Using artificial intelligence in medical school admissions screening to decrease inter- and intra-observer variability.

Objectives: Inter- and intra-observer variability is a concern for medical school admissions. Artificial intelligence (AI) may present an opportunity to apply a fair standard to all applicants systematically and yet maintain sensitivity to nuances that have been a part of traditional screening methods. Material and Methods: Data from 5 years of medical school applications were retrospectively accrued and analyzed. The applicants (m = 22 258 applicants) were split 60%-20%-20% into a training set (m = 13 354), validation set (m = 4452), and test set (m = 4452). An AI model was trained and evaluated with the ground truth being whether a given applicant was invited for an interview. In addition, a "real-world" evaluation was conducted simultaneously within an admissions cycle to observe how it would perform if utilized. Results: The algorithm had an accuracy of 95% on the training set, 88% on the validation set, and 88% on the test set. The area under the curve of the test set was 0.93. The SHapely Additive exPlanations (SHAP) values demonstrated that the model utilizes features in a concordant manner with current admissions rubrics. By using a combined human and AI evaluation process, the accuracy of the process was demonstrated to be 96% on the "real-world" evaluation with a negative predictive value of 0.97. Discussion and Conclusion: These results demonstrate the feasibility of an AI approach applied to medical school admissions screening decision-making. Model explainability and supplemental analyses help ensure that the model makes decisions as intended.

Comparison of the Multiple Mini-Interview and the Traditional Interview in Medical School Admissions: Lessons Learned Using a Hybrid Model at One Institution.

PURPOSE: Medical school admissions interviews are a critical form of assessment; however, the most effective interview strategy is debated. This study compares the traditional interview (TI) and multiple mini-interview (MMI) within a hybrid TI-MMI model at one medical school to determine whether the interview approaches reveal different information about applicants and whether a hybrid model results in a more diversified applicant pool. METHOD: Admissions data from 3 application cycles at the Donald and Barbara Zucker School of Medicine at Hofstra/Northwell were used. The TI was used in 2017-2018 and the hybrid TI-MMI model in 2018-2019 and 2019-2020. Applicants were scored on a 5-point scale and referred to a voting committee for acceptance consideration if interview scores met threshold criteria. Changes in the number of students referred to the committee using the TI vs the TI-MMI score criteria were analyzed. RESULTS: In 2017-2018 (TI only), 683 applicants were interviewed; in 2018-2019 (TI-MMI), 844 applicants were interviewed; and in 2019-2020 (TI-MMI), 805 applicants were interviewed. Medium correlations were found between total MMI and TI scores in 2018-2019 ( ρ = 0.37, P < .001) and 2019-2020 ( ρ = 0.33, P < .001). No differences were found in TI scores between 2017-2018 and 2018-2019 ( P = .30), but TI scores were significantly lower in 2019-2020 vs 2017-2018 ( P < .001) and 2018-2019 ( P = .002). Overall, a 10% to 18% increase was found in the number of applicants referred to the voting committee when using hybrid criteria, with a 19% to 27% increase in underrepresented in medicine applicants. CONCLUSIONS: The TI-MMI model may allow for a more holistic interview approach and an expanded pool of applicants, particularly underrepresented in medicine applicants, considered for acceptance.

Primary CNS anaplastic diffuse large B-cell lymphoma mimicking undifferentiated metastatic tumors: a case report.

Primary central nervous system lymphoma (PCNSL) is a rare intracranial tumor, with an annual incidence of six per million population. Anaplastic variant of primary CNS diffuse large B-cell lymphoma is less common; to our knowledge, there is only one other case report in the world literature. We describe a 71 year old immunocompetent female without significant past medical history who presented with confusion and a homogeneously enhancing midline mass. The patient underwent craniotomy for tumor biopsy, followed by high-dose methotrexate-based chemotherapy despite a remarkably low performance status. Histologically, this tumor was composed of undifferentiated polymorphic tumor cells, multi-nucleated giant cells, extensive necrosis, and conspicuous mitotic activity, mimicking undifferentiated metastatic tumors. Immunohistochemical stains demonstrated immunopositivity of tumor cells for CD20, MUM-1, and BCL-6, and negative staining for CD3, CD10, and CD30. The clinical course, diagnostic workup, pathologic correlates, and treatment outcomes are described.

Acute syringomyelia: case report.

OBJECTIVE AND IMPORTANCE: Syringomyelia is generally regarded as a chronic, slowly progressive disorder. We describe a case of acute dilation of the central canal of the spinal cord that presented with rapidly progressive segmental signs. CLINICAL PRESENTATION: A 29-year-old female patient who had previously undergone surgical treatment for a Chiari I malformation, syringomyelia, and hydrocephalus presented with an 8-day history of headaches, progressive paraparesis, and urinary retention. Magnetic resonance imaging scans demonstrated panventricular hydrocephalus in association with a holocord syrinx that extended to the obex. Magnetic resonance imaging scans that had been coincidentally obtained just 3 days before the onset of symptoms had revealed no evidence of hydrocephalus or syringomyelia. INTERVENTION: The patient underwent emergency revision of a failed ventriculoperitoneal shunt. Postoperatively, there was prompt resolution of the syringomyelia, hydrocephalus, and associated neurological deficits. CONCLUSION: Among patients with communicating syringomyelia, the central canal of the spinal cord participates as a "fifth ventricle" and can undergo rapid dilation in association with acute hydrocephalus. Appropriate treatment in such cases involves placement of a ventriculoperitoneal shunt.

Endovascular obliteration of a ruptured posterior spinal artery pseudoaneurysm.

Aneurysms of the posterior spinal artery (PSA) are rare lesions. Isolated PSA aneurysms, not in the setting of a high-flow environment, are even more rare. In the few reported cases, these lesions have been predominantly resected or observed. The authors report an isolated pseudoaneurysm of the PSA at the T-11 level presenting with subarachnoid hemorrhage. The patient underwent successful endovascular obliteration. To the authors' knowledge, this is the first report of an endovascular repair of an isolated PSA aneurysm.

Microcystic meningioma presenting as a cystic lesion with an enhancing mural nodule in elderly women: report of three cases.

Cystic meningioma with an enhancing mural nodule is uncommon and can present as a radiologic and clinical dilemma with wide differential. We report a series of rare and unique presentation of microcystic meningioma in three elderly women aged 76 (case 1), 72 (case 2), and 76 (case 3) years, respectively. The first patient presented with a 3-year history of vertigo and past history of carotid artery stenosis, hypertension, and hypothyroidism. The second patient presented with headache and an acute episode of weakness in her legs. The third patient presented with headache, vomiting, and confusion. Magnetic resonance imaging for these three cases showed a cystic lesion with an enhancing mural nodule in the right frontal lobe. The preoperative differential diagnoses included hemangioblastoma and well-circumscribed gliomas for the first two cases. Glioblastoma and metastatic tumor were the working diagnoses for the third case because of vasogenic brain edema and marked mass effect. The final pathological diagnosis was microcystic meningioma for all three cases. Case reports are mainly of fibrous or meningothelial meningiomas with cystic formation. Male predominance and young age are most commonly reported. Our series is unique because of the rare and unusual clinical-radiologic presentation of microcystic meningioma in elderly women.

Identification of diffuse and focal brain lesions by clinical magnetic resonance spectroscopy.

The purpose of this paper is to facilitate the comparison of magnetic resonance (MR) spectra acquired from unknown brain lesions with published spectra in order to help identify unknown lesions in clinical settings. The paper includes lists of references for published MR spectra of various brain diseases, including pyogenic abscesses, encephalitis (herpes simplex, Rasmussen's and subacute sclerosing panencephalitis), neurocysticercosis, tuberculoma, cysts (arachnoid, epidermoid and hydatid), acute disseminated encephalomyelitis (ADEM), adrenoleukodystrophy (ALD), Alexander disease, Canavan's disease, Krabbe disease (globoid cell leukodystrophy), Leigh's disease, megalencephalic leukoencephalopathy with cysts, metachromatic leukodystrophy (MLD), Pelizaeus-Merzbacher disease, Zellweger syndrome, HIV-associated lesions [cryptococcus, lymphoma, toxoplasmosis and progressive multifocal leukoencephalopathy (PML)], hydrocephalus and tuberous sclerosis. Each list includes information on the echo time(s) (TE) of the published spectra, whether a control spectrum is shown, whether the corresponding image and voxel position are shown and the patient ages if known. The references are listed in the approximate order of usefulness, based on spectral quality, number of spectra, range of echo times and whether the voxel positions are shown. Spectra of Zellweger syndrome, cryptococcal infection, toxoplasmosis and lymphoma are included, along with a spectrum showing propanediol (propylene glycol).