Gold Standard Classification Research Articles

#2423 Molecular classification of lupus nephritis based on immune pathway profiling—correlations with histological class and clinical manifestations

Abstract Background and Aims The ISN/RPS 2003 classification is the current gold standard histopathological classification for lupus nephritis (LN), and has important roles in guiding treatment and predicting prognosis. The classification system, largely based on light microscopy features, does not inform the underlying immunological aberrations. A classification based on molecular typing of immune-related pathways may better stratify LN patients and help select treatments that target specific immune cascades. Method The normalized expression matrix and clinical data were extracted from Gene Expression Omnibus database, Human Cell Atlas (Hacohen-Human-CELseq2) and Nephroseq. Four chip datasets (GSE127797, 32591, 69438 and 37463) and one single cell dataset were analyzed. Sample gene set enrichment analysis (ssGSEA) method was used to derive immune phenotype with gene expression data. The hierarchical clustering with ssGSEA scores of selected gene sets was used to classify LN tissues. Functional characterization and protein-protein interactions of the differential expression genes (DEGs) of three groups were compared with healthy donors using Metascape (absolute log FC > 1 and adjusted P-value < .05). Kruskal-Walli test and chi-square test were performed to compare the clinical parameters of the different groups. Results We analyzed 96 immune-related gene sets in the glomerular and tubulointerstitial regions of LN kidney biopsy samples. The immune-related genes were categorized into three clusters (Immune-Mild, Immune-Moderate and Immune-Severe) based on the degree of immune pathway activation. Interferon-stimulated genes are a hallmark of LN, with high signals in all three clusters. When compared to other groups, the Immune-Mild cluster from the glomerular region showed no T-cell activation or T cell receptor pathway. Also, the Immune-Mild (tubulointerstitial) group also showed minimal lymphocyte activation or migration. Protein-protein interactions networks with MOCDE components further suggested that STAT1 and ISG15 the hub genes in different clusters. The gene expressions of hub genes were then compared among epithelial cells and 21 immune cells from LN and heath controls. Immune clusters are correlated with clinical phenotypes, in which Immune-Mild Group (Glomerular) showed high prevalence of Class II and V LN, and Immune-Mild (Tubulointerstitial) showed more Class V LN. Immune-Severe group also showed higher degree of proteinuria and blood pressure but lower eGFR compared to Immune-Moderate and Immune-Mild groups. Conclusion A new molecular classification of LN based on the degree of immune pathway activation shows correlation with clinical manifestations and may potentially guide personalized therapy in LN patients.

Abstract 75: Validation of Vascular Location Subcodes for Acute Ischemic Stroke by the International Classification of Diseases-10

Background: The affected vascular region is included in the International Classification of Diseases-10 (ICD-10) coding scheme for stroke. These data have the potential to enable studies of vascular and regional location. For example, differentiating anterior versus posterior circulation stroke. However, the coding in real world practice has not been validated. The purpose of this study was to evaluate the validity of these subcodes. Methods: We identified all hospitalizations for ischemic stroke at a single center from 2018-2022. We selected a random sample of 100 hospitalizations with vascular region subcoding specifying 50 with anterior circulation subcodes (carotid, anterior cerebral artery [CA], middle CA) and 50 with posterior circulation subcodes (vertebral, basilar, cerebellar, posterior CA). The gold standard classification for the primary infarct vascular distribution was made by the study team, blinded to the subcode, after review of the available imaging studies and the medical record. We calculated the sensitivity, specificity, positive predictive value, and negative predictive value of the administrative data posterior circulation subcodes versus anterior circulation subcodes with the gold standard classification. We also calculated the kappa statistic for overall agreement of the 7 vascular regions. Results: The final study population was 50 ICD-10 anterior circulation ischemic stroke hospitalizations and 50 ICD-10 posterior circulation ischemic stroke hospitalizations. Mean age was 68 (SD, 15) and 44% (44/100) were female. Mean NIHSS was 8 (SD, 8). Neuroimaging was performed in 100% (100/100): Head CT, 95% (95/100); MRI brain, 77% (77/100). The accuracy of the ICD-10 classification for primary posterior circulation stroke was as follows: sensitivity 89% (49/55); specificity 98% (44/45); PPV 98% (49/50); NPV 88% (44/50), respectively. The reliability of the 7-region classification was excellent (kappa statistic, 0.85). Conclusions: We found that the ICD-10 subcode classification for vascular location used in clinical practice had excellent agreement with our gold standard based on medical review. These data validate the use of these subcodes for anterior versus posterior circulation stroke studies.

Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography

BackgroundAutomated identification of spectral domain optical coherence tomography (SD-OCT) features can improve retina clinic workflow efficiency as they are able to detect pathologic findings. The purpose of this study was to test a deep learning (DL)-based algorithm for the identification of Idiopathic Full Thickness Macular Hole (IFTMH) features and stages of severity in SD-OCT B-scans.MethodsIn this cross-sectional study, subjects solely diagnosed with either IFTMH or Posterior Vitreous Detachment (PVD) were identified excluding secondary causes of macular holes, any concurrent maculopathies, or incomplete records. SD-OCT scans (512 × 128) from all subjects were acquired with CIRRUS™ HD-OCT (ZEISS, Dublin, CA) and reviewed for quality. In order to establish a ground truth classification, each SD-OCT B-scan was labeled by two trained graders and adjudicated by a retina specialist when applicable. Two test sets were built based on different gold-standard classification methods. The sensitivity, specificity and accuracy of the algorithm to identify IFTMH features in SD-OCT B-scans were determined. Spearman’s correlation was run to examine if the algorithm’s probability score was associated with the severity stages of IFTMH.ResultsSix hundred and one SD-OCT cube scans from 601 subjects (299 with IFTMH and 302 with PVD) were used. A total of 76,928 individual SD-OCT B-scans were labeled gradable by the algorithm and yielded an accuracy of 88.5% (test set 1, 33,024 B-scans) and 91.4% (test set 2, 43,904 B-scans) in identifying SD-OCT features of IFTMHs. A Spearman’s correlation coefficient of 0.15 was achieved between the algorithm’s probability score and the stages of the 299 (47 [15.7%] stage 2, 56 [18.7%] stage 3 and 196 [65.6%] stage 4) IFTMHs cubes studied.ConclusionsThe DL-based algorithm was able to accurately detect IFTMHs features on individual SD-OCT B-scans in both test sets. However, there was a low correlation between the algorithm’s probability score and IFTMH severity stages. The algorithm may serve as a clinical decision support tool that assists with the identification of IFTMHs. Further training is necessary for the algorithm to identify stages of IFTMHs.

Reliability of ChatGPT for performing triage task in the emergency department using the Korean Triage and Acuity Scale.

Artificial intelligence (AI) technology can enable more efficient decision-making in healthcare settings. There is a growing interest in improving the speed and accuracy of AI systems in providing responses for given tasks in healthcare settings. This study aimed to assess the reliability of ChatGPT in determining emergency department (ED) triage accuracy using the Korean Triage and Acuity Scale (KTAS). Two hundred and two virtual patient cases were built. The gold standard triage classification for each case was established by an experienced ED physician. Three other human raters (ED paramedics) were involved and rated the virtual cases individually. The virtual cases were also rated by two different versions of the chat generative pre-trained transformer (ChatGPT, 3.5 and 4.0). Inter-rater reliability was examined using Fleiss' kappa and intra-class correlation coefficient (ICC). The kappa values for the agreement between the four human raters and ChatGPTs were .523 (version 4.0) and .320 (version 3.5). Of the five levels, the performance was poor when rating patients at levels 1 and 5, as well as case scenarios with additional text descriptions. There were differences in the accuracy of the different versions of GPTs. The ICC between version 3.5 and the gold standard was .520, and that between version 4.0 and the gold standard was .802. A substantial level of inter-rater reliability was revealed when GPTs were used as KTAS raters. The current study showed the potential of using GPT in emergency healthcare settings. Considering the shortage of experienced manpower, this AI method may help improve triaging accuracy.

Monitoring the Epidemiology of Otitis Using Free-Text Pediatric Medical Notes: A Deep Learning Approach.

Free-text information represents a valuable resource for epidemiological surveillance. Its unstructured nature, however, presents significant challenges in the extraction of meaningful information. This study presents a deep learning model for classifying otitis using pediatric medical records. We analyzed the Pedianet database, which includes data from January 2004 to August 2017. The model categorizes narratives from clinical record diagnoses into six types: no otitis, non-media otitis, non-acute otitis media (OM), acute OM (AOM), AOM with perforation, and recurrent AOM. Utilizing deep learning architectures, including an ensemble model, this study addressed the challenges associated with the manual classification of extensive narrative data. The performance of the model was evaluated according to a gold standard classification made by three expert clinicians. The ensemble model achieved values of 97.03, 93.97, 96.59, and 95.48 for balanced precision, balanced recall, accuracy, and balanced F1 measure, respectively. These results underscore the efficacy of using automated systems for medical diagnoses, especially in pediatric care. Our findings demonstrate the potential of deep learning in interpreting complex medical records, enhancing epidemiological surveillance and research. This approach offers significant improvements in handling large-scale medical data, ensuring accuracy and minimizing human error. The methodology is adaptable to other medical contexts, promising a new horizon in healthcare analytics.

Preliminary Study of Axillary Lymphatic Drainage in Cutaneous Melanoma Patients: A Cross-Sectional Study.

Background: The axilla is a region of fundamental importance for the implications during oncological surgery, and there are many classifications of axillary lymph node subdivision: on the basis of studies on women with breast cancer, we used Clough's and Li's classification. However, currently we do not have a gold-standard classification regarding axillary lymphatic drainage in melanoma patients. Purpose: Our aim was to evaluate how these classifications could be adapted to sentinel lymph node evaluation in skin-melanoma patients and to look for a possible correlation between the most recent classifications of axillary lymph node location and Oeslner's classification, one of the most common anatomical classifications still widespread today. Methods: We analyzed data from 21 patients who underwent sentinel lymph node biopsy between January 2021 and January 2022. Results: Our study demonstrates that, to an extent, there is a possible difference in the use of the various classifications, hinting at possible limits of each. The data we obtained underline how cutaneous melanoma presents extremely heterogenous lymphatic drainage at the level of the axillary cavity. However, the limited data in our possession do not allow us to obtain, at the moment, results that are statistically significant, although we are continuing to enroll patients and collect data. Conclusions: Results of this study support the evidence that the common classifications used for breast cancer do not seem to be exhaustive. Therefore, a specific axillary lymph node classification is necessary in skin melanoma patients.

Assessing Detection of Children With Suicide-Related Emergencies: Evaluation and Development of Computable Phenotyping Approaches.

Although suicide is a leading cause of death among children, the optimal approach for using health care data sets to detect suicide-related emergencies among children is not known. This study aimed to assess the performance of suicide-related International Classification of Diseases, Tenth Revision, Clinical Modification (ICD-10-CM) codes and suicide-related chief complaint in detecting self-injurious thoughts and behaviors (SITB) among children compared with clinician chart review. The study also aimed to examine variations in performance by child sociodemographics and type of self-injury, as well as develop machine learning models trained on codified health record data (features) and clinician chart review (gold standard) and test model detection performance. A gold standard classification of suicide-related emergencies was determined through clinician manual review of clinical notes from 600 emergency department visits between 2015 and 2019 by children aged 10 to 17 years. Visits classified with nonfatal suicide attempt or intentional self-harm using the Centers for Disease Control and Prevention surveillance case definition list of ICD-10-CM codes and suicide-related chief complaint were compared with the gold standard classification. Machine learning classifiers (least absolute shrinkage and selection operator-penalized logistic regression and random forest) were then trained and tested using codified health record data (eg, child sociodemographics, medications, disposition, and laboratory testing) and the gold standard classification. The accuracy, sensitivity, and specificity of each detection approach and relative importance of features were examined. SITB accounted for 47.3% (284/600) of the visits. Suicide-related diagnostic codes missed nearly one-third (82/284, 28.9%) and suicide-related chief complaints missed more than half (153/284, 53.9%) of the children presenting to emergency departments with SITB. Sensitivity was significantly lower for male children than for female children (0.69, 95% CI 0.61-0.77 vs 0.84, 95% CI 0.78-0.90, respectively) and for preteens compared with adolescents (0.66, 95% CI 0.54-0.78 vs 0.86, 95% CI 0.80-0.92, respectively). Specificity was significantly lower for detecting preparatory acts (0.68, 95% CI 0.64-0.72) and attempts (0.67, 95% CI 0.63-0.71) than for detecting ideation (0.79, 95% CI 0.75-0.82). Machine learning-based models significantly improved the sensitivity of detection compared with suicide-related codes and chief complaint alone. Models considering all 84 features performed similarly to models considering only mental health-related ICD-10-CM codes and chief complaints (34 features) and models considering non-ICD-10-CM code indicators and mental health-related chief complaints (53 features). The capacity to detect children with SITB may be strengthened by applying a machine learning-based approach to codified health record data. To improve integration between clinical research informatics and child mental health care, future research is needed to evaluate the potential benefits of implementing detection approaches at the point of care and identifying precise targets for suicide prevention interventions in children.

Effectiveness of R1-nj Anthocyanin Marker in the Identification of In Vivo Induced Maize Haploid Embryos.

Doubled haploid (DH) technology has become integral to maize breeding programs to expedite inbred line development and increase the efficiency of breeding operations. Unlike many other plant species that use in vitro methods, DH production in maize uses a relatively simple and efficient in vivo haploid induction method. However, it takes two complete crop cycles for DH line generation, one for haploid induction and the other one for chromosome doubling and seed production. Rescuing in vivo induced haploid embryos has the potential to reduce the time for DH line development and improve the efficiency of DH line production. However, the identification of a few haploid embryos (~10%) resulting from an induction cross from the rest of the diploid embryos is a challenge. In this study, we demonstrated that an anthocyanin marker, namely R1-nj, which is integrated into most haploid inducers, can aid in distinguishing haploid and diploid embryos. Further, we tested conditions that enhance R1-nj anthocyanin marker expression in embryos and found that light and sucrose enhance anthocyanin expression, while phosphorous deprivation in the media had no affect. Validating the use of the R1-nj marker for haploid and diploid embryo identification using a gold standard classification based on visual differences among haploids and diploids for characteristics such as seedling vigor, erectness of leaves, tassel fertility, etc., indicated that the R1-nj marker could lead to significantly high false positives, necessitating the use of additional markers for increased accuracy and reliability of haploid embryo identification.

Combination of CEACAM5, EpCAM and CK19 gene expressions in mediastinal lymph node micrometastasis is a prognostic factor for non-small cell lung cancer

BackgroundLung cancer is known as the most common and highly metastatic form of cancer worldwide. Tumour node metastasis (TNM) staging is the gold standard classification system for the decision-making process for appropriate treatment. Particularly N status has the most important prognostic value in the absence of distant metastasis. Traditional diagnostic methods are capable of detecting metastasis; however, they may fail to detect micrometastasis, which plays a role in disease recurrence and patients' long-term survival. Occult micrometastasis can change the tumour's TNM staging and, consequently, the patient's treatment regimen.MethodsThe median number of three lymph node tissues were collected from 30 patients who underwent surgery for non-small cell lung cancer. Lymph node tissues were collected from different lymph node stations according to the location of the patient's tumour. CK19, EpCAM and CEACAM5 gene expressions were analysed in tissues using quantitative real-time polymerase chain reaction to detect micrometastasis in distant lymph nodes.ResultsTriple positivity was seen in 26 out of 30 patients which 19 patients were upstaged from N0 to N2. While survival was not significantly affected between upstaged and non-upstaged patients, patients upstaged with multiple-station N2 had a significantly higher recurrence and lower survival compared to single-station N2.ConclusionA combination of CK19, EpCAM and CEACAM5 gene expressions in lymph nodes can be used to identify micrometastasis which postoperatively may be used as a tool to predict patients’ recurrence and survival.

Is the Robinson classification of clavicle fractures accurate enough within the setting of the Swedish Fracture Register?

IntroductionIn the Swedish Fracture Register (SFR) clavicle fractures are classified according to the Robinson classification. This study aimed to evaluate the accuracy of the classification of clavicle fractures in the SFR. A secondary aim was to assess inter- and intraobserver agreement. Materials and MethodsClavicle fractures (n = 132) were randomly selected from the SFR and radiographs were requested for each patient from their treating departments. Not all radiographs could be acquired, and after exclusion, 115 fractures were independently classified by three expert raters blinded to patient information. The 115 fractures were classified on two occasions, 3 months apart. The raters’ consensus classification was used as a gold standard that was compared to the classification registered in the SFR. The accuracy, defined as the degree of agreement between the gold standard and SFR classifications, was reported, as was the inter- and intraobserver agreement for the expert raters. ResultsAgreement between the classification in the SFR and the gold standard classification was fair (kappa = 0.35). Fractures with only partial displacement were often incorrectly classified as fully displaced in the SFR (n = 31 of 78 displaced fractures in the SFR). The inter- and intraobserver agreement among the expert raters was almost perfect (interobserver kappa = 0.81–0.87, intraobserver kappa = 0.84–0.94). ConclusionsThe accuracy of the classification of clavicle fractures in the SFR was only fair, whereas the inter- and intraobserver agreement among the expert raters was almost perfect. Accuracy in the SFR may be improved if the classification instructions in the SFR are updated by incorporating the original classification displacement criteria, both in text and in illustrated form.

Validation of the Antifungal National Antimicrobial Prescribing Survey (AF-NAPS) quality assessment tool.

The Antifungal National Antimicrobial Prescribing Survey (AF-NAPS) was developed to undertake streamlined quality audits of antifungal prescribing. The validity and reliability of such tools is not characterized. To assess the validity and reliability of the AF-NAPS quality assessment tool. Case vignettes describing antifungal prescribing were prepared. A steering group was assembled to determine gold-standard classifications for appropriateness and guideline compliance. Infectious diseases physicians, antimicrobial stewardship (AMS) and specialist pharmacists undertook a survey to classify appropriateness and guideline compliance of prescriptions utilizing the AF-NAPS tool. Validity was measured as accuracy, sensitivity and specificity compared with gold standard. Inter-rater reliability was measured using Fleiss' kappa statistics. Assessors' responses and comments were thematically analysed to determine reasons for incorrect classification. Twenty-eight clinicians assessed 59 antifungal prescriptions. Overall accuracy of appropriateness assessment was 77.0% (sensitivity 85.3%, specificity 68.0%). Highest accuracy was seen amongst specialist (81%) and AMS pharmacists (79%). Prescriptions with lowest accuracy were in the haematology setting (69%), use of echinocandins (73%), mould-active azoles (75%) and for prophylaxis (71%). Inter-rater reliability was fair overall (0.3906), with moderate reliability amongst specialist pharmacists (0.5304). Barriers to accurate classification were incorrect use of the appropriateness matrix, knowledge gaps and lack of guidelines for some indications. The AF-NAPS is a valid tool, assisting assessors to correctly classify appropriate prescriptions more accurately than inappropriate prescriptions. Specialist and AMS pharmacists had similar performance, providing confidence that both can undertake AF-NAPS audits to a high standard. Identified reasons for incorrect classification will be targeted in the online tool and educational materials.

Unforced errors in the matching problem

The solution of the Montmort's matching problem can be seen as the probability mass function of the number of matches in an experiment for assessing the agreement between nominal variables and gold standard classifications. [Vidal I, de Castro M. A Bayesian analysis of the matching problem. J Stat Plan Inference. 2021;212:194–200] presented a generalization of the Montmort's matching problem by considering the chronological order in what assignments are made and counting the number of unforced errors additionally to the number of matches. These authors carried out a Bayesian analysis of the problem, but in this paper we found a solution of this new approach from a frequentist point of view. We found the bivariate probability mass function of the number of matches and the number of unforced errors. The marginal distribution of the number of unforced errors is computed and expressed in terms of the Stirling numbers of the second kind. Also, some elementary properties were proven, including that the distribution of the unforced errors is equal to that of forced errors. As a practical consequence, we propose a new experiment and a new way of collecting and analysing the data in order to assess the agreement between nominal variables and gold standard classifications. Two real data sets were analysed using the proposed methodology.

58 Comparison of the 2015 pediatric diagnostic criteria for Behcet’s disease with the 2014 and 1990 International Study Group Diagnostic Criteria

BackgroundBehçet's disease is a multisystem vasculitis whose pathogenesis remains unclear. Although usually described in young adults, it may begin in childhood. The diagnosis is clinical, based on international criteria. The limitations of early diagnosis are related to the progressive onset of symptoms and the variety of differential diagnoses at this age in the absence of a pathognomonic diagnostic test.ObjectivesTo report the epidemiological features of our series and to compare the 2015 pediatric criteria with the 2014 and 1990 international criteria.Materials and MethodsThis is a monocentric, retrospective study of 31 children over an 11-year period from January 2011 to December 2021. All patients suspected with Behcet's disease by a pediatric rheumatologist were included in the study, the 2014 international criteria “ISG 2014” being the gold standard classification criteria used in our center.Results31 cases of Behcet's were collected. The mean age was 10 years (5.5–16) ± 2.87 years. A female predominance is noted with a sex ratio F/M of 1.21. A quarter of the patients were from a consanguineous marriage and 38.7% had a family history of Behcet disease. Mucocutaneous manifestations were represented by recurrent oral aphthosis 87.1%, genital aphthosis 29%, pseudofolliculitis 48.4%, erythema nodosum 6.5% and acne lesions 3.2%. The pathergy test was positive in 1 case. Ocular involvement was reported in 29% and joint involvement in 45.2%. Thromboembolic complication was seen in 9.6% and neurobehcet in one patient. The HLA B51 antigen was present in 45.2% of cases. In our series 38.7% respond the pediatric criteria, while 61.3% met the 2014 international criteria and 35.5% met the 1990 international criteria. The 2015 pediatric criteria have respectively a sensitivity and specificity of 63.2% and 100% (p = 0.002) compared with the 2014 international criteria taken as gold standard, as well as the 1990 international criteria with a respective sensitivity and specificity of 52.6% and 91.7% (p = 0.034).ConclusionOur study highlights a female predominance, a high rate of consanguinity and familial Behcet. The sensitivity and specificity of the 1990 pediatric and international criteria appear to be better than those of 2014, with a more significant trend for the 2015 pediatric criteria (p = 0.002).

On the use of multi-objective evolutionary classifiers for breast cancer detection.

PurposeBreast cancer is one of the most common tumours in women, nevertheless, it is also one of the cancers that is most usually treated. As a result, early detection is critical, which can be accomplished by routine mammograms. This paper aims to describe, analyze, compare and evaluate three image descriptors involved in classifying breast cancer images from four databases.ApproachMulti–Objective Evolutionary Algorithms (MOEAs) prove themselves as being efficient methods for selection and classification problems. This paper aims to study combinations of well–known classification objectives in order to compare the results of their application in solving very specific learning problems. The experimental results undergo empirical analysis which is supported by a statistical approach. The results are illustrated on a collection of medical image databases, but with a focus on the MOEAs’ performance in terms of several well–known measures. The databases were chosen specifically to feature reliable human annotations, so as to measure the correlation between the gold standard classifications and the various MOEA classifications.ResultsWe have seen how different statistical tests rank one algorithm over the others in our set as being better. These findings are unsurprising, revealing that there is no single gold standard for comparing diverse techniques or evolutionary algorithms. Furthermore, building meta-classifiers and evaluating them using a single, favorable metric is both extremely unwise and unsatisfactory, as the impact is to skew the results.ConclusionsThe best method to address these flaws is to select the right set of objectives and criteria. Using accuracy-related objectives, for example, is directly linked to maximizing the number of true positives. If, on the other hand, accuracy is chosen as the generic metric, the primary classification goal is shifted to increasing the positively categorized data points.

A New Motor and Cognitive Dual-Task Approach Based on Foot Tapping for The Identification of Mild Cognitive Impairment.

This study investigates the adoption of innovative Motor and Cognitive Dual-Task (MCDT) based on the combination of increasing motor and cognitive tasks to discern between subjects with Mild Cognitive Impairment (MCI) and Cognitively Normal Adults (CNA). We aim to adopt new MCDT protocols and to compare their performance against the gold standard (a walking based MCDT, called GAIT). 27 older adults have been assessed through a customized wearable system during 4 MCDTs. We developed as many pooled indices (PIs), based on MCDTs perfomance, demographic data, and clinical scores. We use these parameters as regressors in 4 different logistic regression models. The regression models that encompassed features from innovative MCDT overcame the gold standard classification performance. In particular, models based on the heel tapping and the alternate heel-toe tapping reach the best outputs, namely +8% of accuracy if compared to the gold standard (a walking task). The use of logistic regression models based on MCDT PI have been effective in discerning between CNA vs MCI. Our results suggest that the gold standard MCDT may represents a too demanding exercise to highlight differences between CNA and MCI. It seems that MCDT based on an intermediate level of motor difficulty could represent the sweet spot for the identification of MCI against CNA. Clinical relevance- The combination of innovative digital devices and innovative approach on data analysis (PIs) opened a new scenarios to the early detection and prediction of dementia. Their use would standardize the assessment procedure, lightening the physician from the burden of cumbersome testing sessions. This study suggests that a broader framework for MCDT, which should encompass an ampler selection of motor tasks with different possibilities in terms of difficulties levels, could provide clinicians with a new appropriate set of tools for the early detection of dementia.

Intra- and inter-examiner reliability in classifying periodontitis according to the 2018 classification of periodontal diseases.

AimTo evaluate the inter‐examiner reliability in classifying periodontitis using the 2018 classification of periodontal diseases, when used by postgraduate students, academics, and specialist clinicians trained in European Federation of Periodontology (EFP) and American Academy of Periodontology (AAP) postgraduate‐accredited programmes.Materials and MethodsAn online survey including five patients with periodontitis was sent twice to seven specialists in periodontology to provide the staging and grading characteristics. After agreeing on a “gold‐standard” classification, the same questionnaire was sent to 16 EFP and 73 AAP postgraduate programmes, to be answered by their faculty, graduates, and students. The responses were compared with the gold‐standard classification, and the inter‐examiner agreement was calculated.ResultsOne‐hundred and seventy‐four participants completed the survey. The inter‐examiner agreement resulted in 68.7% in assigning the stage, 82.4% in assigning the grade, and 75.5% in assigning the extent. The academic position and the experience of the participants did not have any significant influence on classifying periodontitis as the gold standard.ConclusionsThe use of the 2018 periodontitis classification resulted in high inter‐examiner reliability when used by a specialist group of clinicians, postgraduate students, and academicians, irrespective of their current position and experience. Given the low response rate and potential selection bias, results pertaining to the use of this system in classifying periodontitis should be interpreted with caution.

Validation of the classification of surgically treated acetabular fractures in the Swedish Fracture Register

ObjectivesTo validate the classification of surgically treated acetabular fractures in the Swedish Fracture Register (SFR) and to investigate the intra- and interrater reliability of the Judet-Letournel / AO/OTA classification systems. MethodsSurgically treated acetabular fractures were randomly selected from the SFR (n = 132) and 124 fractures were classified independently by three experienced orthopedic pelvic surgeons at two different occasions. A gold standard classification was established for each case after these two sessions or, if necessary, after a discussion session. The gold standard classification was compared to the registered SFR classification to assess the validity of SFR data. Accuracy and intra- and interrater agreement were evaluated using Cohen´s kappa with interpretation according to Landis and Koch. ResultsThere was moderate agreement between the established gold standard classification and the SFR (kappa 0.43). The level of agreement differed between classification groups. The intrarater agreement was substantial to almost perfect and interrater agreement was moderate to substantial. ConclusionsThe accuracy of acetabular fracture classifications in the SFR was moderate and comparable to previous validation studies from the SFR on other fracture types. As the accuracy differed between fracture groups, care should be taken when analyzing data from the SFR on specific acetabular fracture groups.

Is It Necessary To Add Soft Tissue Injury to the Classification in Tibial Plateau Fracture Management?

BackgroundA gold standard classification for the treatment of tibial plateau fractures with soft tissue injury has not been established yet.This study aimed to evaluate the usability of a novel modified classification that can provide preoperative information to the surgeon about soft tissue injuries in tibial plateau fractures.MethodologyA total of 36 patients with tibial plateau fractures were included in the study. Patients’ age, gender, and affected sides were recorded. Injuries to the medial meniscus, lateral meniscus, anterior cruciate ligament, posterior cruciate ligament, medial collateral ligament, and lateral collateral ligament were examined with preoperative magnetic resonance imaging. Soft tissue injuries were arranged according to the novel modified classification based on the Schatzker classification.ResultsThe mean age of the study participants was 45 (19-76) years; 72% of the patients were men and 28% were women. Moreover, 44% and 56% of the patients had broken the right and left tibial plateaus, respectively. At least one soft tissue injury was detected in 29 (81%) patients. In 14 (39%) patients, two or more soft tissue injuries were observed. All patients were arranged according to the novel modified classification regarding ligament and meniscus injuries.ConclusionsWith this novel modified classification system, we think that having better information about the preoperative condition of the soft tissue injuries can change the surgical strategy in patients with tibial plateau fractures.

Surveillance of atypical femoral fractures in a nationwide fracture register.

Background and purposeTo continuously assess the incidence of atypical femoral fractures (AFFs) in the population is important, to allow the evaluation of the risks and benefits associated with osteoporosis treatment. Therefore, we investigated the possibility to use the Swedish Fracture Register (SFR) as a surveillance tool for AFFs in the population and to explore means of improvement.Patients and methodsAll AFF registrations in the SFR from January 1, 2015 to December 31, 2018 were enrolled in the study. For these patients, radiographs were obtained and combined with radiographs from 176 patients with normal femoral fractures, to form the study cohort. All images were reviewed and classified into AFFs or normal femur fractures by 2 experts in the field (gold-standard classification) and 1 orthopedic resident educated on the specific radiographic features of AFF (educated-user classification). Furthermore, we estimated the incidence rate of AFFs in the population captured by the register through comparison with a previous cohort and calculated the positive predictive value (PPV) and, where possible, the inter-observer agreement (Cohen’s kappa) between the different classifications.ResultsOf the 178 available patients with AFF in the SFR, 104 patients were classified as AFF using the goldstandard classification, and 89 using the educated-user classification. The PPV increased from 0.58 in the SFR classification to 0.93 in the educated-user classification. The interobserver agreement between the gold-standard classification and the educated-user classification was 0.81.InterpretationWith a positive predictive value of 0.58 the Swedish Fracture Register outperforms radiology reports and reports to the Swedish Medical Products Agency on adverse drug reactions as a diagnostic tool to identify atypical femoral fractures.

Plant Disease Classification Using Deep Bilinear CNN

Plant diseases have become a major threat in farming and provision of food. Various plant diseases have affected the natural growth of the plants and the infected plants are the leading factors for loss of crop production. The manual detection and identification of the plant diseases require a careful and observative examination through expertise. To overcome manual testing procedures an automated identification and detection can be implied which provides faster, scalable and precisive solutions. In this research, the contributions of our work are threefold. Firstly, a bi-linear convolution neural network (Bi-CNNs) for plant leaf disease identification and classification is proposed. Secondly, we fine-tune VGG and pruned ResNets and utilize them as feature extractors and connect them to fully connected dense networks. The hyperparameters are tuned to reach faster convergence and obtain better generalization during stochastic optimization of Bi-CNN(s). Finally, the proposed model is designed to leverage scalability by implying the Bi-CNN model into a real-world application and release it as an open-source. The model is designed on variant testing criteria ranging from 10% to 50%. These models are evaluated on gold-standard classification measures. To study the performance, testing samples were expanded by 5x (i.e., from 10% to 50%) and it is found that the deviation in the accuracy was quite low (0.27%) which resembles the consistent generalization ability. Finally, the larger model obtained an accuracy score of 94.98% for 38 distinct classes.