Citations

ImportanceAutoimmune encephalitis misdiagnosis can lead to harm.ObjectiveTo determine the diseases misdiagnosed as autoimmune encephalitis and potential reasons for misdiagnosis.Design, Setting, and ParticipantsThis retrospective multicenter study took place from January 1, 2014, to December 31, 2020, at autoimmune encephalitis subspecialty outpatient clinics including Mayo Clinic (n = 44), University of Oxford (n = 18), University of Texas Southwestern (n = 18), University of California, San Francisco (n = 17), Washington University in St Louis (n = 6), and University of Utah (n = 4). Inclusion criteria were adults (age ≥18 years) with a prior autoimmune encephalitis diagnosis at a participating center or other medical facility and a subsequent alternative diagnosis at a participating center. A total of 393 patients were referred with an autoimmune encephalitis diagnosis, and of those, 286 patients with true autoimmune encephalitis were excluded.Main Outcomes and MeasuresData were collected on clinical features, investigations, fulfillment of autoimmune encephalitis criteria, alternative diagnoses, potential contributors to misdiagnosis, and immunotherapy adverse reactions.ResultsA total of 107 patients were misdiagnosed with autoimmune encephalitis, and 77 (72%) did not fulfill diagnostic criteria for autoimmune encephalitis. The median (IQR) age was 48 (35.5-60.5) years and 65 (61%) were female. Correct diagnoses included functional neurologic disorder (27 [25%]), neurodegenerative disease (22 [20.5%]), primary psychiatric disease (19 [18%]), cognitive deficits from comorbidities (11 [10%]), cerebral neoplasm (10 [9.5%]), and other (18 [17%]). Onset was acute/subacute in 56 (52%) or insidious (>3 months) in 51 (48%). Magnetic resonance imaging of the brain was suggestive of encephalitis in 19 of 104 patients (18%) and cerebrospinal fluid (CSF) pleocytosis occurred in 16 of 84 patients (19%). Thyroid peroxidase antibodies were elevated in 24 of 62 patients (39%). Positive neural autoantibodies were more frequent in serum than CSF (48 of 105 [46%] vs 7 of 91 [8%]) and included 1 or more of GAD65 (n = 14), voltage-gated potassium channel complex (LGI1 and CASPR2 negative) (n = 10), N-methyl-d-aspartate receptor by cell-based assay only (n = 10; 6 negative in CSF), and other (n = 18). Adverse reactions from immunotherapies occurred in 17 of 84 patients (20%). Potential contributors to misdiagnosis included overinterpretation of positive serum antibodies (53 [50%]), misinterpretation of functional/psychiatric, or nonspecific cognitive dysfunction as encephalopathy (41 [38%]).Conclusions and RelevanceWhen evaluating for autoimmune encephalitis, a broad differential diagnosis should be considered and misdiagnosis occurs in many settings including at specialized centers. In this study, red flags suggesting alternative diagnoses included an insidious onset, positive nonspecific serum antibody, and failure to fulfill autoimmune encephalitis diagnostic criteria. Autoimmune encephalitis misdiagnosis leads to morbidity from unnecessary immunotherapies and delayed treatment of the correct diagnosis.

AbstractDeep learning has a profound impact on daily life. As Orthopedics makes use of this rapid escalation in technology, Orthopedic surgeons will need to take leadership roles on deep learning projects. Moreover, surgeons must possess an understanding of what is necessary to design and implement deep learning‐based project pipelines. This review provides a practical guide for the Orthopedic surgeon to understand the steps needed to design, develop, and deploy a deep learning pipeline for clinical applications. A detailed description of the processes involved in defining the problem, building the team, acquiring and curating the data, labeling the data, establishing the ground truth, pre‐processing and augmenting the data, and selecting the required hardware is provided. In addition, an overview of unique considerations involved in the training and evaluation of deep learning models is provided. This review strives to provide surgeons with the groundwork needed to identify gaps in the clinical landscape that deep learning models may be able to fill and equips them with the knowledge needed to lead an interdisciplinary team through the process of creating novel deep‐learning‐based solutions to fill those gaps.

BackgroundSarcopenia increases with age and is associated with poor survival outcomes in patients with cancer. By using a deep learning–based segmentation approach, clinical computed tomography (CT) images of the abdomen of patients with newly diagnosed multiple myeloma (NDMM) were reviewed to determine whether the presence of sarcopenia had any prognostic value.MethodsSarcopenia was detected by accurate segmentation and measurement of the skeletal muscle components present at the level of the L3 vertebrae. These skeletal muscle measurements were further normalized by the height of the patient to obtain the skeletal muscle index for each patient to classify them as sarcopenic or not.ResultsThe study cohort consisted of 322 patients of which 67 (28%) were categorized as having high risk (HR) fluorescence in situ hybridization (FISH) cytogenetics. A total of 171 (53%) patients were sarcopenic based on their peri‐diagnosis standard‐dose CT scan. The median overall survival (OS) and 2‐year mortality rate for sarcopenic patients was 44 months and 40% compared to 90 months and 18% for those not sarcopenic, respectively (p < .0001 for both comparisons). In a multivariable model, the adverse prognostic impact of sarcopenia was independent of International Staging System stage, age, and HR FISH cytogenetics.ConclusionsSarcopenia identified by a machine learning–based convolutional neural network algorithm significantly affects OS in patients with NDMM. Future studies using this machine learning–based methodology of assessing sarcopenia in larger prospective clinical trials are required to validate these findings.

Abstract Characterizing intra- and inter-tumoral heterogeneity of glioblastoma has historically relied on discrete classifications of malignant cell populations leaving immune and other cell populations, known to exist admixed with the malignant tumor cells, relatively neglected. Manifold learning algorithms can manage deconvolving multiple cell populations and are often used to track cell state transitions in single cell transcriptomics. We applied a manifold learning approach to TCGA microarray data (Nf525) and bulk transcriptomics of 134 image localized biopsies across 30 patients with primary and 9 with recurrent glioblastoma to further elucidate how to organize biopsies across a spectrum of possible tissue states. The algorithm revealed a low-dimensional manifold graph for which each biopsy lives across 3 polarizing tissue states - one that is associated with diffusely invaded brain, one that is enriched in mesenchymal genes, and one that is enriched in classical proliferative tumor signatures. We deconvolved the bulk transcriptomics of the image-localized biopsies to reveal the relative abundance of 18 malignant, immune, and other cell subpopulations in each biopsy. Overlaying the cellular decomposition onto the manifold graph visualizing the tissue state distributions revealed that transitions between states correlate with changes in cellular cohabitation composition. The tumor cellular cohabitation ecologies have the lowest diversity, as inferred by ecological measures such as Shannon entropy and evenness, at the distal poles of the graph when compared to the transitional arms. Further, we found that the relationship between imaging appearance of contrast enhancement on T1-weighted MRI and the biopsy cellular composition varies with sex and primary vs recurrent biopsy status. The limited spectrum of possible tissue states revealed by the manifold learning is suggestive of a limited continuum along which tumor and non-tumoral cell populations can cohabitate. Such a limited low-dimensional biological space may constrain the dynamics of tumor biology in a predictable manner.

Abstract Brain tumor associated edema is a significant cause of patient morbidity and mortality often requiring continual treatment with differing levels of success across patients. Edema is a broad term that can indicate increased local water as well as diffusely infiltrating tumor cells. Edema is visualized as hyperintense regions on T2-weighted (T2W) magnetic resonance imaging (MRI) and is typically associated with blood-brain barrier (BBB) breakdown and tumor aggressiveness. Understanding the molecular mechanisms driving imaging patterns of “edema” could provide insights into clinical imaging interpretation. We have an ongoing image-guided biopsy study that allows us to link biopsy molecular markers with locoregional MRI patterns of edema. Further, we previously developed a physics-based method to estimate edema abundance (i.e., edema map) from T2W MRIs. Our goal was to identify connections between BBB-associated molecular factors and edema abundance in brain tumors. Our cohort included 38 patients (female: 15, male: 23) with 129 image-guided biopsies (female: 62, male: 67). We correlated image-localized edema map values with the mean transcriptional frequency for 57 genes related to BBB function. Additionally, we examined correlations separately according to patient reported sex (i.e., male and female) and imaging phenotype (i.e., ENH: enhancing and NE: non-enhancing). We utilized multiple comparisons corrections with a 5% false discovery rate to determine significance. For the overall cohort, we observed significant positive correlations for the HIF1A (p&lt; 0.001) and SOX2 markers with edema. For NE samples, significant correlations included APOE (p=0.001), HIF1A (p&lt; 0.001), PIK3CA (p&lt; 0.001), PTCH1 (p&lt; 0.001), and SOX2 (p&lt; 0.001). Amongst female samples, a significant correlation with PTCH1 (p=0.002) was observed. There were no significant correlations noted for male and enhancing sub-cohorts. Significant correlations between molecular markers of BBB and edema map values could lead to clinical biomarkers for edema or tumor aggressiveness.

Abstract Glioblastoma (GBM) is the most aggressive primary brain tumor with a median survival of 14 months. GBMs are challenging to treat due to their heterogeneous nature. It has also been seen that these tumors have sex differences in their cellular subtypes as well as imaging. Radiomics has the potential to provide a non-invasive, spatial understanding of genetic and epigenetic diversity in these complex tumors and to aid in treatment planning. We have an ongoing study to obtain image-localized biopsies from GBM patients, allowing us to complete radiomic analysis and make connections between immunohistochemistry (IHC) and magnetic resonance imaging (MRI) features. We sought to determine if the patterns on imaging were correlated with underlying tumor biology. We focused on immunohistochemistry (IHC) markers of key features of tumor biology including SOX2 for stem-like tumor cells, CD68 for immune response and Ki67 for proliferation kinetics. Our study included 38 patients with a total of 99 biopsies (bxs): 27 males with 77 bxs and 11 females with 22 bxs. Biopsies were sectioned and stained for the SOX2, CD68, and KI67 markers. We computed 18 first-order radiomic features at each biopsy location for patients’ multimodal MRIs: T1W, T1Gd, T2W, FLAIR, apparent diffusion coefficient, diffusion weighted imaging (DWI) and susceptibility weighted imaging. We then performed correlation analysis between each radiomic feature and marker abundance for each IHC stain. Overall, we found sex-distinct patterns connecting imaging with these IHC markers. For example, amongst female patients, DWI held more prominent correlations with SOX2 than in males. Whereas there were more correlations between CD68 IHC abundance and T1Gd imaging features in males compared to females. Taken together, the overall patterns connecting locoregional imaging features to these IHC markers showed sex-distinct patterns suggesting the potential for sex to be an important biological variable when interpreting the biology underlying imaging changes.

Abstract Overall Survival estimates from diagnosis are valuable for guiding treatment, but do not consider the years already survived. Conditional survival (CS) provides dynamic survival predictions over time. This study was conducted to estimate CS at 1–8 years from diagnosis and the impact of baseline prognostic factors on CS in multiple myeloma (MM) patients. This is a retrospective study including 2556 MM patients diagnosed between 2004–2019. CS (t|s) was defined as the probability of surviving t years given survival of s years. Median age was 64 years. Median follow-up was 6.2 years and median overall survival from diagnosis was 7.5 years. The 5-year CS estimates at s = 0, 1, 2, 3, and 5 years were 0.64, 0.61, 0.61, 0.61, and 0.58, respectively. On multivariate analysis, age ≥ 65 and proteasome inhibitor + immunomodulatory-based induction were associated with decreased survival and increased survival, respectively, retained at 5 years. The adverse impact of 1q gain/amplification, high-risk IgH translocation, and ISS-3 was significant at 1 and 3 years but not 5 years. Chromosome 17 abnormality was associated with decreased survival only at 1 year. Among MM patients, 5-year CS was stable at 1–5 years from diagnosis. The prognostic impact of high-risk cytogenetic factors decreased with additional years survived.