A deep learning approach for prediction of Parkinson’s disease progression

Afzal Hussain Shahid,Maheshwari Prasad Singh 대한의용생체공학회 2020 Biomedical Engineering Letters (BMEL) Vol.10 No.2

This paper proposes a deep neural network (DNN) model using the reduced input feature space of Parkinson’s telemonitoringdataset to predict Parkinson’s disease (PD) progression. PD is a chronic and progressive nervous system disorder that aff ectsbody movement. PD is assessed by using the unifi ed Parkinson’s disease rating scale (UPDRS). In this paper, fi rstly, principalcomponent analysis (PCA) is employed to the featured dataset to address the multicollinearity problems in the dataset andto reduce the dimension of input feature space. Then, the reduced input feature space is fed into the proposed DNN modelwith a tuned parameter norm penalty (L2) and analyses the prediction performance of it in PD progression by predictingMotor and Total-UPDRS score. The model’s performance is evaluated by conducting several experiments and the result iscompared with the result of previously developed methods on the same dataset. The model’s prediction accuracy is measuredby fi tness parameters, mean absolute error (MAE), root mean squared error (RMSE), and coeffi cient of determination (R 2 ). The MAE, RMSE, and R 2 values are 0.926, 1.422, and 0.970 respectively for motor-UPDRS. These values are 1.334, 2.221,and 0.956 respectively for Total-UPDRS. Both the Motor and Total-UPDRS score is better predicted by the proposed method. This paper shows the usefulness and effi cacy of the proposed method for predicting the UPDRS score in PD progression.

Facebook Activities and Mental Illness

Jamil Hussain(자밀 후세인),Muhammad Afzal(무하마드 아프잘),Maqbool Hussain(막불 후세인),Wajahat Ali Khan(와자핫 알리 칸),Sungyoung Lee(이승룡) 한국정보과학회 2014 한국정보과학회 학술발표논문집 Vol.2014 No.6

Personalization of wellness recommendations using contextual interpretation

Afzal, Muhammad,Ali, Syed Imran,Ali, Rahman,Hussain, Maqbool,Ali, Taqdir,Khan, Wajahat Ali,Amin, Muhammad Bilal,Kang, Byeong Ho,Lee, Sungyoung Elsevier 2018 expert systems with applications Vol.96 No.-

<P><B>Abstract</B></P> <P>A huge array of personalized healthcare and wellness systems are introduced into the portfolio of digital health and quantified-self movement in recent years. These systems share common capabilities including self-tracking/monitoring and self-quantifications, based on the raw sensory data. These capabilities provide solid ground for the users to be more aware of their health; however, such measures are inefficient for changing the unhealthy habits of the users. In order to induce healthy habits in the users, a system must be capable of generating context-aware personalized recommendations. The main obstacle in this regard is the contextual interpretation of recommendations based on user's current context and contextual preferences. To resolve these issues, we propose a methodology of cross-context interpretation of recommendations (CCIR) for personalized health and wellness services. The CCIR method adds additional capabilities to the traditional reasoning methods and builds advanced form of the reasoning with the incorporation of contextual factors in the process of interpretations of the recommendations. With CCIR, the self-quantification systems can be enhanced to generate personalized recommendations in addition to tracking, quantifying, and monitoring user activities. In order to validate the proposed CCIR methodology, a set of 40 contextual scenarios and corresponding recommendations are presented for the evaluation collected from 40 different end users and 10 domain experts. Using chi-square test evaluation, the results demonstrated acceptable “goodness of fit” indices for the system developed on proposed CCIR methodology with respect to the end users’ opinion. Also from the statistical observation, it is found that there exists a higher level agreement towards the system between the participants of both end users and experts.</P> <P><B>Highlights</B></P> <P> <UL> <LI> A method for cross-context interpretations of health and wellness recommendations. </LI> <LI> A mechanism of refining generalized recommendations to personalized recommendations. </LI> <LI> The contextual interpretations are made for increasing the user acceptability of a system. </LI> </UL> </P>

EFFECT OF VITAMIN E AND SELENIUM ON IMMUNITY IN NEWBORN JERSEY AND BUFFALO CALVES

Afzal, M.,Hussain, M.,Khan, K.N.M.,Munir, R. Asian Australasian Association of Animal Productio 1988 Animal Bioscience Vol.1 No.1

Effect of vitamin E and selenium supplementation on immunity was studied in newborn Jersey and buffalo calves. The supplement contained 500 mg vitamin E and $200\;{\mu}g$ selenium; and was fed daily from birth to day 30. Differences in weight gain, total leucocytic count, differential leucocytic count, antibody titre and susceptibility to disease were found to be nonsignificant between supplemented and control calves during the study period of 3 months. Vitamin E seemed to enhance the recovery from disease in buffalo calves. Buffalo calves were found to be more sensitive to selenium toxicity than Jersey calves.

Recommendations Service for Chronic Disease Patient in Multimodel Sensors Home Environment

Hussain, Maqbool,Ali, Taqdir,Khan, Wajahat Ali,Afzal, Muhammad,Lee, Sungyoung,Latif, Khalid Mary Ann Liebert 2015 TELEMEDICINE JOURNAL AND E HEALTH Vol.21 No.3

<P>With advanced technologies in hand, there exist potential applications and services built around monitoring activities of daily living (ADL) of elderly people at nursing homes. Most of the elderly people in these facilities are suffering from different chronic diseases such as dementia. Existing technologies are mainly focusing on non-medication interventions and monitoring of ADL for addressing loss of autonomy or well-being. Monitoring and managing ADL related to cognitive behaviors for non-medication intervention are very effective in improving dementia patients' conditions. However, cognitive functions of patients can be improved if appropriate recommendations of medications are delivered at a particular time. Previously we developed the Secured Wireless Sensor Network Integrated Cloud Computing for Ubiquitous-Life Care (SC(3)). SC(3) services were limited to monitoring ADL of elderly people with Alzheimer's disease and providing non-medication recommendations to the patient. In this article, we propose a system called the Smart Clinical Decision Support System (CDSS) as an integral part of the SC(3) platform. Using the Smart CDSS, patients are provided with access to medication recommendations of expert physicians. Physicians are provided with an interface to create clinical knowledge for medication recommendations and to observe the patient's condition. The clinical knowledge created by physicians as the knowledge base of the Smart CDSS produces recommendations to the caregiver for medications based on each patient's symptoms.</P>

Smart Extraction and Analysis System for Clinical Research

Afzal, Muhammad,Hussain, Maqbool,Khan, Wajahat Ali,Ali, Taqdir,Jamshed, Arif,Lee, Sungyoung Mary Ann Liebert 2017 TELEMEDICINE JOURNAL AND E HEALTH Vol.23 No.5

Comprehensible knowledge model creation for cancer treatment decision making

Afzal, Muhammad,Hussain, Maqbool,Ali Khan, Wajahat,Ali, Taqdir,Lee, Sungyoung,Huh, Eui-Nam,Farooq Ahmad, Hafiz,Jamshed, Arif,Iqbal, Hassan,Irfan, Muhammad,Abbas Hydari, Manzar Elsevier 2017 Computers in biology and medicine Vol.82 No.-

<P><B>Abstract</B></P> <P> <I>Background</I>: A wealth of clinical data exists in clinical documents in the form of electronic health records (EHRs). This data can be used for developing knowledge-based recommendation systems that can assist clinicians in clinical decision making and education. One of the big hurdles in developing such systems is the lack of automated mechanisms for knowledge acquisition to enable and educate clinicians in informed decision making. <I>Materials and Methods</I>: An automated knowledge acquisition methodology with a comprehensible knowledge model for cancer treatment (CKM-CT) is proposed. With the CKM-CT, clinical data are acquired automatically from documents. Quality of data is ensured by correcting errors and transforming various formats into a standard data format. Data preprocessing involves dimensionality reduction and missing value imputation. Predictive algorithm selection is performed on the basis of the ranking score of the weighted sum model. The knowledge builder prepares knowledge for knowledge-based services: clinical decisions and education support. <I>Results</I>: Data is acquired from 13,788 head and neck cancer (HNC) documents for 3447 patients, including 1526 patients of the oral cavity site. In the data quality task, 160 staging values are corrected. In the preprocessing task, 20 attributes and 106 records are eliminated from the dataset. The Classification and Regression Trees (CRT) algorithm is selected and provides 69.0% classification accuracy in predicting HNC treatment plans, consisting of 11 decision paths that yield 11 decision rules. <I>Conclusion</I>: Our proposed methodology, CKM-CT, is helpful to find hidden knowledge in clinical documents. In CKM-CT, the prediction models are developed to assist and educate clinicians for informed decision making. The proposed methodology is generalizable to apply to data of other domains such as breast cancer with a similar objective to assist clinicians in decision making and education.</P> <P><B>Highlights</B></P> <P> <UL> <LI> Automated methods for data acquisition from clinical documents and preprocessing. </LI> <LI> Data quality assessment and standardization of language for improved data accuracy. </LI> <LI> Machine learning algorithm selection on the basis of weighted sum model's ranking score. </LI> <LI> The development of a decision tree-based knowledge model for treatment recommendations. </LI> </UL> </P> <P><B>Graphical abstract</B></P> <P>[DISPLAY OMISSION]</P>

A Step towards the Improvement in the Performance of Text Classification

( Shahid Hussain ),( Muhammad Rafiq Mufti ),( Muhammad Khalid Sohail ),( Humaira Afzal ),( Ghufran Ahmad ),( Arif Ali Khan ) 한국인터넷정보학회 2019 KSII Transactions on Internet and Information Syst Vol.13 No.4

The performance of text classification is highly related to the feature selection methods. Usually, two tasks are performed when a feature selection method is applied to construct a feature set; 1) assign score to each feature and 2) select the top-N features. The selection of top-N features in the existing filter-based feature selection methods is biased by their discriminative power and the empirical process which is followed to determine the value of N. In order to improve the text classification performance by presenting a more illustrative feature set, we present an approach via a potent representation learning technique, namely DBN (Deep Belief Network). This algorithm learns via the semantic illustration of documents and uses feature vectors for their formulation. The nodes, iteration, and a number of hidden layers are the main parameters of DBN, which can tune to improve the classifier’s performance. The results of experiments indicate the effectiveness of the proposed method to increase the classification performance and aid developers to make effective decisions in certain domains.

임상 의사 결정에서 온라인 지식 자원의 역할

무하마드아프잘 ( Muhammad Afzal ),마크불후세인 ( Maqbool Hussain ),와자하트알리칸 ( Wajahat Ali Khan ),탁디르알 ( Taqdir Ali ),이승룡 ( Sungyoung Lee ) 한국정보처리학회 2012 한국정보처리학회 학술대회논문집 Vol.19 No.2

The need of Clinical Decision Support System (CDSS) in healthcare setup is increasing day by day. EHR Meaningful Use advocates CDSS as an important component of EHR/EMR systems. CDSS can be ranged from a simple to a very sophisticated system. The more complex CDSS systems need more attention to develop because of many reasons including its Knowledge Base (KB) structure/maintenance/evolution, inference capabilities and usability. Above all the KB maintenance and evolution is very crucial and important from the perspective of useful decision capabilities. Also the richness of the KB is important to cover the decision gaps handling a particular situation in the course of patient care. It cannot be expected from the clinicians to remember everything in regard to patient diagnosis and treatment. Similarly, it is also crucial for clinicians to keep themselves updated with the new research in the area. That is the reason they frequently require accessing to the online knowledge resources. Literature proved that online knowledge resources are capable providing answers to questions that might not be answered rely only on clinician wisdom and experience. This paper provides the theme of meaningful utilization of online knowledge resources in the context of diagnosis and treatment process for cancer patients more specifically Head and Neck cancer.

만성 질병환자를 위한 CDSS 를 적용한 PHR 시스템

마크불후세인 ( Maqbool Hussain ),와자하트알리칸 ( Wajahat Ali Khan ),무하마드아프잘 ( Muhammad Afzal ),탁디르알리 ( Taqdir Ali ),이승룡 ( Sungyoung Lee ) 한국정보처리학회 2012 한국정보처리학회 학술대회논문집 Vol.19 No.2

With the advance of Information Technology (IT) and dynamic requirements, diverse application services have been provided for end users. With huge volume of these services and information, users are required to acquire customized services that provide personalized information and decision at particular extent of time. The case is more appealing in healthcare, where patients wish to have access to their medical record where they have control and provided with recommendation on the medical information. PHR (Personal Health Record) is most prevailing initiative that gives secure access on patient record at anytime and anywhere. PHR should also incorporate decision support to help patients in self-management of their diseases. Available PHR system incorporates basic recommendations based on patient routine data. We have proposed decision support service called “Smart CDSS” that provides recommendations on PHR data for diabetic patients. Smart CDSS follows HL7 vMR (Virtual Medical Record) to help in integration with diverse application including PHR. PHR shares patient data with Smart CDSS through standard interfaces that pass through Adaptability Engine (AE). AE transforms the PHR CCR/CCD (Continuity of Care Record/Document) into standard HL7 vMR format. Smart CDSS produces recommendation on PHR datasets based on diabetic knowledge base represented in shareable HL7 Arden Syntax format. The Smart CDSS service is deployed on public cloud over MS Azure environment and PHR is maintaining on private cloud. The system has been evaluated for recommendation for 100 diabetic patients from Saint’s Mary Hospital. The recommendations were compared with physicians’ guidelines which complement the self-management of the patient.