Cancer is associated with significant morbimortality globally. Advances in screening, diagnosis, management and survivorship were substantial in the last decades, however, challenges in providing personalized and data-oriented care remain. Artificial intelligence (AI), a branch of computer science used for predictions and automation, has emerged as potential solution to improve the healthcare journey and to promote precision in healthcare. AI applications in oncology include, but are not limited to, optimization of cancer research, improvement of clinical practice (eg., prediction of the association of multiple parameters and outcomes – prognosis and response) and better understanding of tumor molecular biology. In this review, we examine the current state of AI in oncology, including fundamentals, current applications, limitations and future perspectives.
The aim of our study was to investigate whether there has been a reduction in patient admission to a high-complexity cancer care center in Brasil during the COVID-19 pandemic, similar to what was reported in Europe. METHODS: We reviewed the cancer tracking database of the largest cancer center in southern Brasil and performed statistical tests to compare first-time appointments from the onset of the outbreak until the end of June to those of the equivalent period in 2019. RESULTS: We observed a dramatic reduction (-42%) in first-time appointments during the pandemic compared to the same period in the previous year (P <0.001). This reduction was observed among all medical specialties (P <0.001). CONCLUSION: The onset of COVID-19 was correlated with a reduction in admission to a high-complexity cancer care center in Brasil. Since a delay in diagnosis and treatment may influence prognosis, it is important that cancer centers and public health strategies reinforce care for non-COVID-19 patients to prevent potentially unnecessary deaths.
Background Emerging artificial intelligence (AI) technologies have diverse applications in medicine. As AI tools advance towards clinical implementation, skills in how to use and interpret AI in a healthcare setting could become integral for physicians. This study examines undergraduate medical students’ perceptions of AI, educational opportunities about of AI in medicine, and the desired medium for AI curriculum delivery. Methods A 32 question survey for undergraduate medical students was distributed from May–October 2021 to students to all 17 Canadian medical schools. The survey assessed the currently available learning opportunities about AI, the perceived need for learning opportunities about AI, and barriers to educating about AI in medicine. Interviews were conducted with participants to provide narrative context to survey responses. Likert scale survey questions were scored from 1 (disagree) to 5 (agree). Interview transcripts were analyzed using qualitative thematic analysis. Results We received 486 responses from 17 of 17 medical schools (roughly 5% of Canadian undergraduate medical students). The mean age of respondents was 25.34, with 45% being in their first year of medical school, 27% in their 2nd year, 15% in their 3rd year, and 10% in their 4th year. Respondents agreed that AI applications in medicine would become common in the future (94% agree) and would improve medicine (84% agree Further, respondents agreed that they would need to use and understand AI during their medical careers (73% agree; 68% agree), and that AI should be formally taught in medical education (67% agree). In contrast, a significant number of participants indicated that they did not have any formal educational opportunities about AI (85% disagree) and that AI-related learning opportunities were inadequate (74% disagree). Interviews with 18 students were conducted. Emerging themes from the interviews were a lack of formal education opportunities and non-AI content taking priority in the curriculum. Conclusion A lack of educational opportunities about AI in medicine were identified across Canada in the participating students. As AI tools are currently progressing towards clinical implementation and there is currently a lack of educational opportunities about AI in medicine, AI should be considered for inclusion in formal medical curriculum.
Cardiac impalement is a rare and usually fatal injury. Immediate recognition and surgical intervention are decisive factors for patient survival. This is a reported case of cardiac impalement with left ventricular transfixation, whose prehospital management, surgical treatment and postoperative care were successful.
Emerging artificial intelligence (AI) technologies have diverse applications in medicine. As AI tools advance towards clinical implementation, skills in how to use and interpret AI in a healthcare setting could become integral for physicians. We deployed a 56 question survey to all 17 Canadian medical schools that assessed currently available learning opportunities about AI, the perceived need for AI education, and barriers to educating about AI among undergraduate medical students. Additionally, interviews were conducted with participants to provide narrative context, and analyzed using thematic analysis. The authors received 475 responses from students at 17 of 17 Canadian medical schools. Likert scale survey questions were scored from 1 (disagree) to 5 (agree). Respondents agreed that AI applications in medicine would become common in the future (3.80 ± 0.38) and would improve medicine (3.71 ± 0.54). Further, respondents agreed that they would need to use and understand AI during their medical careers (3.76 ± 0.572; 3.43 ± 0.773), and that AI should be formally taught in medical education (3.43 ± 0.756). In contrast, a significant number of participants indicated that they did not have any formal educational opportunities about AI (1.76 ± 785) and that AI-related learning opportunities were inadequate (2.12 ± 0.802). Interviews with 18 students were conducted, with emerging themes including a lack of formal education opportunities and logistical challenges in adding AI to curriculum. Given that medical students overwhelmingly belief that AI is important to the future of medicine, and the progression of AI tools towards clinical implementation, AI should be considered for inclusion in formal medical curriculum.
Introduction: Breast cancer is the most frequent cancer among women in Brazil and worldwide, with the exception of nonmelanoma skin tumors. The nipple-areola complex (NAC)-sparing mastectomy was developed with the aim of improving aesthetic results and psychological impact on patients. The oncological safety of this technique has been well established in early-stage tumors and risk-reducing surgery; however, it is still uncertain in patients undergoing neoadjuvant chemotherapy who are often at a higher risk for relapse. Objectives: This study aims to analyze the oncologic outcome in a retrospective cohort of patients that were submitted to mastectomy with preservation of the NAC after neoadjuvant chemotherapy for breast cancer treatment, and to correlate clinicopathological and magnetic resonance (MRI) variables to NAC local relapse. Methods: All the patients who were submitted to nipple-sparing mastectomy after neoadjuvant chemotherapy at the Centro de Doenças de Mama de Curitiba, in the period from January 1, 2012, to December 31, 2019, for breast cancer curative treatment were selected. Patients who had incomplete data in their medical records or who were lost to follow-up were excluded. Local and systemic recurrence rates and clinicopathological and MRI variables associated with the oncological outcome were analyzed. To evaluate factors associated with the incidence of recurrence, the Fine and Gray models were adjusted, considering death as a competitive risk. The estimated association measure was the subdistribution hazard ratio (SHR), for which the 95% confidence interval was presented. After adjusting the models, the significance of each variable was analyzed using the Wald test. Values of p <0.05 indicated statistical significance. Results: In all, 134 patients were included, with a mean age of 42.3±10.1 (23–68) years in an average follow-up time of 44.5 (4.2–148) months. The locoregional recurrence rate in the sample was 9.7% (13 cases) in a median time of 17.8 (4.5–40) months; in 5 of these 13 cases, the local relapse involved the nipple-areolar complex corresponding to 3.7% of the sample in a median time of 24.2 (11.7–40.1) months. The systemic recurrence rate was 11.9% (16 cases) in a median time of 20.9 (2.7–130) months. There were 12 deaths (9%) in this sample, in a median follow-up time of 37.8 (4.6–98.4) months. Stage 3 tumors (p=0.016, SHR) and Ki67 index (p=0.004) were significantly associated with local and/or systemic recurrence risk. There was found no association between the NAC recurrence and multicentricity/multifocality presentation (p=0.716; SHR 1.39, 95%CI 0.23–8.30), tumor size on prechemotherapy MRI (p=0.934; SHR 1.00, 95%CI 0.96–1.05), or the distance from the tumor to the NAC on pre (p=0.866; SHR 0.99, 95%CI 0.92–1.08) or pos chemotherapy MRI (p=0.205; SHR 1.03, 95%CI 0.98–1.09). Adjuvant radiotherapy was also a nonsignificant factor. When analyzing immunohistochemical parameters, the Ki67 index was the only variable that was correlated (p=0.018; SHR 1.04, 95%CI 1.01–1.08) to the locoregional failure in the NAC. Conclusion: Locoregional relapse rate in NAC was within acceptable limits for performing nipple-sparing mastectomy in patients submitted to neoadjuvant chemotherapy in this sample. More studies are needed to confirm the safety of this technique, especially in the stage 3 subgroup of patients.
e13587 Background: The use of artificial intelligence (AI) and machine learning is becoming more common and is expected to expand further in order to meet the needs of our ever-evolving healthcare system. In oncology, AI and machine learning are already being explored in various applications. Despite AI’s importance, there is sparse formal teaching on AI incorporated into medical schools’ curricula and residency training programs. In this study, we examined the perceptions and knowledge of Canadian oncology residents and fellows with respect to AI technologies. Methods: An electronic, anonymous, questionnaire-based survey was distributed to residents and fellows in medical and radiation oncology programs across Canada. Survey questions spanned areas of demographics, familiarity with AI, personal attitudes towards AI, and perspectives regarding AI use in different specialties. Approval was obtained from the Queen’s Research Ethics Board prior to conducting this study. Mixed-methods statistical analysis is ongoing. Qualitative data will be analyzed using thematic analysis. Univariable and multivariable regressions will be conducted to identify any correlation between perception or knowledge of AI and demographic factors. Results: Fifty-seven participants responded in total. Most residents (67%) agreed or strongly agreed that it was important they learn about AI. Seventy percent indicated that, if given the chance, they would like to learn more about AI, yet the majority of participants (88%) indicated they had not received formalized teaching. Disciplines that were felt to be most associated with AI were radiology (98%), radiation oncology (84%), and pathology (58%). With respect to the field of radiation oncology, 98% of respondents felt that AI had the potential to replace some, most, or all medical activities. A perceived barrier to understanding AI was a lack of knowledge of mathematics and programming (63%). Respondents indicated that their preferred formats for learning about AI would be workshops (78%), lectures (60%), and collaborative activities with other departments (46%). Conclusions: Our results show that Canadian oncology residents’ sense that AI is important and relevant to their area of training. Despite this, they have not received education on these topics. Thus, formalized teaching, such as lectures and workshops, would be perceived as beneficial by most Canadian oncology residents.
e13583 Background: Emerging artificial intelligence (AI) technologies have diverse applications in medicine, with early evidence suggesting that AI tools can accurately perform key tasks in oncology. As AI tools advance towards clinical implementation, skills in how to use and interpret AI in a healthcare setting could become integral for physicians. This study seeks to assess exposure to AI in medical education among trainees interested in pursuing a career in oncology, and the need for AI education in medicine. Methods: A 32 question survey for Canadian undergraduate medical students was distributed to students at all 17 Canadian medical schools. The survey assessed the currently available and perceived need for learning opportunities about AI and barriers to educating about AI in medicine. Interviews were conducted with participants to provide narrative context to survey responses. Likert scale (LS) survey questions were scored from 1 (disagree) to 5 (agree), and analyzed using a two-sided one sample t-test vs a neutral value. Interview transcripts were analyzed using qualitative thematic analysis. Results are described as mean LS score ± standard deviation. Results: We received 486 responses from 17 of 17 medical schools. Of these respondents, 98 (20.2%) are willing to pursue a residency in an oncology-related field (pathology, radiology, general surgery, internal medicine, radiation oncology). Respondents agreed that AI applications in medicine would become common in the future (3.80±0.38) and would improve medicine (3.71±0.54). Further, respondents agreed that they would need to use and understand AI during their medical careers (3.76±0.572; 3.43±0.773), and that AI should be formally taught in medical education (3.43±0.756). In contrast, a significant number of participants indicated that they did not have any formal educational opportunities about AI (1.76±0.785) and that AI-related learning opportunities were inadequate (2.12±0.802). Interviews with 18 students were conducted. Emerging themes from the interviews were a lack of formal education opportunities and logistical challenges in adding AI to curriculum. Conclusions: A lack of educational opportunities about AI in medicine were identified across Canadian medical students. Given that medical students overwhelmingly believe that AI is important to the future of medicine, and AI tools are currently progressing towards clinical implementation, AI should be considered for inclusion in formal medical curriculum.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.