The Cases for and against Artificial Intelligence in the Medical School Curriculum.

Although artificial intelligence (AI) has immense potential to shape the future of medicine, its place in undergraduate medical education currently is unclear. Numerous arguments exist both for and against including AI in the medical school curriculum. AI likely will affect all medical specialties, perhaps radiology more so than any other. The purpose of this article is to present a balanced perspective on whether AI should be included officially in the medical school curriculum. After presenting the balanced point-counterpoint arguments, the authors provide a compromise. Keywords: Artificial Intelligence, Medical Education, Medical School Curriculum, Medical Students, Radiology, Use of AI in Education © RSNA, 2022.

Novel System of Simulation Models for Aneurysm Clipping Training: Description of Models and Assessment of Face, Content, and Construct Validity.

BACKGROUND: Aneurysm clipping simulation models are needed to provide tactile feedback of biological vessels in a nonhazardous but surgically relevant environment. OBJECTIVE: To describe a novel system of simulation models for aneurysm clipping training and assess its validity. METHODS: Craniotomy models were fabricated to mimic actual tissues and movement restrictions experienced during actual surgery. Turkey wing vessels were used to create aneurysm models with patient-specific geometry. Three simulation models (middle cerebral artery aneurysm clipping via a pterional approach, anterior cerebral artery aneurysm clipping via an interhemispheric approach, and basilar artery aneurysm clipping via an orbitozygomatic pretemporal approach) were subjected to face, content, and construct validity assessments by experienced neurosurgeons (n = 8) and neurosurgery trainees (n = 8). RESULTS: Most participants scored the model as replicating actual aneurysm clipping well and scored the difficulty of clipping as being comparable to that of real surgery, confirming face validity. Most participants responded that the model could improve clip-applier-handling skills when working with patients, which confirms content validity. Experienced neurosurgeons performed significantly better than trainees on all 3 models based on subjective (P = .003) and objective (P < .01) ratings and on time to complete the task (P = .04), which confirms construct validity. Simulations were used to discuss clip application strategies and compare them to prototype clinical cases. CONCLUSION: This novel aneurysm clipping model can be used safely outside the wet laboratory; it has high face, content, and construct validity; and it can be an effective training tool for microneurosurgery training during aneurysm surgery courses.

Delays in presentation and mortality among Black patients with mechanical thrombectomy after large-vessel stroke at a US hospital.

OBJECTIVE: The incidence and severity of stroke are disproportionately greater among Black patients. In this study, the authors sought to examine clinical outcomes among Black versus White patients after mechanical thrombectomy for stroke at a single US institution. METHODS: All patients who underwent mechanical thrombectomy at a single center from January 1, 2014, through March 31, 2020, were retrospectively analyzed. Patients were grouped based on race, and demographic characteristics, preexisting conditions, clinical presentation, treatment, and stroke outcomes were compared. The association of race with mortality was analyzed in multivariable logistic regression analysis adjusted for potential confounders. RESULTS: In total, 401 patients (233 males) with a reported race of Black (n = 28) or White (n = 373) underwent mechanical thrombectomy during the study period. Tobacco use was more prevalent among Black patients (43% vs 24%, p = 0.04), but there were no significant differences between the groups with respect to insurance, coronary artery disease, diabetes, illicit drug use, hypertension, or hyperlipidemia. The mean time from stroke onset to hospital presentation was significantly greater among Black patients (604.6 vs 333.4 minutes) (p = 0.007). There were no differences in fluoroscopy time, procedural success (Thrombolysis in Cerebral Infarction grade 2b or 3), hospital length of stay, or prevalence of hemicraniectomy. In multivariable analysis, Black race was strongly associated with higher mortality (32.1% vs 14.5%, p = 0.01). The disparity in mortality rates resolved after adjusting for the average time from stroke onset to presentation (p = 0.14). CONCLUSIONS: Black race was associated with an increased risk of death after mechanical thrombectomy for stroke. The increased risk may be associated with access-related factors, including delayed presentation to stroke centers.

Visualization of brain microvasculature and blood flow in vivo: Feasibility study using confocal laser endomicroscopy.

OBJECTIVE: Qualitative and quantitative analyses of blood flow in normal and pathologic brain and spinal cord microvasculature were performed using confocal laser endomicroscopy (CLE). METHODS: Blood flow in cortical, dural, and spinal cord microvasculature was assessed in vivo in swine. We assessed microvasculature under normal conditions and after vessel occlusion, brain injury due to cold or surgical trauma, and cardiac arrest. Tumor-associated microvasculature was assessed in vivo and ex vivo in 20 patients with gliomas. RESULTS: We observed erythrocyte flow in vessels 5-500 µm in diameter. Thrombosis, flow arrest and redistribution, flow velocity changes, agglutination, and cells rolling were assessed in normal and injured brain tissue. Microvasculature in in vivo CLE images of gliomas was classified as normal in 68% and abnormal in 32% of vessels on the basis of morphological appearance. Dural lymphatic channels were discriminated from blood vessels. Microvasculature CLE imaging was possible for up to 30 minutes after a 1 mg/kg intravenous dose of fluorescein. CONCLUSIONS: CLE imaging allows assessment of cerebral and tumor microvasculature and blood flow alterations with subcellular resolution intraoperative imaging demonstrating precise details of real-time cell movements. Research and clinical scenarios may benefit from this novel intraoperative in vivo microscopic fluorescence imaging modality.

AI in the Intensive Care Unit: Up-to-Date Review.

AI is the latest technologic trend that likely will have a huge impact in medicine. AI's potential lies in its ability to process large volumes of data and perform complex pattern analyses. The ICU is an area of medicine that is particularly conducive to AI applications. Much AI ICU research currently is focused on improving high volumes of data on high-risk patients and making clinical workflow more efficient. Emerging topics of AI medicine in the ICU include AI sensors, sepsis prediction, AI in the NICU or SICU, and the legal role of AI in medicine. This review will cover the current applications of AI medicine in the ICU, potential pitfalls, and other AI medicine-related topics relevant for the ICU.

Artificial Intelligence: Has Its Time Come for Inclusion in Medical School Education? Maybe Maybe Not.

This article was migrated. The article was marked as recommended. Artificial intelligence (AI) has the potential to strongly modify or even transform the landscape of medicine. Judicious utilization of AI can further propel progress in medical research, facilitate precision medicine, and optimize clinical workflow-the applications are limitless. Although technology and AI algorithms are evolving rapidly and have important implications for future physicians, there is a dearth of literature available for medical students and their educators to learn about AI. While scientific journals provide information regarding AI, they often are written for and by scientists, engineers, and physicians who are well-versed in technology. Currently, medical students must navigate the technical jargon and decipher AI literature without any foundational exposure. It is difficult for students to understand the implications of AI if they do not have basic knowledge of AI and its current capabilities. A fear about AI is pervasive amongst medical students. There is virtually no literature that provides a fundamental and easily digestible overview of AI for medical students and educators, while also offering suggestions about how to integrate AI into medical school curricula. Our goal is to address the lack of formal AI instruction by presenting an informative primer with curricular suggestions for each medical school year, from a U.S. perspective, tailored to medical students and their educators. We seek to present a balanced approach, as there are pros and cons about incorporating AI in undergraduate medical education.

Intraoperative Confocal Laser Endomicroscopy Ex Vivo Examination of Tissue Microstructure During Fluorescence-Guided Brain Tumor Surgery.

BACKGROUND: Noninvasive intraoperative optical biopsy that provides real-time imaging of histoarchitectural (cell resolution) features of brain tumors, especially at the margin of invasive tumors, would be of great value. To assess clinical-grade confocal laser endomicroscopy (CLE) and to prepare for its use intraoperatively in vivo, we performed an assessment of CLE ex vivo imaging in brain lesions. METHODS: Tissue samples from patients who underwent intracranial surgeries with fluorescein sodium (FNa)-based wide-field fluorescence guidance were acquired for immediate intraoperative ex vivo optical biopsies with CLE. Hematoxylin-eosin-stained frozen section analysis of the same specimens served as the gold standard for blinded neuropathology comparison. FNa 2 to 5 mg/kg was administered upon induction of anesthesia, and FNa 5 mg/kg was injected for CLE contrast improvement. Histologic features were identified, and the diagnostic accuracy of CLE was assessed. RESULTS: Of 77 eligible patients, 47 patients with 122 biopsies were enrolled, including 32 patients with gliomas and 15 patients with other intracranial lesions. The positive predictive value of CLE optical biopsies was 97% for all specimens and 98% for gliomas. The specificity of CLE was 90% for all specimens and 94% for gliomas. The second FNa injection in seven patients, a mean of 2.6 h after the first injection, improved image quality and increased the percentage of accurately diagnosed images from 67% to 93%. Diagnostic CLE features of lesional glioma biopsies and normal brain were identified. Seventeen histologic features were identified. CONCLUSIONS: Results demonstrated high specificity and positive predictive value of ex vivo intraoperative CLE optical biopsies and justify an in vivo intraoperative trial. This new portable, noninvasive intraoperative imaging technique provides diagnostic features to discriminate lesional tissue with high specificity and is feasible for incorporation into the fluorescence-guided surgery workflow, particularly for patients with invasive brain tumors.

Confocal Laser Endomicroscopy Assessment of Pituitary Tumor Microstructure: A Feasibility Study.

This is the first study to assess confocal laser endomicroscopy (CLE) use within the transsphenoidal approach and show the feasibility of obtaining digital diagnostic biopsies of pituitary tumor tissue after intravenous fluorescein injection. We confirmed that the CLE probe reaches the tuberculum sellae through the transnasal transsphenoidal corridor in cadaveric heads. Next, we confirmed that CLE provides images with identifiable histological features of pituitary adenoma. Biopsies from nine patients who underwent pituitary adenoma surgery were imaged ex vivo at various times after fluorescein injection and were assessed by a blinded board-certified neuropathologist. With frozen sections used as the standard, pituitary adenoma was diagnosed as "definitively" for 13 and as "favoring" in 3 of 16 specimens. CLE digital biopsies were diagnostic for pituitary adenoma in 10 of 16 specimens. The reasons for nondiagnostic CLE images were biopsy acquisition <1 min or >10 min after fluorescein injection (n = 5) and blood artifacts (n = 1). In conclusion, fluorescein provided sufficient contrast for CLE at a dose of 2 mg/kg, optimally 1-10 min after injection. These results provide a basis for further in vivo studies using CLE in transsphenoidal surgery.

Leukaemia hijacks a neural mechanism to invade the central nervous system.

Acute lymphoblastic leukaemia (ALL) has a marked propensity to metastasize to the central nervous system (CNS). In contrast to brain metastases from solid tumours, metastases of ALL seldom involve the parenchyma but are isolated to the leptomeninges, which is an infrequent site for carcinomatous invasion. Although metastasis to the CNS occurs across all subtypes of ALL, a unifying mechanism for invasion has not yet been determined. Here we show that ALL cells in the circulation are unable to breach the blood-brain barrier in mice; instead, they migrate into the CNS along vessels that pass directly between vertebral or calvarial bone marrow and the subarachnoid space. The basement membrane of these bridging vessels is enriched in laminin, which is known to coordinate pathfinding of neuronal progenitor cells in the CNS. The laminin receptor α6 integrin is expressed in most cases of ALL. We found that α6 integrin-laminin interactions mediated the migration of ALL cells towards the cerebrospinal fluid in vitro. Mice with ALL xenografts were treated with either a PI3Kδ inhibitor, which decreased α6 integrin expression on ALL cells, or specific α6 integrin-neutralizing antibodies and showed significant reductions in ALL transit along bridging vessels, blast counts in the cerebrospinal fluid and CNS disease symptoms despite minimally decreased bone marrow disease burden. Our data suggest that α6 integrin expression, which is common in ALL, allows cells to use neural migratory pathways to invade the CNS.