Browsing by Subject "Sensitivity and specificity"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Automatic classification of white regions in liver biopsies by supervised machine learning
    (Elsevier, 2014-04) Vanderbeck, Scott; Bockhorst, Joseph; Komorowski, Richard; Kleiner, David E.; Gawrieh, Samer; Medicine, School of Medicine
    Automated assessment of histological features of non-alcoholic fatty liver disease (NAFLD) may reduce human variability and provide continuous rather than semiquantitative measurement of these features. As part of a larger effort, we perform automatic classification of steatosis, the cardinal feature of NAFLD, and other regions that manifest as white in images of hematoxylin and eosin-stained liver biopsy sections. These regions include macrosteatosis, central veins, portal veins, portal arteries, sinusoids and bile ducts. Digital images of hematoxylin and eosin-stained slides of 47 liver biopsies from patients with normal liver histology (n = 20) and NAFLD (n = 27) were obtained at 20× magnification. The images were analyzed using supervised machine learning classifiers created from annotations provided by two expert pathologists. The classification algorithm performs with 89% overall accuracy. It identified macrosteatosis, bile ducts, portal veins and sinusoids with high precision and recall (≥ 82%). Identification of central veins and portal arteries was less robust but still good. The accuracy of the classifier in identifying macrosteatosis is the best reported. The accurate automated identification of macrosteatosis achieved with this algorithm has useful clinical and research-related applications. The accurate detection of liver microscopic anatomical landmarks may facilitate important subsequent tasks, such as localization of other histological lesions according to liver microscopic anatomy.
  • Thumbnail Image
    Item
    Delirium diagnosis defined by cluster analysis of symptoms versus diagnosis by DSM and ICD criteria: diagnostic accuracy study
    (BioMed Central, 2016-05-26) Sepulveda, Esteban; Franco, Jose G.; Trzepacz, Paula T.; Gaviria, Ana M.; Meagher, David J.; Palma, Jose; Viñuelas, Eva; Grau, Imma; Vilella, Elisabet; de Pablo, Joan; Department of Psychiatry, IU School of Medicine
    BACKGROUND: Information on validity and reliability of delirium criteria is necessary for clinicians, researchers, and further developments of DSM or ICD. We compare four DSM and ICD delirium diagnostic criteria versions, which were developed by consensus of experts, with a phenomenology-based natural diagnosis delineated using cluster analysis of delirium features in a sample with a high prevalence of dementia. We also measured inter-rater reliability of each system when applied by two evaluators from distinct disciplines. METHODS: Cross-sectional analysis of 200 consecutive patients admitted to a skilled nursing facility, independently assessed within 24-48 h after admission with the Delirium Rating Scale-Revised-98 (DRS-R98) and for DSM-III-R, DSM-IV, DSM-5, and ICD-10 criteria for delirium. Cluster analysis (CA) delineated natural delirium and nondelirium reference groups using DRS-R98 items and then diagnostic systems' performance were evaluated against the CA-defined groups using logistic regression and crosstabs for discriminant analysis (sensitivity, specificity, percentage of subjects correctly classified by each diagnostic system and their individual criteria, and performance for each system when excluding each individual criterion are reported). Kappa Index (K) was used to report inter-rater reliability for delirium diagnostic systems and their individual criteria. RESULTS: 117 (58.5 %) patients had preexisting dementia according to the Informant Questionnaire on Cognitive Decline in the Elderly. CA delineated 49 delirium subjects and 151 nondelirium. Against these CA groups, delirium diagnosis accuracy was highest using DSM-III-R (87.5 %) followed closely by DSM-IV (86.0 %), ICD-10 (85.5 %) and DSM-5 (84.5 %). ICD-10 had the highest specificity (96.0 %) but lowest sensitivity (53.1 %). DSM-III-R had the best sensitivity (81.6 %) and the best sensitivity-specificity balance. DSM-5 had the highest inter-rater reliability (K =0.73) while DSM-III-R criteria were the least reliable. CONCLUSIONS: Using our CA-defined, phenomenologically-based delirium designations as the reference standard, we found performance discordance among four diagnostic systems when tested in subjects where comorbid dementia was prevalent. The most complex diagnostic systems have higher accuracy and the newer DSM-5 have higher reliability. Our novel phenomenological approach to designing a delirium reference standard may be preferred to guide revisions of diagnostic systems in the future.
  • Thumbnail Image
    Item
    Mayo Normative Studies: Amyloid and Neurodegeneration Negative Normative Data for the Auditory Verbal Learning Test and Sex-Specific Sensitivity to Mild Cognitive Impairment/Dementia
    (IOS Press, 2024) Stricker, Nikki H.; Christianson, Teresa J.; Pudumjee, Shehroo B.; Polsinelli, Angelina J.; Lundt, Emily S.; Frank, Ryan D.; Kremers, Walter K.; Machulda, Mary M.; Fields, Julie A.; Jack, Clifford R., Jr.; Knopman, David S.; Graff-Radford, Jonathan; Vemuri, Prashanthi; Mielke, Michelle M.; Petersen, Ronald C.; Neurology, School of Medicine
    Background: Conventional normative samples include individuals with undetected Alzheimer's disease neuropathology, lowering test sensitivity for cognitive impairment. Objective: We developed Mayo Normative Studies (MNS) norms limited to individuals without elevated amyloid or neurodegeneration (A-N-) for Rey's Auditory Verbal Learning Test (AVLT). We compared these MNS A-N- norms in female, male, and total samples to conventional MNS norms with varying levels of demographic adjustments. Methods: The A-N- sample included 1,059 Mayo Clinic Study of Aging cognitively unimpaired (CU) participants living in Olmsted County, MN, who are predominantly non-Hispanic White. Using a regression-based approach correcting for age, sex, and education, we derived fully-adjusted T-score formulas for AVLT variables. We validated these A-N- norms in two independent samples of CU (n = 261) and mild cognitive impairment (MCI)/dementia participants (n = 392) > 55 years of age. Results: Variability associated with age decreased by almost half in the A-N- norm sample relative to the conventional norm sample. Fully-adjusted MNS A-N- norms showed approximately 7- 9% higher sensitivity to MCI/dementia compared to fully-adjusted MNS conventional norms for trials 1- 5 total and sum of trials. Among women, sensitivity to MCI/dementia increased with each normative data refinement. In contrast, age-adjusted conventional MNS norms showed greatest sensitivity to MCI/dementia in men. Conclusions: A-N- norms show some benefits over conventional normative approaches to MCI/dementia sensitivity, especially for women. We recommend using these MNS A-N- norms alongside MNS conventional norms. Future work is needed to determine if normative samples that are not well characterized clinically show greater benefit from biomarker-refined approaches.