Can machine learning be useful as a screening tool for depression in primary care?

Depression is a widespread disease with a high economic burden and a complex pathophysiology disease that is still not wholly clarified, not to mention it usually is associated as a risk factor for absenteeism at work and suicide. Just 50% of patients with depression are diagnosed in primary care, and only 15% receive treatment. Stigmatization, the coexistence of somatic symptoms, and the need to remember signs in the past two weeks can contribute to explaining this situation. In this context, tools that can serve as diagnostic screening are of great value, as they can reduce the number of undiagnosed patients. Besides, Artificial Intelligence (AI) has enabled several fruitful applications in medicine, particularly in psychiatry. This study aims to evaluate the performance of Machine Learning (ML) algorithms in the detection of depressive patients from the clinical, laboratory, and sociodemographic data obtained from the Brazilian National Network for Research on Cardiovascular Diseases from June 2016 to July 2018. The results obtained are promising. In one of them, Random Forests, the accuracy, sensibility, and area under the receiver operating characteristic curve were, respectively, 0.89, 0.90, and 0.87.

Imaging spinal cord activity in behaving animals.

The spinal cord is the primary neurological link between the brain and peripheral organs. How important it is in everyday life is apparent in patients with spinal cord injury or motoneuron disease, who have dramatically reduced musculoskeletal control or capacity to sense their environment. Despite its crucial role in sensory and motor processing little is known about the cellular and molecular signaling events that underlie spinal cord function under naturalistic conditions. While genetic, electrophysiological, pharmacological, and circuit tracing studies have revealed important roles for different molecularly defined neurons, these approaches insufficiently describe the moment-to-moment neuronal and non-neuronal activity patterns that underlie sensory-guided motor behaviors in health and disease. The recent development of imaging methods for real-time interrogation of cellular activity in the spinal cord of behaving mice has removed longstanding technical obstacles to spinal cord research and allowed new insight into how different cell types encode sensory information from mechanoreceptors and nociceptors in the skin. Here, we review the current state-of-the-art in interrogating cellular and microcircuit function in the spinal cord of behaving mammals and discuss current opportunities and technological challenges.

Phosphatidylserine Exposure Controls Viral Innate Immune Responses by Microglia.

Microglia are the intrinsic immune sentinels of the central nervous system. Their activation restricts tissue injury and pathogen spread, but in some settings, including viral infection, this response can contribute to cell death and disease. Identifying mechanisms that control microglial responses is therefore an important objective. Using replication-incompetent adenovirus 5 (Ad5)-based vectors as a model, we investigated the mechanisms through which microglia recognize and respond to viral uptake. Transgenic, immunohistochemical, molecular-genetic, and fluorescence imaging approaches revealed that phosphatidylserine (PtdSer) exposure on the outer leaflet of transduced cells triggers their engulfment by microglia through TAM receptor-dependent mechanisms. We show that inhibition of phospholipid scramblase 1 (PLSCR1) activity reduces intracellular calcium dysregulation, prevents PtdSer externalization, and enables months-long protection of vector-transduced, transgene-expressing cells from microglial phagocytosis. Our study identifies PLSCR1 as a potent target through which the innate immune response to viral vectors, and potentially other stimuli, may be controlled.

Imaging large-scale cellular activity in spinal cord of freely behaving mice.

Sensory information from mechanoreceptors and nociceptors in the skin plays key roles in adaptive and protective motor behaviours. To date, very little is known about how this information is encoded by spinal cord cell types and their activity patterns, particularly under freely behaving conditions. To enable stable measurement of neuronal and glial cell activity in behaving mice, we have developed fluorescence imaging approaches based on two- and miniaturized one-photon microscopy. We show that distinct cutaneous stimuli activate overlapping ensembles of dorsal horn neurons, and that stimulus type and intensity is encoded at the single-cell level. In contrast, astrocytes show large-scale coordinated calcium responses to intense but not weak sensory inputs. Sensory-evoked activity is potently suppressed by anaesthesia. By revealing the cellular and computational logic of spinal cord networks under behaving conditions, our approach holds promise for better understanding of healthy and aberrant spinal cord processes.