How AI Responds to Common Lung Cancer Questions: ChatGPT vs Google Bard.

Background The recent release of large language models (LLMs) for public use, such as ChatGPT and Google Bard, has opened up a multitude of potential benefits as well as challenges. Purpose To evaluate and compare the accuracy and consistency of responses generated by publicly available ChatGPT-3.5 and Google Bard to non-expert questions related to lung cancer prevention, screening, and terminology commonly used in radiology reports based on the recommendation of Lung Imaging Reporting and Data System (Lung-RADS) v2022 from American College of Radiology and Fleischner society. Materials and Methods Forty of the exact same questions were created and presented to ChatGPT-3.5 and Google Bard experimental version as well as Bing and Google search engines by three different authors of this paper. Each answer was reviewed by two radiologists for accuracy. Responses were scored as correct, partially correct, incorrect, or unanswered. Consistency was also evaluated among the answers. Here, consistency was defined as the agreement between the three answers provided by ChatGPT-3.5, Google Bard experimental version, Bing, and Google search engines regardless of whether the concept conveyed was correct or incorrect. The accuracy among different tools were evaluated using Stata. Results ChatGPT-3.5 answered 120 questions with 85 (70.8%) correct, 14 (11.7%) partially correct, and 21 (17.5%) incorrect. Google Bard did not answer 23 (19.1%) questions. Among the 97 questions answered by Google Bard, 62 (51.7%) were correct, 11 (9.2%) were partially correct, and 24 (20%) were incorrect. Bing answered 120 questions with 74 (61.7%) correct, 13 (10.8%) partially correct, and 33 (27.5%) incorrect. Google search engine answered 120 questions with 66 (55%) correct, 27 (22.5%) partially correct, and 27 (22.5%) incorrect. The ChatGPT-3.5 is more likely to provide correct or partially answer than Google Bard, approximately by 1.5 folds (OR = 1.55, P = 0.004). ChatGPT-3.5 and Google search engine were more likely to be consistent than Google Bard by approximately 7 and 29 folds (OR = 6.65, P = 0.002 for ChatGPT and OR = 28.83, P = 0.002 for Google search engine, respectively). Conclusion Although ChatGPT-3.5 had a higher accuracy in comparison with the other tools, neither ChatGPT nor Google Bard, Bing and Google search engines answered all questions correctly and with 100% consistency.

A variant selection framework for genome graphs.

MOTIVATION: Variation graph representations are projected to either replace or supplement conventional single genome references due to their ability to capture population genetic diversity and reduce reference bias. Vast catalogues of genetic variants for many species now exist, and it is natural to ask which among these are crucial to circumvent reference bias during read mapping. RESULTS: In this work, we propose a novel mathematical framework for variant selection, by casting it in terms of minimizing variation graph size subject to preserving paths of length α with at most δ differences. This framework leads to a rich set of problems based on the types of variants [e.g. single nucleotide polymorphisms (SNPs), indels or structural variants (SVs)], and whether the goal is to minimize the number of positions at which variants are listed or to minimize the total number of variants listed. We classify the computational complexity of these problems and provide efficient algorithms along with their software implementation when feasible. We empirically evaluate the magnitude of graph reduction achieved in human chromosome variation graphs using multiple α and δ parameter values corresponding to short and long-read resequencing characteristics. When our algorithm is run with parameter settings amenable to long-read mapping (α = 10 kbp, δ = 1000), 99.99% SNPs and 73% SVs can be safely excluded from human chromosome 1 variation graph. The graph size reduction can benefit downstream pan-genome analysis. AVAILABILITY AND IMPLEMENTATION: : https://github.com/AT-CG/VF. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Medication adherence in patients with hypertension: Does satisfaction with doctor-patient relationship work?

BACKGROUND: It is assumed that doctor-patient relationship plays an effective role in patients' satisfaction, medication adherence, and health outcomes since exploring different aspects of this relationship, such as addressing medication adherence, has rarely been investigated. Therefore, the main aim of the present study was to assess the impact of patients' satisfaction derived from communicating with doctors on medication adherence in hypertensive patients. MATERIALS AND METHODS: This cross-sectional survey was conducted on three hundred patients with hypertension, using multistage sampling technique in health care centers in Isfahan, Iran. Data were collected by two questionnaires comprised (1) patients' satisfaction derived from the relationship with doctors and (2) medication adherence named "Morisky Medication Adherence Scale" with 8 items. Multivariate logistic regression model was applied to test the odds ratio (OR) of patients' satisfaction resulting from the relationship with physicians in numerous aspects in two groups: appropriate and inappropriate medication adherence. RESULTS: A lower level of satisfaction derived from building the relationship (confidence interval [CI] =0.95, 0.06-0.71 and OR = 0.20) and empathy subscales (CI = 0.95, 13-0.80 and OR = 0.33) was associated with nonadherence to treatment after controlling the physicians' gender and patients' age, gender, education, and duration of disease. CONCLUSION: Patients' satisfaction resulting from building the relationship and empathy with physicians appeared to be associated with medication adherence among hypertensive patients.

The transtheoretical model, health belief model, and breast cancer screening among Iranian women with a family history of breast cancer.

BACKGROUND: Participation of Iranian women with a family history of breast cancer in breast cancer screening programs is low. This study evaluates the compliance of women having a family history of breast cancer with clinical breast exam (CBE) according to the stage of transtheoretical model (TTM) and health belief model (HBM). MATERIALS AND METHODS: In this cross-sectional study, we used Persian version of champion's HBM scale to collect factors associated with TTM stages applied to screening from women over 20 years and older. The obtained data were analyzed by SPSS, using descriptive statistics, Chi-square test, independent t-test, and analysis of covariance. RESULTS: Final sample size was 162 women. Thirty-three percent were in action/maintenance stage. Older women, family history of breast cancer in first-degree relatives, personal history of breast disease, insurance coverage, and a history of breast self-examination were associated with action/maintenance stage. Furthermore, women in action/maintenance stages had significantly fewer perceived barriers in terms of CBE in comparison to women in other stages (P < 0.05). There was no significant difference in other HBM subscales scores between various stages of CBE screening behavior (P > 0.05). CONCLUSION: The finding indicates that the rate of women in action/maintenance stage of CBE is low. Moreover, results show a strong association between perceived barriers and having a regular CBE. These clarify the necessity of promoting national target programs for breast cancer screening, which should be considered as the first preference for reducing CBE barriers.

GraphSlimmer: Preserving Read Mappability with the Minimum Number of Variants.

Modern genomic datasets, like those generated under the 1000 Genome Project, contain millions of variants belonging to known haplotypes. Although these datasets are more representative than a single reference sequence and can alleviate issues like reference bias, they are significantly more computationally burdensome to work with, often involving large-indexed genome graph data structures for tasks such as read mapping. The construction, preprocessing, and mapping algorithms can require substantial computational resources depending on the size of these variant sets. Moreover, the accuracy of mapping algorithms has been shown to decrease when working with complete variant sets. Therefore, a drastically reduced set of variants that preserves important properties of the original set is desirable. This work provides a technique for finding a minimal subset of variants S such that for given parameters α and δ, all substrings up to length α in the haplotypes are guaranteed to be still alignable to the appropriate locations with either Hamming or edit distance at most δ, using only S. Our contributions include showing the NP-hardness and inapproximability of these optimization problems and providing Integer Linear Programming (ILP) formulations. Our edit distance ILP formulation carefully decomposes the problem according to variant locations, which allows it to scale to support all of chromosome 22's variants from the 1000 Genome Project. Our experiments also demonstrate a significant reduction in the number of variants. For example, for moderately long reads, e.g., α = 1000, over 75% of the variants can be removed while preserving read mappability with edit distance at most one.

Illness Anxiety Disorder and Its Relationship with Social Health in the Elderly, Isfahan, Iran.

Background: The present study investigated the prevalence of illness anxiety disorder and its relationship with social health in the elderly population. Materials and Methods: This cross-sectional study was conducted on 400 elderly people in Isfahan referred to the educational health service in 2020. In addition to demographic characteristics, they answered the 36-item Evans hypochondriasis questionnaire and the 28-item social health questionnaire. Results: Four hundred elderly participants with a mean age of 68.1 ± 6.6 (range: 60-89) were included in the study. One hundred and ninety-nine (49.8%) were female and 201 (50.3%) were male. Only 24.3% of the geriatrics were in the healthy group and 21.2% in the borderline category. Seventy-two of the geriatric population (18%) had poor social health and 299 of this population (74.8%) had moderate social health, and the social health status of 29 elderlies (7.3%) was favorable. There was an inverse relationship between hypochondriasis score and total social health score and its dimensions (P < 0.05). Conclusion: High prevalence of hypochondriasis was observed in the geriatrics compared to global studies. Most of the elderly population had moderate social health. Gender and education do not affect hypochondriasis and social health in the elderly. People with higher social health scores were clearly less likely to get hypochondriasis. Therefore, by improving the various dimensions of social health of the geriatrics, we can help reduce the prevalence of hypochondriasis in this age group.

Similarity analysis of federal reserve statements using document embeddings: the Great Recession vs. COVID-19.

The coronavirus pandemic has already caused plenty of severe problems for humanity and the economy. The exact impact of the COVID-19 pandemic is still unknown, and economists and financial advisers are exploring all possible scenarios to mitigate the risks arising from the pandemic. An intriguing question is whether this pandemic and its impacts are similar, and to what extent, to any other catastrophic events that occurred in the past, such as the 2009 Great Recession. This paper intends to address this problem by analyzing official public announcements and statements issued by federal authorities such as the Federal Reserve. More specifically, we measure similarities of consecutive statements issued by the Federal Reserve during the 2009 Great Recession and the COVID-19 pandemic using natural language processing techniques. Furthermore, we explore the usage of document embedding representations of the statements in a more complex task: clustering. Our analysis shows that, using an advanced NLP technique in document embedding such as Doc2Vec, we can detect a difference of 10.8% in similarities of Federal Open Market Committee (FOMC) statements issued during the Great Recession (2007-2009) and the COVID-19 pandemic. Finally, the results of our clustering exercise show that the document embeddings representations of the statements are suitable for more complex tasks, which provides a basis for future applications of state-of-the-art natural language processing techniques using the FOMC post-meeting statements as the dataset.

Study of baseline echocardiography and treatment endpoint in patients with acute lymphoblastic leukemia.

INTRODUCTION: Acute lymphoblastic leukemia (ALL) is the most common malignancy in children. Anthracyclines are among the most common and effective drugs for the treatment of children ALL. However, long-term consumption and higher doses of these drugs may lead to toxic effects on the heart of children. For this purpose, in the present study, the baseline and posttreatment echocardiography status was evaluated in children with ALL during 7 years. MATERIALS AND METHODS: This retrospective cross-sectional study was performed on 53 children with ALL who were under the age of 18 years. Different factors including risk groups, age, gender, white blood cells, dosage, and duration of treatment, as well as baseline and posttreatment echocardiography findings including EF, E/E/, E//A/, MVE/A were evaluated in all patients. RESULTS: All enrolled patients had not any abnormalities in the baseline echocardiography preventing the beginning of chemotherapy. The results of this study did not show a significant difference in mean baseline echocardiography parameters after treatment including EF̨E/E/˛E//A/˛, MVE/A. In addition, there was no significant difference in mean EF, E//A/˛, MVE/A, and ˛E/E/ before and after treatment among SR, IR, and HR groups. Although there was no significant difference in the mean EF, E//A/, and MVE/A before and after treatment between male and female sex, the mean E/E/ after chemotherapy in girls (8.5 ± 0.7) was significantly higher than the mean before treatment (6.85 ± 1.5) (P < 0.001). It was also higher than the mean in boys (7.04 ± 0.99) (P = 0.019). Although there was no significant relationship between the duration of chemotherapy and the mean of EF̨E/E/˛E//A/˛, MVE/A after treatment, high dose of the drug was found to be significantly associated with a gradual decrease of EF or systolic function of the heart (P < 0.001). There was no significant relationship between drug dose and other parameters of echocardiography including E/ A/, MVE/A, and E/E/ after treatment. CONCLUSION: It appears that chemotherapy should not be delayed by echocardiography. Based on the findings presented herein, increasing the dose of anthracycline can be considered as an effective factor in reducing the systolic function of the heart (EF reduction). On the other hand, chemotherapy in the period of 1 to 5.3 years does not seem to have a significant effect on the mean parameters of EF, E/E/, E//, and MVE/A although another study with higher sample size and follow-up is needed to confirm these results.