scispace - formally typeset
Search or ask a question
Book ChapterDOI

Performance Analysis of Psychological Disorders for a Clinical Decision Support System

TL;DR: The technology proposed in this paper, attempts to understand psychological case studies by identifying the psychological disorder they represent along with the severity of that particular case, with the help of a Multinomial Naive Bayes model for disorder identification and a regular expression based severity processing algorithm.
Abstract: In the domain of psychological practice, experts follow different methodologies for the diagnosis of psychological disorders and might change their line of treatment based on their observations from previous sessions. In such a scenario, a standardized clinical decision support system based on big data and machine learning techniques can immensely help professionals in the process of diagnosis as well as improve patient care. The technology proposed in this paper, attempts to understand psychological case studies by identifying the psychological disorder they represent along with the severity of that particular case, with the help of a Multinomial Naive Bayes model for disorder identification and a regular expression based severity processing algorithm. A knowledge base is created based on the knowledge of human experts of psychology. Psychological disorders however need not possess distinct symptoms to easily differentiate between them. Some are very closely connected with a variety of overlapping symptoms between them. Our work, in this paper, focuses on analyzing the performance of such psychological disorders represented in the form of case studies in a decision support system, with an aim of understanding this gray area of psychology.
References
More filters
Journal ArticleDOI
TL;DR: An issue concerning the criteria for tic disorders is highlighted, and how this might affect classification of dyskinesias in psychotic spectrum disorders.
Abstract: Given the recent attention to movement abnormalities in psychosis spectrum disorders (e.g., prodromal/high-risk syndromes, schizophrenia) (Mittal et al., 2008; Pappa and Dazzan, 2009), and an ongoing discussion pertaining to revisions of the Diagnostic and Statistical Manuel of Mental Disorders (DSM) for the upcoming 5th edition, we would like to take this opportunity to highlight an issue concerning the criteria for tic disorders, and how this might affect classification of dyskinesias in psychotic spectrum disorders. Rapid, non-rhythmic, abnormal movements can appear in psychosis spectrum disorders, as well as in a host of commonly co-occurring conditions, including Tourette’s Syndrome and Transient Tic Disorder (Kerbeshian et al., 2009). Confusion can arise when it becomes necessary to determine whether an observed movement (e.g., a sudden head jerk) represents a spontaneous dyskinesia (i.e., spontaneous transient chorea, athetosis, dystonia, ballismus involving muscle groups of the arms, legs, trunk, face, and/or neck) or a tic (i.e., stereotypic or patterned movements defined by the relationship to voluntary movement, acute and chronic time course, and sensory urges). Indeed, dyskinetic movements such as dystonia (i.e., sustained muscle contractions, usually producing twisting and repetitive movements or abnormal postures or positions) closely resemble tics in a patterned appearance, and may only be visually discernable by attending to timing differences (Gilbert, 2006). When turning to the current DSM-IV TR for clarification, the description reads: “Tic Disorders must be distinguished from other types of abnormal movements that may accompany general medical conditions (e.g., Huntington’s disease, stroke, Lesch-Nyhan syndrome, Wilson’s disease, Sydenham’s chorea, multiple sclerosis, postviral encephalitis, head injury) and from abnormal movements that are due to the direct effects of a substance (e.g., a neuroleptic medication)”. However, as it is written, it is unclear if psychosis falls under one such exclusionary medical disorder. The “direct effects of a substance” criteria, referencing neuroleptic medications, further contributes to the uncertainty around this issue. As a result, ruling-out or differentiating tics in psychosis spectrum disorders is at best, a murky endeavor. Historically, the advent of antipsychotic medication in the 1950s has contributed to the confusion about movement signs in psychiatric populations. Because neuroleptic medications produce characteristic movement disorder in some patients (i.e. extrapyramidal side effects), drug-induced movement disturbances have been the focus of research attention in psychotic disorders. However, accumulating data have documented that spontaneous dyskinesias, including choreoathetodic movements, can occur in medication naive adults with schizophrenia spectrum disorders (Pappa and Dazzan, 2009), as well as healthy first-degree relatives of chronically ill schizophrenia patients (McCreadie et al., 2003). Taken together, this suggests that movement abnormalities may reflect pathogenic processes underlying some psychotic disorders (Mittal et al., 2008; Pappa and Dazzan, 2009). More specifically, because spontaneous hyperkinetic movements are believed to reflect abnormal striatal dopamine activity (DeLong and Wichmann, 2007), and dysfunction in this same circuit is also proposed to contribute to psychosis, it is possible that spontaneous dyskinesias serve as an outward manifestation of circuit dysfunction underlying some schizophrenia-spectrum symptoms (Walker, 1994). Further, because these movements precede the clinical onset of psychotic symptoms, sometimes occurring in early childhood (Walker, 1994), and may steadily increase during adolescence among populations at high-risk for schizophrenia (Mittal et al., 2008), observable dyskinesias could reflect a susceptibility that later interacts with environmental and neurodevelopmental factors, in the genesis of psychosis. In adolescents who meet criteria for a prodromal syndrome (i.e., the period preceding formal onset of psychotic disorders characterized by subtle attenuated positive symptoms coupled with a decline in functioning), there is sometimes a history of childhood conditions which are also characterized by suppressible tics or tic like movements (Niendam et al., 2009). On the other hand, differentiating between tics and dyskinesias has also complicated research on childhood disorders such as Tourette syndrome (Kompoliti and Goetz, 1998; Gilbert, 2006). We propose consideration of more explicit and operationalized criteria for differentiating tics and dyskinesias, based on empirically derived understanding of neural mechanisms. Further, revisions of the DSM should allow for the possibility that movement abnormalities might reflect neuropathologic processes underlying the etiology of psychosis for a subgroup of patients. Psychotic disorders might also be included among the medical disorders that are considered a rule-out for tics. Related to this, the reliability of movement assessment needs to be improved, and this may require more training for mental health professionals in movement symptoms. Although standardized assessment of movement and neurological abnormalities is common in research settings, it has been proposed that an examination of neuromotor signs should figure in the assessment of any patient, and be as much a part of the patient assessment as the mental state examination (Picchioni and Dazzan, 2009). To this end it is important for researchers and clinicians to be aware of differentiating characteristics for these two classes of abnormal movement. For example, tics tend to be more complex than myoclonic twitches, and less flowing than choreoathetodic movements (Kompoliti and Goetz, 1998). Patients with tics often describe a sensory premonition or urge to perform a tic, and the ability to postpone tics at the cost of rising inner tension (Gilbert, 2006). For example, one study showed that patients with tic disorders could accurately distinguish tics from other movement abnormalities based on the subjective experience of some voluntary control of tics (Lang, 1991). Another differentiating factor derives from the relationship of the movement in question to other voluntary movements. Tics in one body area rarely occur during purposeful and voluntary movements in that same body area whereas dyskinesia are often exacerbated by voluntary movement (Gilbert, 2006). Finally, it is noteworthy that tics wax and wane in frequency and intensity and migrate in location over time, often becoming more complex and peaking between the ages of 9 and 14 years (Gilbert, 2006). In the case of dyskinesias among youth at-risk for psychosis, there is evidence that the movements tend to increase in severity and frequency as the individual approaches the mean age of conversion to schizophrenia spectrum disorders (Mittal et al., 2008). As revisions to the DSM are currently underway in preparation for the new edition (DSM V), we encourage greater attention to the important, though often subtle, distinctions among subtypes of movement abnormalities and their association with psychiatric syndromes.

67,017 citations

Journal Article
TL;DR: Diagnostic and statistical manual of mental disorders (DSM-5) was translated by psychiatrists and psychologists, mainly from the University psychiatric hospital Vrapce and published by the Naklada Slap publisher.
Abstract: Title: Diagnostic and statistical manual of mental disorders (DSM-5) Author: American Psychiatric Association Editors of Croatian Edition: Vlado Jukic, Goran Arbanas ISBN: 978-953-191-787-2 Publisher: Naklada Slap, Jastrebarsko, Croatia Number of pages: 936Diagnostic and statistical manual of mental disorders is a national classification, but since its third edition it became a worldwide used manual. [1] It has been published by the American Psychiatric Association and two years ago the fifth edition was released. [2] Croatian was among the first languages this book was translated to. [3] DSM-5 was translated by psychiatrists and psychologists, mainly from the University psychiatric hospital Vrapce and published by the Naklada Slap publisher.DSM has always been more publicly debated than the other main classification - the International Classification of Diseases (ICD). [4] The same happened with this fifth edition. Even before it was released, numerous individuals, organizations, groups and associations were publicly speaking about the classification, new diagnostic entities and changing criteria. [5]Although there is a tendency of authors of both DSM and ICD to synchronize these two classifications and to make them more harmonized with each new edition, there are several differences among them. While ICD covers all the diseases, disorders and reasons for making a contact with the health system, DSM covers "only" mental disorders. Other disorders (medical conditions, as they are named in DSM-5) are not included, except in situations when they lead to a development of a mental disorder. The other main difference is that DSM is more operational zed, and gives criteria for each of the disorders, listing how many criteria have to be met to make a diagnosis of a particular disorder, and what excluding criteria are.Due to the fact that it is used all around the globe and since it has become the most used psychiatric manual, it is sometimes said that DSM is a "psychiatric Bible". [6]Some critics of DSM say that it stigmatizes people and that in each edition it includes more diagnostic entities. It is true that in each edition of DSM there are more disorders listed, but this is due to the fact that medicine is a developing area and new insights are made every year, so some disorders are separated into different subtypes or subgroups and different new diagnoses, giving the impression more behaviour are being pathologized. The intention of the authors was to make more homogenous groups. But, the truth is that, compared with ICD, it is more difficult to get a diagnosis in DSM, than in ICD, with the same clinical presentation. [7] DSM requires functional impairment or distress to pathologize behaviour, while in ICD this criterion is not present in every case.During the process of developing DSM-5 there was an open public discussion. [2] For over a year any person was able to participate in the discussion about future criteria, inclusion or exclusion of diagnostic entities from DSM. More than 21000 letters was sent to the authors. This was the unprecedented way of developing a classification that ICD now tries to follow in preparation of its 11th edition.As a direct consequence of such an open and wide discussion, some new disorders were included (e.g. hoarding disorder), some were excluded even though they were included during the proposal period (e.g. hypersexual disorders), some were heavily debated (e.g. narcissistic personality disorder). [8-10]As previously mentioned, DSM and ICD systems try to harmonize more. There were more non-American authors included in DSM-5 than ever before and some of the experts in the field were in the task force of DSM-5 and ICD-11. [2, 11]What is new in DSM-5, compared to DSM-IV. The organization of the chapters has been changed, so now the flow of the disorders follow life cycle. The book starts with neurodevelopmental disorders, followed by schizophrenia, bipolar and depressive disorders, and closing with neurocognitive disorders. …

15,478 citations

Book
01 Jan 1973
TL;DR: In this article, a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition is provided, including Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.
Abstract: Provides a unified, comprehensive and up-to-date treatment of both statistical and descriptive methods for pattern recognition. The topics treated include Bayesian decision theory, supervised and unsupervised learning, nonparametric techniques, discriminant analysis, clustering, preprosessing of pictorial data, spatial filtering, shape description techniques, perspective transformations, projective invariants, linguistic procedures, and artificial intelligence techniques for scene analysis.

13,647 citations

Proceedings Article
21 Aug 2003
TL;DR: This paper proposes simple, heuristic solutions to some of the problems with Naive Bayes classifiers, addressing both systemic issues as well as problems that arise because text is not actually generated according to a multinomial model.
Abstract: Naive Bayes is often used as a baseline in text classification because it is fast and easy to implement. Its severe assumptions make such efficiency possible but also adversely affect the quality of its results. In this paper we propose simple, heuristic solutions to some of the problems with Naive Bayes classifiers, addressing both systemic issues as well as problems that arise because text is not actually generated according to a multinomial model. We find that our simple corrections result in a fast algorithm that is competitive with state-of-the-art text classification algorithms such as the Support Vector Machine.

1,050 citations