=Paper=
{{Paper
|id=Vol-2472/p9
|storemode=property
|title=A comprehensive solution for psychological treatment and therapeutic path planning based on knowledge base and expertise sharing
|pdfUrl=https://ceur-ws.org/Vol-2472/p9.pdf
|volume=Vol-2472
|authors=Samuele Russo,Christian Napoli
}}
==A comprehensive solution for psychological treatment and therapeutic path planning based on knowledge base and expertise sharing==
https://ceur-ws.org/Vol-2472/p9.pdf
A comprehensive solution for psychological
treatment and therapeutic path planning based on
knowledge base and expertise sharing
Samuele Russoa and Christian Napolib
a Advanced specialization student, University of Palermo
Piazza Marina 61, Palermo 90133 PA, Italy
samuelerussoct@gmail.com
b Department of Mathematics and Computer Science, University of Catania
Viale Andrea Doria 6, Catania 95126 CT, Italy
napoli@dmi.unict.it
Abstract—The healthcare systems are nowadays going trough testing among different patients. Moreover trough standardiza-
a broad standardization process so that the caregivers are guided tion the caregivers are guided in making decisions regarding
in making decisions regarding the diagnosis and the therapeutic the more appropriate therapeutic plan for a specific conditions,
plannning. Differently from other fields of medicine, psychology
does not base its protocol on drugs and prescription, and neither while the medical practices can be rationalized improving, in
on standard surgical procedures. In this work we present a the end, the general outcome for the therapy at full advantage
software solution to support psychologists during their decision of the patient’s well being.
making process, helping them both during the diagnosis and the Unfortunately for several field of healthcare standardization
treatment of psychological patients. The developed software is is not easily feasible and sometimes even impossible due to the
structured as a twofold application: it returns a set of clinical
decision rule starting from the definitions contained on the extreme variability of the human subjects and their afflictions.
Diagnostic and Statistical Manual of Mental Disorder, but joining Differently from other fields of medicine, psychology does
the approach with a consensus-based clinical practice oriented not base its protocol on drugs and prescription, and neither
approach. The first is realized by applying knowledge base to the on standard surgical procedures. It follows that, while the
research of well structured standard practices, while the second diagnostics assessment of a psychological patient is based
is obtained by means of expertise sharing from a network of
psychologists. This latter characteristic not only allows us to share on well standardized tests and observations, the therapeutic
experiences and tips among expert operators, but also to integrate plan, while grossly defined, must be adapted to the peculiar
a scoring and evaluation system for to guide the choice of the user personality and characteristics of each patient. It follows that
among comparable practices. The prototype has been tested and a psychological treatment and its therapeutic path plan must
highly appreciated with an overall 96% of good evaluations. We mainly rely on the therapist experience and knowledge of
believe that such a support could build the basis of an entire set
of support software tools for medical and psychological diagnosis similar scenario.
and treatment. On the contrary many other fields of medicine can rely
Index Terms—component, formatting, style, styling, insert on very effective clinical prediction rules in order to reduce
the uncertainty inherent the medical practice by defining how
I. I NTRODUCTION to use clinical findings to make predictions [1]. Clinical
In the recent years the field of medicine and healthcare prediction rules are derived from systematic clinical observa-
have gone trough a broad standardization process by means tions. They can help physicians identify patients who require
of therapeutic protocols and standard procedures to be applied diagnostic tests, treatment, or hospitalization [2].
by physicians, caregivers and healthcare operators in general. We can define a clinical decision rule as a decision making
Obviously the introduction of standard protocols helps both tool that is derived from original research and incorporates
the physician and the patients by means of a well scheduled variables from the history, physical examination, or simple
and well experimented and refined therapeutic path. tests [3]. In [4] the development process of clinical decision
While standardization comes with a price, since it results rules has been originally described.
in a lack of customization for the developed therapy, it also On the other hand clinical decision rule must be based on
presents great advantages in terms of comparability and results evidences, when no evidence-based guideline exists, i.e. due
to the extreme variability of a disease, then a consensus-based
©2019 for this paper by its authors. Use permitted under Creative clinical practice guideline is the best option [5]. This latter
Commons License Attribution 4.0 International (CC BY 4.0) is often used for psychological treatments planning, sometime
41
also along with more orthodox clinical decision rules. Finally, acute headache and demonstrate that their best bedside de-
it must be said that in certain cases it is uttermost difficult cision rule identified all cases of subarachnoid hemorrhage
to draw methodology-proof clinical practice guidelines due to among emergency department patients presenting with new,
the extreme statistical and subjective variability of the matter isolated headaches. In [22] uses fuzzy decision-making rules
at hand [6]. adapted to classification problems by using the methodology
It follows that physicians, therapists, psychologists, and of exploratory analysis followed by unification of particular
caregivers in general could obtain great advantages from decision rules into fuzzy groups. The fuzzyfication of such
specific support systems in order to be informed of the existing rules in facts can introduce an ‘useful randomness which is
decision making rules. When such rules are not available it often the key requirement for a large point of view often
could be of great use to be made aware of the common clinical required in differential diagnosis. In facts shown in [23] several
decision rules at hand. On the other hand, end especially in this ambiguous pathological conditions can lead to the possible
latter scenario, extreme benefit is reached by communicating diagnosis of suspected deep venous thrombosis, on the other
with other colleagues to share knowledge and feedback about hand in this case is the physicians’ judgement that takes over
their clinical practices. the decision rules. Moreover, while many authors tried to
In this work we present a software solution to support reach a universal model of diagnostic reasoning [24], ir is
psychologists during their decision making process, helping common knowledge that the physicians’ personal experiences,
them both during the diagnosis and the treatment of psy- skills and diagnostic abilities hold a key role on the decision
chological patients. The developed software is structured as making process [25]. This latter is also often self-regulated by
a twofold application: it returns a set of clinical decision rule precise ad well as perfectible psychological mechanisms [26].
starting from the definitions contained on the DSM-5, the Individuals’ independent judgment as well as common and
Diagnostic and Statistical Manual of Mental Disorders [7], but shared experiences are therefore the basis for a good diagnostic
joining the approach with a consensus-based clinical practice process [27], on the other hand such a process cannot neglect a
oriented approach. The first is realized by applying knowledge minimum standardization requirement which decision-making
base to the research of well structured standard practices, rules help to fulfill. In facts it has been shown that diagnostic
while the second is obtained by means of expertise sharing decisions can be generally improved when a decision-making
from a network of psychologists. This latter characteristic rules are associated with a knowledge-based approach [28].
not only allows us to share experiences and tips among From this short survey of the literature it follows that while
expert operators, but also to integrate a scoring and evaluation therapeutic path planning must be based on a set of codified
system for to guide the choice of the user among comparable rules, it also retain a paramount dependence from common
practices [8], [9]. knowledge. The first requirement can be fulfilled by using
The paper is organized as follows. After this brief intro- techniques such as knowledge base, while the second can
duction, in the following Section III the designed system is be implemented by means of a customized expertise sharing
described in its constituent parts. In Section IV we will focus support system. These two aspect have been integrated by the
on the management of the cloud services giving further details solution that will be explained in the following.
on the resource allocation policies. Finally in Section V we
will report a pilot case study and the obtained results. Finally III. T HE DEVELOPED SYSTEM
in Section VI we will draw our conclusions. In Figure 1 a gross schema of the designed system is
reported, this is composed by the following components:
II. R ELATED WORKS I. Frontend:
Decision making rules have been adopted since many years • Online interface
and with different purposes. E. g. in [10] descision making • DNS handler
rules have been developed as a guide for hospitalization II. Backend:
of patients presenting community-acquired pneumonia, while A. QoS handler
in [11]–[13] decision making rules are adopted to define when • Local Search Visibility component (LSV)
x-rays are needed in acute ankle injuries. In facts such a • Secure Sockets Layer (SSL)
support tool is often used for trauma treatments and when • HTTP caching component
diagnostical imagery is involved [14], [15].
B. Cloud VM
There are many works in literature about the extraction
• Apache service
and formulation of decision making rules. In [16] decision
• Local Storage
making rules have been extracted by means of a decision
• Local cluster cache service
tree [17]–[20] for the diagnostic workup of patients with
• Computing nodes (CN)
Meniere’s disease, vestibular schwannoma, traumatic vertigo,
• Storage Units (SU)
sudden deafness, benign paroxysmal positional vertigo, and
vestibular neuritis. In [21] the authors present the results of C. Cloud Services
a prospective, cross-sectional study involving patients with • Job queque component
42
USER
QOS HANDLER DISTRIBUTED DB
HTTP LOG
LSV SSL
caching HANDLER
Local
storage
DNS NAMESERVER
CLOUD VM
Apache
Local
Local Cluster
storage Slave
cache DB
CLOUD SERVICES
Job Main
Queque DB
Fig. 1: Schematics of the developed system.
D. Cloud Services granted the ability to execute JavaScript on a browser-like
• Log handler application. Although a web browser would have sufficed to
• Local storage interface with the online service, we developed a simple ad-
• Slave database hoc application to oversimplify the interface. In this manner
• Main database it is possible to avoid unnecessary distractions during the test
The components are better described in the following. execution. Finally a psychologist provided with the necessary
credentials can log into the system to administer the test to a
A. Frontend patient once such a test has been standardized and approved to
The frontend of the system has been developed by means be used. The frontend remote client only provides the interface
of the Angular JS [29], [30] framework in order to grant for the final users.
portability and compatibility with almost all the available
hardware and software systems. In this manner there are no
particular requirements to interface with the developed system, In the following the backend is described.
43
USER AMAZON LEX IOT RULE
AMAZON
AMAZON S3 AWS IOT CORE
API GATEWAY
AMAZON KINESIS AMAZON
DATA STREAM DYNAMO DB
AMAZON
POLY
AMAZON
AMAZON
DYNAMO DB
PINPOINT
STREAMS
INTERFACE CLOUD
Fig. 2: The adopted Amazon Web Services (AWS) configuration and the relative data flow among the different component and
services within the cloud environment
.
B. QoS Handler C. Cloud VM
The virtual machine when allocated run an Apache servie
daemon, in this manner a simple set of queries makes it pos-
For distributed systems to properly react to peaks of sible for the user to interact with the system in order to select,
requests, their adaptation activities would benefit from the extract and store data from and to the base, distributed on
estimation of the amount of requests. We implemented a a several storage units. Each VM retains on its local storage only
solution to adapt server-side resources on-the-fly. In order to a portion of the distributed databases, in fact the connection
ensure a minimum level of quality of service (QoS), even to such a VM depends on the required portion of data and the
when sudden variations on the number of requests arise, a related operations. The data are then updated connecting with
large number of (over-provisioned) resources is often used, a a slave database which retain a potentially updated version of
hence incurring into relevant costs and wasted resources for a the data. Each VM keep trace of the required updates by means
considerable time interval. We wanted to guarantee a minimum of a local cluster cache, this latter is responsible to signal the
QoS level once the connection has been established by using necessary global updates to the job queue scheduler.
resource allocation and adaption algorithms.
Moreover, in order to minimize bandwidth and resources D. Cloud services
usage we implemented an internal local search visibility The cloud resources are allocated both for computational
component (LSV) and an integrated HTTP caching system. and provisional purposes. The details on the cloud policies
In this manner the internal research engine can spare the are given in the following Section IV. The cloud service layer
user a pedant manual search between the existent records. is responsible for the update and merge procedure between the
Moreover due to obvious privacy and security requirements we temporary slave databases and the main database. The reason
also implemented a Secure Sockets Layer (SLL) connection for this double database system is the time required for a global
between the interface and the HTTP caching service. This update and merge phase, since this latter is extremely expen-
latter maintains a record of headers and tags to index the sive in terms of time and resources consumption. Therefore it
knowledge base content and speed up the internal research is more suitable to live store temporary slave DB the updates,
and retrieval of the required information. while delegate at scheduled time both the global merging and
44
update, and the distribution of shadow temporary copies to the 4) Symptoms do not occur exclusively during the
slave DBs. course of schizophrenia or another psychotic dis-
The users sessions are logged and stored on a local storage order, and are not better explained by another
represented by a replicated sql database. The process is mental disorder (eg, mood disorder, anxiety dis-
handled by a LOG handler component. order, dissociative disorder, personality disorder,
substance intoxication, or withdrawal).
IV. T HE CLOUD ENVIRONMENT
Since the system has been applied in Italy , given the known
For this work we took advantage of the Amazon Web association between ADHD and impaired performance on neu-
Services (AWS) [31], and particularly on the AWS ECS and ropsychological tests due to the effects of ADHD symptoms on
S3 service [32] (see Figure 2). speed and performance on a non-verbal intellectual test [34],
The resource request is provided to the cloud manager the interface also reports the official guidelines written by the
component which uses the Amazon AWS APIs to effectively Italian Society of Infantry and Adolescence NeuroPsychiatry
request the allocation of new virtual machines. The cloud and approved by many official associations and operator’s
administration is up to the AWS IoT Core taking into consider- syndicates. Therefore it also reports that the following tests
ation the AWS IoT rule component that determine the policies are commonly used:
for the Amazon Kinesis Data Stream. The Amazon Kinesis
1) Child Behavior CheckList (CBCL) [35]
Data Stream is a real-time streaming service that provides
2) Conners Rating Scales (CRS) [36]
event-driven messaging and supports extended microservice
3) Disruptive Behavior Disorder Rating Scale
architectures. This latter allows the processing requests trough
(DBD) [37]
the Amazon API Gateway once an admin has been logged and
4) ADHD Rating Scale IV [38]
identified trough his credentials by the Amazon Lex component
5) SNAP-IV [39]
to access the Amazon S3 service.
6) Diagnostic Interview for Children and Adoles-
In our system design also the database is distributed on
cents (DICA) [40]
the cloud and supported by the Amazon DynamoDB services
7) Kiddie-Schedule for Affective Disorders and
that allows data flow by means of the Amazon DynamoDb
Schizophrenia (K-SADS) [41]
Streams component. Data transactions and session state are en-
8) Ravens Standard Progressive Matrices
crypted at-rest and securely managed in the high-performance
(RSPM) [42]
and scalable NoSQL datastore offered by DynamoDB. The
Amazon DynamoDB Streams is also able to trigger an AWS While the system will shows these guidelines, it will also
Lambda function in order to send notifications, by means of highlight a note written by a colleague psychologist that says:
the Amazon Pinpoint and Amazon Polly services. The DSM-5 manual extends from 7 years to 12 years
An example of the system in action is provided in the the age limit for the comparisons of ADHD related
following Section V. symptoms.
Finally, while the system proposes an high scoring for the
V. A CASE STUDY suggested procedures, it also shows tips and comments from
Let suppose that a psychologist wants to diagnose a patient other colleagues which commonly positively rated the follow-
with attention deficit hyperactivity disorder (ADHD): a men- ing advice:
tal disorder of the neurodevelopmental type [33]. When the It can be helpful and good practice to associate
psychologist searches the relative keywords on the system the the Ravens Standard Progressive Matrices with
ADHD diagnosis will be suggested and associated with the in- the Leiter International Performance Scale Revised
formation contained within the DSM-5 diagnostic manual [7]: (Leiter-R).
1) Five or more symptoms of inattention and/or ≥ 5 Then leading the user to use the Leiter-R test [43].
symptoms of hyperactivity/impulsivity must have While the reported case is only an example, the system has
persisted for ≥ 6 months to a degree that is been tested with the help of 25 psychologists that, after using
inconsistent with the developmental level and neg- the developed system, evaluated the overall performances
atively impacts social and academic/occupational and utility as an asset for their profession.Figure 3 shows
activities. Several symptoms (inattentive or hyper- the results of such a poll that indicated an high degree of
active/impulsive) were present before the age of appreciation for the developed solution with 96% of good
12 years. evaluations among the overall received scores.
2) Several symptoms (inattentive or hyperac-
tive/impulsive) must be present in ≥ 2 settings VI. C ONCLUSION
(eg, at home, school, or work; with friends or In this work we developed a software solution to support
relatives; in other activities). psychologists during their decision making process, helping
3) There is clear evidence that the symptoms inter- them both during the diagnosis and the treatment of psycho-
fere with or reduce the quality of social, academic, logical patients. The application offers a set of clinical decision
or occupational functioning. rule starting from the definitions contained on the DSM-5
45
Fig. 3: Experts’ scoring of the developed system (1 is the lower grade, while 5 is the highest grade).
as well as the evaluations and advises of other colleagues. [11] Ian G Stiell, Gary H Greenberg, R Douglas McKnight, Rama C Nair,
The prototype has been tested and highly appreciated with I McDowell, and James R Worthington. A study to develop clinical
decision rules for the use of radiography in acute ankle injuries. Annals
an overall 96% of good evaluations. We believe that such of emergency medicine, 21(4):384–390, 1992.
a support could build the basis of an entire set of support [12] Clement J McDonald and J Marc Overhage. Guidelines you can follow
software tools for medical and psychological diagnosis and and can trust: an ideal and an example. Jama, 271(11):872–873, 1994.
[13] John H Wasson and Harold C Sox. Clinical prediction rules: have they
treatment. come of age? Jama, 275(8):641–642, 1996.
[14] Cynthia Madden, Donald B Witzke, Arthur B Sanders, John Valente, and
ACKNOWLEDGMENT Mark Fritz. High-yield selection criteria for cranial computed tomogra-
This work has been supported by “Piano della Ricerca phy after acute trauma. Academic Emergency Medicine, 2(4):248–253,
1995.
2016/2018 - linea di intervento 2, University of Catania”. [15] Ian D Graham, Ian G Stiell, Andreas Laupacis, Annette M O’Connor,
and George A Wells. Emergency physicians’ attitudes toward and use of
R EFERENCES clinical decision rules for radiography. Academic Emergency Medicine,
5(2):134–140, 1998.
[1] Brendan M Reilly and Arthur T Evans. Translating clinical research
[16] Erna Kentala, Ilmari Pyykkö, Kati Viikki, and Martti Juhola. Production
into clinical practice: impact of using prediction rules to make decisions.
of diagnostic rules from a neurotologic database with decision trees.
Annals of internal medicine, 144(3):201–209, 2006.
Annals of Otology, Rhinology & Laryngology, 109(2):170–176, 2000.
[2] John H Wasson, Harold C Sox, Raymond K Neff, and Lee Goldman.
Clinical prediction rules: applications and methodological standards. [17] Wei-Yin Loh. Classification and regression trees. Wiley Interdisciplinary
New England Journal of Medicine, 313(13):793–799, 1985. Reviews: Data Mining and Knowledge Discovery, 1(1):14–23, 2011.
[3] Andreas Laupacis, Nandita Sekar, et al. Clinical prediction rules: a [18] Tin Kam Ho. Random decision forests. In Proceedings of 3rd inter-
review and suggested modifications of methodological standards. Jama, national conference on document analysis and recognition, volume 1,
277(6):488–494, 1997. pages 278–282. IEEE, 1995.
[4] Alvan R Feinstein. Clinimetrics. Yale University Press, 1987. [19] Simon Bernard, Laurent Heutte, and Sebastien Adam. On the selection
[5] Tetsuo Ashizawa, Cynthia Gagnon, William J Groh, Laurie Gutmann, of decision trees in random forests. In 2009 International Joint
Nicholas E Johnson, Giovanni Meola, Richard Moxley, Shree Pandya, Conference on Neural Networks, pages 302–307. IEEE, 2009.
Mark T Rogers, Ericka Simpson, et al. Consensus-based care recommen- [20] Jehad Ali, Rehanullah Khan, Nasir Ahmad, and Imran Maqsood. Ran-
dations for adults with myotonic dystrophy type 1. Neurology: Clinical dom forests and decision trees. International Journal of Computer
Practice, 8(6):507–520, 2018. Science Issues (IJCSI), 9(5):272, 2012.
[6] Terrence M Shaneyfelt, Michael F Mayo-Smith, and Johann Rothwangl. [21] David E Newman-Toker and Jonathan A Edlow. High-stakes diagnostic
Are guidelines following guidelines?: The methodological quality of decision rules for serious disorders: the ottawa subarachnoid hemorrhage
clinical practice guidelines in the peer-reviewed medical literature. Jama, rule. JAMA, 310(12):1237–1239, 2013.
281(20):1900–1905, 1999. [22] NA Korenevskiy. Application of fuzzy logic for decision-making in
[7] American Psychiatric Association et al. Diagnostic and statistical man- medical expert systems. Biomedical Engineering, 49(1):46–49, 2015.
ual of mental disorders, fifth edition (DSM-5®). American Psychiatric [23] Geert-Jan Geersing, Kristel J Janssen, Ruud Oudega, Henk van Weert,
Pub, 2013. Henri Stoffers, Arno Hoes, Karel Moons, AMUSE Study Group, et al.
[8] Kathleen N Lohr, Marilyn J Field, et al. Guidelines for clinical practice: Diagnostic classification in patients with suspected deep venous throm-
from development to use. National Academies Press, 1992. bosis: physicians’ judgement or a decision rule? Br J Gen Pract,
[9] Michael D Cabana, Cynthia S Rand, Neil R Powe, Albert W Wu, 60(579):742–748, 2010.
Modena H Wilson, Paul-Andre C Abboud, and Haya R Rubin. Why [24] Pat Croskerry. A universal model of diagnostic reasoning. Academic
don’t physicians follow clinical practice guidelines?: A framework for medicine, 84(8):1022–1028, 2009.
improvement. Jama, 282(15):1458–1465, 1999. [25] Robert Wood and Albert Bandura. Impact of conceptions of ability on
[10] Michael J Fine, Thomas E Auble, Donald M Yealy, Barbara H Hanusa, self-regulatory mechanisms and complex decision making. Journal of
Lisa A Weissfeld, Daniel E Singer, Christopher M Coley, Thomas J personality and social psychology, 56(3):407, 1989.
Marrie, and Wishwa N Kapoor. A prediction rule to identify low-risk [26] John A Swets, Robyn M Dawes, and John Monahan. Psychological
patients with community-acquired pneumonia. New England journal of science can improve diagnostic decisions. Psychological science in the
medicine, 336(4):243–250, 1997. public interest, 1(1):1–26, 2000.
46
[27] Ralf HJM Kurvers, Stefan M Herzog, Ralph Hertwig, Jens Krause, [53] Max Gluckman. Clinical psychology: The study of personality and
Patricia A Carney, Andy Bogart, Giuseppe Argenziano, Iris Zalaudek, behavior. Routledge, 2017.
and Max Wolf. Boosting medical diagnostics by pooling indepen- [54] Andrew M Pomerantz. Clinical psychology: Science, practice, and
dent judgments. Proceedings of the National Academy of Sciences, culture. Sage Publications, 2016.
113(31):8777–8782, 2016. [55] David Watson and Lee Anna Clark. Clinical diagnosis at the crossroads.
[28] Luiz Moutinho, Paulo Rita, and Shuliang Li. Strategic diagnostics and Clinical Psychology: Science and Practice, 13(3):210–215, 2006.
management decision making: a hybrid knowledge-based approach. In- [56] Donald A Rock, Charles E Werts, and Ronald L Flaugher. The use of
telligent Systems in Accounting, Finance & Management: International analysis of covariance structures for comparing the psychometric prop-
Journal, 14(3):129–155, 2006. erties of multiple variables across populations. Multivariate Behavioral
[29] Brad Green and Shyam Seshadri. AngularJS. ” O’Reilly Media, Inc.”, Research, 13(4):403–418, 1978.
2013. [57] Cyril Burt. The factorial analysis of qualitative data. British Journal of
[30] Peter Bacon Darwin and Pawel Kozlowski. AngularJS web application Statistical Psychology, 3(3):166–185, 1950.
development. Packt Publ., 2013. [58] Ingwer Borg and Patrick Groenen. Modern multidimensional scal-
[31] James Murty. Programming amazon web services: S3, EC2, SQS, FPS, ing: Theory and applications. Journal of Educational Measurement,
and SimpleDB. ” O’Reilly Media, Inc.”, 2008. 40(3):277–280, 2003.
[32] Zhiwu Xie, Yinlin Chen, Tingting Jiang, Julie Speer, Tyler Walters, [59] Leonard Kaufman and Peter J Rousseeuw. Finding groups in data: an
Pablo A Tarazaga, and Mary Kasarda. On-demand big data analysis in introduction to cluster analysis, volume 344. John Wiley & Sons, 2009.
digital repositories: A lightweight approach. In International Conference
on Asian Digital Libraries, pages 274–277. Springer, 2015.
[33] Ariane Sroubek, Mary Kelly, and Xiaobo Li. Inattentiveness in attention-
deficit/hyperactivity disorder. Neuroscience bulletin, 29(1):103–110,
2013.
[34] Emily Goodwin, Gisli H Gudjonsson, Jon Fridrik Sigurdsson, and Susan
Young. The impact of adhd symptoms on intelligence test achievement
and speed of performance. Personality and Individual Differences,
50(8):1273–1277, 2011.
[35] Thomas M Achenbach and Craig Edelbrock. Child behavior checklist
(cbcl). 1983.
[36] C Keith Conners. Conners 3. MHS, 2008.
[37] William E Pelham Jr, Elizabeth M Gnagy, Karen E Greenslade, and
Richard Milich. Teacher ratings of dsm-iii-r symptoms for the disruptive
behavior disorders. Journal of the American Academy of Child &
Adolescent Psychiatry, 31(2):210–218, 1992.
[38] George J DuPaul, Thomas J Power, Arthur D Anastopoulos, and
Robert Reid. ADHD Rating ScaleIV: Checklists, norms, and clinical
interpretation. Guilford Press, 1998.
[39] J Swanson, W Nolan, and WE Pelham. The snap-iv rating scale. Irvine,
CA: University of California at Irvine, 1992.
[40] Wendy Reich. Diagnostic interview for children and adolescents (dica).
Journal of the American Academy of Child & Adolescent Psychiatry,
39(1):59–66, 2000.
[41] Joan Kaufman, Boris Birmaher, David Brent, UMA Rao, Cynthia Flynn,
Paula Moreci, Douglas Williamson, and Neal Ryan. Schedule for
affective disorders and schizophrenia for school-age children-present and
lifetime version (k-sads-pl): initial reliability and validity data. Journal
of the American Academy of Child & Adolescent Psychiatry, 36(7):980–
988, 1997.
[42] John Carlyle Raven et al. Raven’s progressive matrices and vocabulary
scales. Oxford pyschologists Press, 1998.
[43] Gale H Roid and Lucy J Miller. Leiter international performance scale-
revised (leiter-r). Wood Dale, IL: Stoelting, 1997.
[44] Nathan M Finnerty, Robert M Rodriguez, Christopher R Carpenter,
Benjamin C Sun, Nik Theyyunni, Robert Ohle, Kenneth W Dodd,
Elizabeth M Schoenfeld, Kendra D Elm, Jeffrey A Kline, et al. Clinical
decision rules for diagnostic imaging in the emergency department: a
research agenda. Academic Emergency Medicine, 22(12):1406–1416,
2015.
[45] Marshal F Folstein, Susan E Folstein, and Paul R McHugh. mini-mental
state: a practical method for grading the cognitive state of patients for
the clinician. Journal of psychiatric research, 12(3):189–198, 1975.
[46] Leonard R Derogatis and Rachael Unger. Symptom checklist-90-revised.
The Corsini encyclopedia of psychology, pages 1–2, 2010.
[47] Starke Rosecrans Hathaway and John Charnley McKinley. Minnesota
multiphasic personality inventory; manual, revised. 1951.
[48] James N Butcher. Minnesota multiphasic personality inventory. The
Corsini Encyclopedia of Psychology, pages 1–3, 2010.
[49] David Wechsler. Wechsler intelligence scale for children. 1949.
[50] David Wechsler. Wechsler preschool and primary scale of intelligence-
fourth edition. The Psychological Corporation San Antonio, TX, 2012.
[51] David Wechsler. Wechsler adult intelligence scale–fourth edition (wais–
iv). San Antonio, TX: NCS Pearson, 22:498, 2008.
[52] William A Hunt. The future of diagnostic testing in clinical psychology.
Journal of Clinical Psychology, 1946.
47