Medical students' AI literacy and attitudes towards AI: a cross-sectional two-center study using pre-validated assessment instruments.

BACKGROUND: Artificial intelligence (AI) is becoming increasingly important in healthcare. It is therefore crucial that today's medical students have certain basic AI skills that enable them to use AI applications successfully. These basic skills are often referred to as "AI literacy". Previous research projects that aimed to investigate medical students' AI literacy and attitudes towards AI have not used reliable and validated assessment instruments. METHODS: We used two validated self-assessment scales to measure AI literacy (31 Likert-type items) and attitudes towards AI (5 Likert-type items) at two German medical schools. The scales were distributed to the medical students through an online questionnaire. The final sample consisted of a total of 377 medical students. We conducted a confirmatory factor analysis and calculated the internal consistency of the scales to check whether the scales were sufficiently reliable to be used in our sample. In addition, we calculated t-tests to determine group differences and Pearson's and Kendall's correlation coefficients to examine associations between individual variables. RESULTS: The model fit and internal consistency of the scales were satisfactory. Within the concept of AI literacy, we found that medical students at both medical schools rated their technical understanding of AI significantly lower (MMS1 = 2.85 and MMS2 = 2.50) than their ability to critically appraise (MMS1 = 4.99 and MMS2 = 4.83) or practically use AI (MMS1 = 4.52 and MMS2 = 4.32), which reveals a discrepancy of skills. In addition, female medical students rated their overall AI literacy significantly lower than male medical students, t(217.96) = -3.65, p <.001. Students in both samples seemed to be more accepting of AI than fearful of the technology, t(745.42) = 11.72, p <.001. Furthermore, we discovered a strong positive correlation between AI literacy and positive attitudes towards AI and a weak negative correlation between AI literacy and negative attitudes. Finally, we found that prior AI education and interest in AI is positively correlated with medical students' AI literacy. CONCLUSIONS: Courses to increase the AI literacy of medical students should focus more on technical aspects. There also appears to be a correlation between AI literacy and attitudes towards AI, which should be considered when planning AI courses.

How to improve initial diagnostic accuracy of kidney tumours in childhood?-A non-invasive approach.

Non-invasive differentiation of paediatric kidney tumours is particularly important in the SIOP-RTSG protocols, which recommend pre-operative chemotherapy without histological confirmation. The identification of clinical and tumour-related parameters may enhance diagnostic accuracy. Age, metastases, and tumour volume (TV) were retrospectively analysed in 3306 patients enrolled in SIOP/GPOH 9, 93-01, and 2001 including Wilms tumour (WT), congenital mesoblastic nephroma (CMN), clear cell sarcoma (CCSK), malignant rhabdoid tumour of the kidney (MRTK), and renal cell carcinoma (RCC). WT was diagnosed in 2927 (88.5%) patients followed by CMN 138 (4.2%), CCSK 126 (3.8%), MRTK 58 (1.8%) and RCC 57 (1.7%). CMN, the most common localized tumour (71.6%) in patients younger than 3 months of age, was diagnosed earliest and RCC the latest (median age [months]: 0 and 154, respectively) both associated with significantly smaller TV (median TV [mL]: 67.2 and 45.0, respectively). RCC occurred in >14% of patients older than 120 months or older than 84 months with TV <100 mL. Receiver operating characteristic analyses discriminated WT from CMN, RCC and MRTK regarding age (AUC = 0.976, 0.929 and 0.791) and TV (AUC = 0.768, 0.813 and 0.622). MRTK had the highest risk of metastasis (37.9%) despite young age, whereas the risk of metastasis increased significantly with age in WT. Age and TV at diagnosis can differentiate WT from CMN and RCC. MRTK must be considered for metastatic tumours at young age. Identification of CCSK without histology remains challenging. Combined with MRI-characteristics, including diffusion-weighted imaging, and radiomics and liquid biopsies in the future, our approach allows optimization of biopsy recommendations and prevention of misdiagnosis-based neoadjuvant treatment.

An Observational Case-Control Study on Parental Age and Childhood Renal Tumors.

Despite excellent outcomes, many open questions remain about Wilms tumor (WT). Influences and risk factors for tumorigenesis, as well as tumor aggressiveness and recurrence, are not fully understood. Parental age plays a role in various childhood diseases and is also discussed as a risk factor for childhood cancer. We analyzed both maternal and paternal age at birth as risk factors for the occurrence of Wilms and non-Wilms tumors in children and investigated whether older maternal or paternal age is associated with a higher tumor incidence. During 1990 and 2019 we collected data from 3991 patients from the multicenter studies SIOP9/GPO, SIOP 93-01/GPOH, and SIOP 2001/GPOH, of whom maternal and paternal age was available in 2277 cases. Data from the Federal Statistical Office containing live births in Germany from 1990-2019 served as a comparative database. For maternal age at birth, the control data yielded 22,451,412 cases and for paternal age yielded 19,046,314 cases. Comparing maternal and paternal ages of the study patients with those of the control data, we confirmed that higher parental age is not correlated with the incidence of renal tumors in childhood. Mean ages of fathers and mothers in patients and the control cohort increased between 1991 and 2019 (fathers: 30.28 vs. 34.04; mothers: 27.68 vs. 29.79 in the patient group and 31.29 vs. 34.23 and 28.88 vs. 32.67 in the control group, respectively) without higher numbers of patients with kidney cancer over time. No influence was found for the subtype of cancer nor for syndromes. In addition, overall survival of patients is independent of the year of diagnosis and the age of the parents but depends on histology type and stage in WT.

Reviewing the current state of virtual reality integration in medical education - a scoping review protocol.

BACKGROUND: Due to an increasing focus of medical curricula on clinical decision-making skills, new learning tools are constantly developed. Virtual reality (VR) is one of the emerging technologies with the potential to improve health professionals' education. Highly realistic learning experiences with repeatable training scenarios can be created within a protected environment that is independent from real patients' presence. Our project "medical tr.AI.ning" is following this approach aiming to simulate immersive virtual first-person scenarios with intelligent, interactable virtual patients. So far, VR has been mainly used in surgical training, but there is evidence for effectiveness in training different procedural skills, such as cardiopulmonary resuscitation, knowledge acquisition, and improvement of reasoning and creativity, while still being cost-effective. The objective of this scoping review is to explore the usage and identify key areas of VR applications in the field of medical education. Furthermore, the corresponding requirements, evaluation methods and outcomes, advantages, and disadvantages will be covered. METHODS: This scoping review protocol implements the updated JBI Scoping Review Methodology. In March 2022, a preliminary literature research in PubMed was performed by two independent reviewers to refine search terms and strategy as well as inclusion criteria of the protocol, accounting for actuality and scientific relevance. The final search will be conducted using PubMed, ScienceDirect, Cochrane Library, Web of Science Core Collection, and JBI Evidence Synthesis. Search, study screening, and data extraction will be done in parallel and independently by two reviewers. Discrepancies will be handled by consensus or consulting a third review author. DISCUSSION: With this scoping review, we anticipate collating the range of application of VR in medical education while using a transparent and reproducible search strategy. This may contribute to the design and development of novel educational VR platforms and their integration into medical curricula while pointing out previous omissions and pitfalls.

Immersive training of clinical decision making with AI driven virtual patients - a new VR platform called medical tr.AI.ning.

Background: Medical students need to be prepared for various situations in clinical decision-making that cannot be systematically trained with real patients without risking their health or integrity. To target system-related limitations of actor-based training, digital learning methods are increasingly used in medical education, with virtual reality (VR)- training seeming to have high potential. Virtually generated training scenarios allow repetitive training of highly relevant clinical skills within a protected, realistic learning environment. Thanks to Artificial Intelligence (AI), face-to-face interaction with virtual agents is feasible. Combining this technology with VR-simulations offers a new way of situated context-based, first-person training for medical students. Project goal and method: The authors' aim is to develop a modular digital training platform for medical education with virtual, interactable agents and to integrate this platform into the medical curriculum. The medical tr.AI.ning platform will provide veridical simulation of clinical scenarios with virtual patients, augmented with highly realistic medical pathologies within a customizable, realistic situational context. Medical tr.AI.ning is scaled to four complementary developmental steps with different scenarios that can be used separately and so each outcome can successively be integrated early within the project. Every step has its own focus (visual, movement, communication, combination) and extends an author toolbox through its modularity. The modules of each step will be specified and designed together with medical didactics experts. Perspective: To ensure constant improvement of user experience, realism, and medical validity, the authors will perform regular iterative evaluation rounds.Furthermore, integration of medical tr.AI.ning into the medical curriculum will enable long-term and large-scale detection of benefits and limitations of this approach, providing enhanced alternative teaching paradigms for VR technology.

Impact of Time to Surgery on Outcome in Wilms Tumor Treated with Preoperative Chemotherapy.

(1) Background: Wilms tumor (WT) treated preoperatively is cured in over 90% of cases. However, how long preoperative chemotherapy can be given is unknown. (2) Methods: 2561/3030 patients with WT (age < 18 years) treated between 1989 and 2022 according to SIOP-9/GPOH, SIOP-93-01/GPOH, and SIOP-2001/GPOH are retrospectively analyzed to assess the risk of time to surgery (TTS) for relapse-free survival (RFS) and overall survival (OS). (3) Results: TTS was calculated for all surgeries, with the mean being 39 days (38.5 ± 12.5) for unilateral tumors (UWT) and 70 days (69.9 ± 32.7) for bilateral disease (BWT). Relapse occurred in 347 patients, of which 63 (2.5%) were local, 199 (7.8%) were metastatic, and 85 (3.3%) were combined. Moreover, 184 patients (7.2%) died, 152 (5.9%) due to tumor progression. In UWT, recurrences and mortality are independent of TTS. For BWT without metastases at diagnosis, the incidence of recurrence is less than 18% up to 120 days and increases to 29% after 120 days, and to 60% after 150 days. The risk of relapse (Hazard Ratio) adjusted for age, local stage, and histological risk group increases to 2.87 after 120 days (CI 1.19-7.95, p = 0.022) and to 4.62 after 150 days (CI 1.17-18.26, p = 0.029). In metastatic BWT, no influence of TTS is detected. (4) Conclusions: The length of preoperative chemotherapy has no negative impact on RFS or OS in UWT. In BWT without metastatic disease, surgery should be performed before day 120, as the risk of recurrence increases significantly thereafter.

Cranial MRI in Childhood Acute Leukemia during Treatment and Follow-Up Including the Impact of Intrathecal MTX-A Single-Center Study and Review of the Literature.

Due to high survival rates, long-term sequelae, especially neurotoxicity, need to be considered in childhood acute leukemias. In this retrospective analysis of morphologic changes of the brain in children treated for acute leukemias, we included 94 patients (77 ALL, 17 AML; 51 male, 43 female; median age: 5 years) from a single center. We analyzed 170 cranial MRI scans (T2, FLAIR axial) for morphologic alterations of the brain and variations of the ventricular width (GDAH). In addition, the corresponding literature was reviewed. More than 50% of all patients showed cerebral pathomorphologies (CP). They were seen more often in children with ALL (55.8%), ≤ 6 years of age (60.8%), in relapse (58.8%) or after CNS irradiation (75.0%) and included white matter changes, brain atrophy, sinus vein thrombosis and ischemic events. GDAH significantly enlarged mainly in children up to 6 years, with relapse, high-risk leukemias or ALL patients. However, GDAH can normalize again. The number of intrathecal Methotrexate applications (≤12 vs. >12) showed no correlation to morphologic alterations besides a significant increase in GDAH (−0.3 vs. 0.9 mm) between the first and last follow-up MRI in ALL patients receiving >12 ith. MTX applications. The role of ith. MTX on CP needs to be further investigated and correlated to the neurocognitive outcome of children with acute leukemias.