A primer on the use of machine learning to distil knowledge from data in biological psychiatry.

Applications of machine learning in the biomedical sciences are growing rapidly. This growth has been spurred by diverse cross-institutional and interdisciplinary collaborations, public availability of large datasets, an increase in the accessibility of analytic routines, and the availability of powerful computing resources. With this increased access and exposure to machine learning comes a responsibility for education and a deeper understanding of its bases and bounds, borne equally by data scientists seeking to ply their analytic wares in medical research and by biomedical scientists seeking to harness such methods to glean knowledge from data. This article provides an accessible and critical review of machine learning for a biomedically informed audience, as well as its applications in psychiatry. The review covers definitions and expositions of commonly used machine learning methods, and historical trends of their use in psychiatry. We also provide a set of standards, namely Guidelines for REporting Machine Learning Investigations in Neuropsychiatry (GREMLIN), for designing and reporting studies that use machine learning as a primary data-analysis approach. Lastly, we propose the establishment of the Machine Learning in Psychiatry (MLPsych) Consortium, enumerate its objectives, and identify areas of opportunity for future applications of machine learning in biological psychiatry. This review serves as a cautiously optimistic primer on machine learning for those on the precipice as they prepare to dive into the field, either as methodological practitioners or well-informed consumers.

Stability of anticholinergic load in Australian community-dwelling older people: a longitudinal analysis.

BACKGROUND: It is recommended that anticholinergic medication is avoided in older people, especially those with cognitive impairment. OBJECTIVE: To investigate anticholinergic load (ACL) over time in older primary care patients with and without cognitive impairment. METHODS: Community-dwelling general practice patients at baseline (n = 1768), at year one (n = 1373) and a restricted cohort (with possible or definite cognitive impairment) at year two (n = 370) had medication regimens documented by a research nurse during a home visit. Anticholinergic medicines were categorized as levels 1-3 (low-high potency) and summed for each participant as a measure of their ACL. RESULTS: Most participants had no change in ACL over time, but there was some turnover in the anticholinergic medications used. The mean change in ACL was 0.012 ± 0.99 from baseline to 12 months and -0.04 ± 1.3 from baseline to 24 months. Cardiovascular drugs were the most commonly used level 1 anticholinergics, followed by antidepressants and opioids. Antidepressants and urologicals were the most commonly used level 3 anticholinergics. The rate of anticholinergic deprescribing was equivalent to the rate of anticholinergic initiation, and commonly involved the level 1 drugs warfarin, furosemide and temazepam, and the level 3 drugs amitriptyline and oxybutynin. People with dementia had a higher ACL at baseline and year one compared with other participants. CONCLUSION: ACL of community-dwelling older people was very stable over time. This may represent lost opportunities for deprescribing as well as potentially inappropriate prescribing, particularly in those with cognitive impairment.

microRNA and the Post-Transcriptional Response to Oxidative Stress during Neuronal Differentiation: Implications for Neurodevelopmental and Psychiatric Disorders.

Oxidative stress is one of the most important environmental exposures associated with psychiatric disorders, but the underlying molecular mechanisms remain to be elucidated. In a previous study, we observed a substantial alteration of the gene expression landscape in neuron-like cells that were differentiated from SH-SY5Y cells after or during exposure to oxidative stress, with a subset of dysregulated genes being enriched for neurodevelopmental processes. To further explore the regulatory mechanisms that might account for such profound perturbations, we have now applied small RNA-sequencing to investigate changes in the expression of miRNAs. These molecules are known to play crucial roles in brain development and response to stress through their capacity to suppress gene expression and influence complex biological networks. Through these analyses, we observed more than a hundred differentially expressed miRNAs, including 80 previously reported to be dysregulated in psychiatric disorders. The seven most influential miRNAs associated with pre-treatment exposure, including miR-138-5p, miR-96-5p, miR-34c-5p, miR-1287-5p, miR-497-5p, miR-195-5p, and miR-16-5p, supported by at least 10 negatively correlated mRNA connections, formed hubs in the interaction network with 134 genes enriched with neurobiological function, whereas in the co-treatment condition, miRNA-mRNA interaction pairs were enriched in cardiovascular and immunity-related disease ontologies. Interestingly, 12 differentially expressed miRNAs originated from the DLK1-DIO3 location, which encodes a schizophrenia-associated miRNA signature. Collectively, our findings suggest that early exposure to oxidative stress, before and during prenatal neuronal differentiation, might increase the risk of mental illnesses in adulthood by disturbing the expression of miRNAs that regulate neurodevelopmentally significant genes and networks.

miRNA cargo in circulating vesicles from neurons is altered in individuals with schizophrenia and associated with severe disease.

While RNA expression appears to be altered in several brain disorders, the constraints of postmortem analysis make it impractical for well-powered population studies and biomarker development. Given that the unique molecular composition of neurons are reflected in their extracellular vesicles (EVs), we hypothesized that the fractionation of neuron derived EVs provides an opportunity to specifically profile their encapsulated contents noninvasively from blood. To investigate this hypothesis, we determined miRNA expression in microtubule associated protein 1B (MAP1B)-enriched serum EVs derived from neurons from a large cohort of individuals with schizophrenia and nonpsychiatric comparison participants. We observed dysregulation of miRNA in schizophrenia subjects, in particular those with treatment-resistance and severe cognitive deficits. These data support the hypothesis that schizophrenia is associated with alterations in posttranscriptional regulation of synaptic gene expression and provides an example of the potential utility of tissue-specific EV analysis in brain disorders.

Developmental vitamin D-deficiency increases the expression of microRNAs involved in dopamine neuron development.

Schizophrenia is a neurodevelopmental disorder associated with abnormal dopamine (DA) signalling and disruptions in early brain development. We have shown that developmental vitamin D-deficiency (DVD-deficiency) increases the risk of schizophrenia in offspring and impairs various aspects of brain development in rodents, particularly that of DA neurons, however the molecular basis of these impairments remains unclear. Here, we explore whether small non-coding microRNAs (miRNAs) are involved. miRNAs regulate gene expression post-transcriptionally via translational repression and destabilisation of mRNA. While dysregulation of multiple miRNAs has been reported in post-mortem brain of patients with schizophrenia, the biological pathways affected by these small RNAs are not clear. Here we identified differential expression of 18 miRNAs in DA neurons isolated from DVD-deficient embryos. Three miRNAs were selected for further functional studies of dopaminergic neuron differentiation based on their interactions with transcripts involved in neuronal maturation. In particular, we show upregulation of miR-181c-5p suppresses neurite outgrowth of dopaminergic neurons. These findings provide further evidence that an environmental risk factor for schizophrenia - DVD-deficiency - disrupts the development of DA neurons and suggests increased miRNA expression may be one possible mechanism. This disruption potentially underlies the long-term alterations in DA mediated brain function in DVD-deficient offspring, and by inference in schizophrenia.

The Alabama Structured Assessment of Treatment Completion for insanity acquittes (The AlaSATcom).

The most complex and risky decisions made by forensic psychiatrists revolve around the decision to release insanity acquittes from custody. This decision has several levels of risk, including the potential liability to the psychiatrist as well as the possible risk to the community. A single bad outcome, even if not predictable, can have disastrous results, not only for victims, but also for the releasing facility. Since predicting violence has so many problems, we chose to look at completeness of treatment instead, so we could say to the Court, "We don't know about violence, but we do know that he has vastly improved." Since many NGRI (Not Guilty by Reason of Insanity) patients spend years in the hospital, they are also expensive. They have rights, as well; therefore the complex assessment must be done as quickly and as accurately as possible. We have developed a spread sheet program to compare these multiple factors, and have compared it against the clinical decisions we have made in more than 100 discharges. We believe this gives a framework for decision-making that will increase the consistency of this process.

Input that contradicts young children's strategy for mapping novel words affects their phonological and semantic interpretation of other novel words.

Children tend to choose an entity they cannot already label, rather than one they can, as the likely referent of a novel noun. The effect of input that contradicts this strategy on the interpretation of other novel nouns was investigated. In pre- and posttests, 4-year-olds were asked to judge whether novel nouns referred to "name-similar" familiar objects or novel objects (e.g., whether japple referred to an apple or a binder clip). During an intervening treatment phase, they were asked to pick the referents of novel nouns from pairs of familiar objects (Experiments 1 and 3) or were taught subordinate names for familiar objects (Experiment 2). Most resisted the lure of phonological similarity in the pretest but increased selection of name-similar familiar objects over novel ones in the posttest. In Experiment 3, which involved monosyllables that differed in initial phoneme from the familiar words, treatment produced this effect only when accompanied by a rhyme-sensitization procedure. Experiment 2 included two other age groups: 2-year-olds, who were less resistant to phonological similarity in the pretest and responded to the treatment like the 4-year-olds; and adults, who nearly always selected the novel objects in the pretest and posttest. For children, the impact of treatment was positively associated with ability to detect phonological similarity and negatively associated with vocabulary size.

BDNF and the maturation of posttranscriptional regulatory networks in human SH-SY5Y neuroblast differentiation.

The SH-SY5Y culture system is a convenient neuronal model with the potential to elaborate human/primate-specific transcription networks and pathways related to human cognitive disorders. While this system allows for the exploration of specialized features in the human genome, there is still significant debate about how this model should be implemented, and its appropriateness for answering complex functional questions related to human neural architecture. In view of these questions we sought to characterize the posttranscriptional regulatory structure of the two-stage ATRA differentiation, BDNF maturation protocol proposed by Encinas et al. (2000) using integrative whole-genome gene and microRNA (miRNA) expression analysis. We report that ATRA-BDNF induced significant increases in expression of key synaptic genes, brain-specific miRNA and miRNA biogenesis machinery, and in AChE activity, compared with ATRA alone. Functional annotation clustering associated BDNF more significantly with neuronal terms, and with synaptic terms not found in ATRA-only clusters. While our results support use of SH-SY5Y as a neuronal model, we advocate considered selection of the differentiation agent/s relative to the system being modeled.

Pediatric short-bowel syndrome: the cost of comprehensive care.

BACKGROUND: Little information is available about the financial charges incurred by patients with short-bowel syndrome (SBS). This is particularly true for pediatric SBS patients who receive some of the most complex medical care. OBJECTIVES: The aims of this study were to determine the total cost of care for these patients and to analyze their utilization of home and hospital-based health care services. DESIGN: This was a retrospective review of the total charges incurred by 41 children with SBS over the past decade, encompassing both inpatient and home-care charges. RESULTS: The mean (+/- SD) total cost of care for pediatric SBS was US$505 250 +/- US$248 398 (corrected for inflation to the year 2005) for the first year of care alone. Inpatient hospitalization accounted for most of these expenses (US$416 818 +/- US$242 689, or 82% of the total), and this was attributable to prolonged requirements for intensive care resources, numerous surgical procedures, and multiple readmissions during the first year of diagnosis. Hospital-based costs steadily declined in subsequent years, but home-care services, in stark contrast, unexpectedly increased every year for the first 5 y of diagnosis-a trend that was highly significant (P < 0.005), reaching US$184 520 +/- US$111 075 for the fifth year of home care. This increasing cost was attributable to increasing complications of parenteral nutrition, especially infectious complications. Although per-patient charges varied widely, the mean total cost of care per child over a 5-y period was US$1 619 851 +/- US$1 028 985. A strong correlation was found between higher charges and infants with <10% of predicted small-bowel length. CONCLUSIONS: This study was the first to calculate the total costs for pediatric SBS patients and to provide an in-depth analysis of these patients' actual utilization of health care services. This information may help guide health care providers and families who have children with SBS. The comprehensive care of pediatric SBS patients costs significantly more than has previously been estimated. Contrary to previous views, home care significantly increases each year after diagnosis.

When mitigation evidence makes a difference: effects of psychological mitigating evidence on sentencing decisions in capital trials.

Little empirical research has addressed the effects of psychological or psychosocial evidence on sentencing decisions. The present study found that death-qualified mock jurors were more likely to sentence a defendant to death without mitigating evidence than in a case with mitigating evidence present. Mock jurors were less likely to assign a death sentence in cases that contained one of the following types of mitigating evidence: The defendant was (i) diagnosed with schizophrenia, not medicated, and suffered from severe delusions and hallucinations, (ii) drug addicted and high at the time of the murder, (iii) diagnosed as borderline mentally retarded during childhood, or (iv) severely physically and verbally abused by his parents during childhood.