COVID-19 psychosis versus psychosis due to cytotoxic lesion of the corpus callosum (CLOCC): A case report and review.

Background: Cytotoxic lesions of the corpus callosum syndrome (CLOCC) is an inflammatory disorder caused by various etiologies such as medications, malignancies, seizure, metabolic abnormalities, and infections, especially COVID-19. It presents on MRI as an area of restricted diffusion in the corpus callosum. We present a case of psychosis and CLOCC in a patient with mild active COVID-19 infection. Case: A 25-year-old male with a history of asthma and unclear past psychiatric history presented to the emergency room with shortness of breath, chest pain, and disorganized behavior. His-COVID-19 PCR was negative, and he was voluntarily admitted to psychiatry for management of unspecified psychosis. Overnight, he spiked a fever and was diaphoretic with headache and altered mental status. Repeat COVID-19 PCR at this time was positive and cycle threshold indicated infectivity. A brain MRI showed a new restricted diffusion within the midline of the splenium of the corpus callosum. Lumbar puncture was unremarkable. He continued to have flat affect and exhibit disorganized behavior with unspecified grandiosity, unclear auditory hallucinations, echopraxia, and poor attention and working memory. He was started on risperidone, with an MRI after 8 days showing complete resolution of the lesion in the corpus callosum and symptoms. Conclusion: This case discusses diagnostic difficulties and treatment options for a patient presenting with psychotic symptoms and disorganized behavior in the context of active COVID-19 infection and CLOCC and highlights differences between delirium, COVID-19 psychosis and neuropsychiatric symptoms of CLOCC. Future research directions are also discussed.

Conditioned Hallucinations and Prior Overweighting Are State-Sensitive Markers of Hallucination Susceptibility.

BACKGROUND: Recent advances in computational psychiatry have identified latent cognitive and perceptual states that predispose to psychotic symptoms. Behavioral data fit to Bayesian models have demonstrated an overreliance on priors (i.e., prior overweighting) during perception in select samples of individuals with hallucinations, corresponding to increased precision of prior expectations over incoming sensory evidence. However, the clinical utility of this observation depends on the extent to which it reflects static symptom risk or current symptom state. METHODS: To determine whether task performance and estimated prior weighting relate to specific elements of symptom expression, a large, heterogeneous, and deeply phenotyped sample of hallucinators (n = 249) and nonhallucinators (n = 209) performed the conditioned hallucination (CH) task. RESULTS: We found that CH rates predicted stable measures of hallucination status (i.e., peak frequency). However, CH rates were more sensitive to hallucination state (i.e., recent frequency), significantly correlating with recent hallucination severity and driven by heightened reliance on past experiences (priors). To further test the sensitivity of CH rate and prior weighting to symptom severity, a subset of participants with hallucinations (n = 40) performed a repeated-measures version of the CH task. Changes in both CH frequency and prior weighting varied with changes in auditory hallucination frequency on follow-up. CONCLUSIONS: These results indicate that CH rate and prior overweighting are state markers of hallucination status, potentially useful in tracking disease development and treatment response.

Measuring Voluntary Control Over Hallucinations: The Yale Control Over Perceptual Experiences (COPE) Scales.

Auditory verbal hallucinations (AVH) frequently cause significant distress and dysfunction, and may be unresponsive to conventional treatments. Some voice-hearers report an ability to fully control the onset and offset of their AVH, making them significantly less disruptive. Measuring and understanding these abilities may lead to novel interventions to enhance control over AVH. Fifty-two voice-hearers participated in the pilot study. 318 participants with frequent AVH participated in the validation study. A pool of 59 items was developed by a diverse team including voice-hearers and clinicians. After the pilot study, 35 items were retained. Factorial structure was assessed with exploratory (EFA, n = 148) and confirmatory (CFA, n = 170) factor analyses. Reliability and convergent validity were assessed using a comprehensive battery of validated phenomenological and clinical scales. CFA on the final 18 items supported two factors for a Methods of Control Scale (5 items each, average ω = .87), and one factor for a Degree of Control Scale (8 items, average ω = .95). Correlation with clinical measures supported convergent validity. Degree of control was associated with positive clinical outcomes in voice-hearers both with and without a psychosis-spectrum diagnosis. Degree of control also varied with quality of life independently of symptom severity and AVH content. The Yale control over perceptual experiences (COPE) Scales robustly measure voice-hearers' control over AVH and exhibit sound psychometric properties. Results demonstrate that the capacity to voluntarily control AVH is independently associated with positive clinical outcomes. Reliable measurement of control over AVH will enable future development of interventions meant to bolster that control.

Deep forest model for diagnosing COVID-19 from routine blood tests.

The Coronavirus Disease 2019 (COVID-19) global pandemic has threatened the lives of people worldwide and posed considerable challenges. Early and accurate screening of infected people is vital for combating the disease. To help with the limited quantity of swab tests, we propose a machine learning prediction model to accurately diagnose COVID-19 from clinical and/or routine laboratory data. The model exploits a new ensemble-based method called the deep forest (DF), where multiple classifiers in multiple layers are used to encourage diversity and improve performance. The cascade level employs the layer-by-layer processing and is constructed from three different classifiers: extra trees, XGBoost, and LightGBM. The prediction model was trained and evaluated on two publicly available datasets. Experimental results show that the proposed DF model has an accuracy of 99.5%, sensitivity of 95.28%, and specificity of 99.96%. These performance metrics are comparable to other well-established machine learning techniques, and hence DF model can serve as a fast screening tool for COVID-19 patients at places where testing is scarce.

Ensemble learning model for diagnosing COVID-19 from routine blood tests.

BACKGROUND AND OBJECTIVES: The pandemic of novel coronavirus disease 2019 (COVID-19) has severely impacted human society with a massive death toll worldwide. There is an urgent need for early and reliable screening of COVID-19 patients to provide better and timely patient care and to combat the spread of the disease. In this context, recent studies have reported some key advantages of using routine blood tests for initial screening of COVID-19 patients. In this article, first we present a review of the emerging techniques for COVID-19 diagnosis using routine laboratory and/or clinical data. Then, we propose ERLX which is an ensemble learning model for COVID-19 diagnosis from routine blood tests. METHOD: The proposed model uses three well-known diverse classifiers, extra trees, random forest and logistic regression, which have different architectures and learning characteristics at the first level, and then combines their predictions by using a second level extreme gradient boosting (XGBoost) classifier to achieve a better performance. For data preparation, the proposed methodology employs a KNNImputer algorithm to handle null values in the dataset, isolation forest (iForest) to remove outlier data, and a synthetic minority oversampling technique (SMOTE) to balance data distribution. For model interpretability, features importance are reported by using the SHapley Additive exPlanations (SHAP) technique. RESULTS: The proposed model was trained and evaluated by using a publicly available data set from Albert Einstein Hospital in Brazil, which consisted of 5644 data samples with 559 confirmed COVID-19 cases. The ensemble model achieved outstanding performance with an overall accuracy of 99.88% [95% CI: 99.6-100], AUC of 99.38% [95% CI: 97.5-100], a sensitivity of 98.72% [95% CI: 94.6-100] and a specificity of 99.99% [95% CI: 99.99-100]. DISCUSSION: The proposed model revealed better performance when compared against existing state-of-the-art studies (Banerjee et al., 2020; de Freitas Barbosa et al., 2020; de Moraes Batista et al., 2020; Soares et al., 2020) [3,22,56,71] for the same set of features employed by them. As compared to the best performing Bayes Net model (de Freitas Barbosa et al., 2020) [22] average accuracy of 95.159%, ERLX achieved an average accuracy of 99.94%. In comparison with AUC of 85% reported by the SVM model (de Moraes Batista et al., 2020) [56], ERLX obtained AUC of 99.77% in addition to improvements in sensitivity, and specificity. As compared with ER-COV model (Soares et al., 2020) [71] average sensitivity of 70.25% and specificity of 85.98%, ERLX model achieved sensitivity of 99.47% and specificity of 99.99%. The ERLX model obtained a considerably higher score as compared with ANN model (Banerjee et al., 2020) [3] in all performance metrics. Therefore, the model presented is robust and can be deployed for reliable early and rapid screening of COVID-19 patients.