27-item questionnaire including socio-demographic characteristics and methods of early diagnosis was created according to the literature. This study was conducted between March-October 2012 in Doganlar neighborhood. RESULTS: Two-hundred-fifty-four women participated in the study, with a mean age of 54,27±1, and an average monthly income of 895,0197 TL (min=0 TL, max=7000 TL). 79,1% were married, 89,8% were housewives, 56,7% were literate, and 83,1% had health insurance. The status of performing regular Breast Self Examination (BSE) was significantly higher in women who had knowledge about BSE, (p=0.000). Married (p=0.015) women and those who had a social security system (p=0.048) had significantly higher rates of mammography. Women who were informed on mammography (p=0.000) had significantly higher rates of mammography. When reasons for not getting mammography was addressed, it was observed that 99,2% was due to lack of information and education. Women who had regular BSE had significantly higher Clinical Breast Examination (CBE) (p=0.024). Women's sociodemographic characteristics did not affect the status of performing regular BSE and CBE significantly. CONCLUSION: Barriers against implementation of breast cancer screening methods in women were related to level of education and lack of adequate information about breast cancer screening, and symptoms of breast cancer. Women's lack of information about signs, symptoms and treatment in the early stages of breast cancer needs to be eliminated. Health care providers may have a key role in increasing breast cancer early detection rates.

Assessment of the effects of breast cancer training on women between the ages of 50 and 70 in Kemalpasa, Turkey.

BACKGROUND: In both developed and developing countries; breast cancer is the major cancer observed in women. The aim of this study was to assess the effect of nursing and mammographic intervention on women with breast cancer between the ages of 50 and 70. MATERIALS AND METHODS: A training program, which was quasi- experimental and had a pretest-protest design, was applied in Kemalpas?a district of Izmir, between October 2008 and August 2010. The target population was women between the ages of 50 and 70, who were registered in the list of 3rd Family Medicine Unit in Izmir's Kemalpas?a metropolis. A total of 106 women who were in conformity with the study criteria participated in the study. Research data were collected through home visits that included face-to-face interviews; Ministry of Health education material and video films were modified and used for the training. Data analysis was performed through 82 women who were paired at the first and the second phase. RESULTS: It was observed that although the rate of breast self examination significantly increased after the training (p=0.022), the rate of clinical breast examination (p=0.122) and mammographic screening (p=0.523) did not. Differences in the stages of change after training were found to be statistically significant (p<0.001) and the group showed a progression in the stages of change in general (46.3%). In women mean scores of breast cancer awareness (p<0.000), severity (p<0.000), health motivation (p<0.000) and perception of the benefits of mammography (p<0.000) increased significantly and mean score of perception of mammography barriers decreased significantly (p<0.000) after the training. CONCLUSIONS: After the training on breast cancer and mammography it was determined that nursing interventions provided positive progression of stages of change of women, affected health beliefs positively and significantly increased BSE incidences. However, it did not have a significant effect on CBE and mammographic screening.

Breast cancer risk and early diagnosis applications in Turkish women aged 50 and over.

BACKGROUND: The aim of the study was to determine breast cancer risk and early diagnosis applications in women aged ≥50. MATERIALS AND METHODS: This cross-sectional, descriptive field study focused on a population of 4,815 in Mansurog?lu with a 55.1% participation rate in screening. In the study, body mass index (BMI) was also evaluated in the calculation of breast cancer risk by the Breast Cancer Risk Assessment Tool (BCRA) (also called the "Gail Risk Assessment Tool") . The interviewers had a three-hour training provided by the researchers, during which interactive training methods were used and applications were supported with role-plays. RESULTS: The mean age of the women participating in the study was 60.1±8.80. Of these women, 57.3% were in the 50-59 age group, 71.7% were married, 57.3% were primary school graduates and 61.7% were housewives. Breast-cancer development rate was 7.4% in the women participating in the study. When they were evaluated according to their relationship with those with breast cancer, it was determined that 73.0% of them had first- degree relatives with breast cancer. According to the assessment based on the Gail method, the women's breast cancer development risk within the next 5 years was 17.6%, whereas their calculated lifetime risk was found to be as low as 0.2%. Statistically significant differences (P=0.000) were determined between performing BSE - CBE and socio-demographic factors. CONCLUSIONS: It was determined that 17.6% of the participants had breast cancer risk. There was no statistically significant difference between the women with and without breast cancer risk in terms of early diagnosis practices, which can be regarded as a remarkable finding. It was planned to provide training about the early diagnosis and treatment of breast cancer for people with high-risk scores, and to conduct population-based breast cancer screening programs.

Health beliefs and breast self-examination in a sample of Turkish women academicians in a university.

OBJECTIVE: The purpose of this study was to evaluate health beliefs and BSE behavior of female academicians in a Turkish university. METHODS: This descriptive study was conducted at various faculties located in Ege University, Izmir, Turkey, in 2005. The sample consisted of 224 female academicians. Data were collected using a self-administered questionnaire and the Turkish version of Champion's Health Belief Model Scales (HBM). Descriptive statistics, t-test and Mann Whitney u analysis were conducted. RESULTS: The percentage of participants who regularly performed BSE was 27.7 %. Benefits and health motivation related to BSE ranked either first or second, along with confidence. Perceived barriers to BSE had the lowest item mean subscale score in academicians. Single academicians perceived susceptibility and seriousness higher than their married counterparts. Family history of breast cancer of participants affected their health beliefs subscale. CONCLUSIONS: BSE performance among participants was more likely in women academicians who exhibited higher confidence and those who perceived fewer barriers related to BSE performance, complying with the conceptual structure of the HBM. Therefore, it is recommended that in order to increase the rates of regular breast cancer screening, mass health protective programs based on the HBM should be executed for women.

Nutrition, lifestyle, and breast cancer risk among Turkish women.

Breast cancer is the most common malignancy in women, with more than 1 million cases occurring worldwide annually. Cancer is one of the leading causes of mortality in Turkey; deaths due to breast cancer constitute 24.1% of all carcinoma cases reported among women. We conducted a case-control study of Turkish women with and without breast cancer to investigate the relationships of selected lifestyle and nutritional risk factors with breast cancer risk. Factors were chosen based upon published associations with breast cancer. Subjects were women in Izmir, Turkey. Cases were 123 women with breast cancer registered with the Department of Oncology, Ege University Hospital, in February through July 2004. The control group included 120 randomly selected women without a breast cancer diagnosis, registered with the Evka-4 Health Care Center and having similar sociodemographic characteristics. Inclusion criteria for participation consisted of 40 yr of age and over and willingness to participate. Chi2 tests and t-tests were used to determine statistical differences between cases and controls based on selected variables. Logistic regression was used to find the association between selected risk factors and breast cancer occurrence. Cases had smoked for more years, their age of first pregnancy was higher, and breast cancer occurrence was more common in first-degree relatives such as mothers and sisters of cases compared with controls. Cases were found to have consumed higher amounts of vegetable oil in contrast to controls. These findings are consistent with similar studies conducted in both developed and developing countries.