Predictive Modeling of Outcomes After Traumatic and Nontraumatic Spinal Cord Injury Using Machine Learning: Review of Current Progress and Future Directions

Omar Khan,Jetan H. Badhiwala,Jamie R.F. Wilson,Fan Jiang,Allan R. Martin,Michael G. Fehlings 대한척추신경외과학회 2019 Neurospine Vol.16 No.4

Machine learning represents a promising frontier in epidemiological research on spine surgery. It consists of a series of algorithms that determines relationships between data. Machine learning maintains numerous advantages over conventional regression techniques, such as a reduced requirement for a priori knowledge on predictors and better ability to manage large datasets. Current studies have made extensive strides in employing machine learning to a greater capacity in spinal cord injury (SCI). Analyses using machine learning algorithms have been done on both traumatic SCI and nontraumatic SCI, the latter of which typically represents degenerative spine disease resulting in spinal cord compression, such as degenerative cervical myelopathy. This article is a literature review of current studies published in traumatic and nontraumatic SCI that employ machine learning for the prediction of a host of outcomes. The studies described utilize machine learning in a variety of capacities, including imaging analysis and prediction in large epidemiological data sets. We discuss the performance of these machine learning-based clinical prognostic models relative to conventional statistical prediction models. Finally, we detail the future steps needed for machine learning to become a more common modality for statistical analysis in SCI.

Fabrication of highly hydrophilic tubular type perlite membrane support

Omar A. Al-Harbi,Cem ÖZGÜR,M. M Khan 한양대학교 세라믹연구소 2016 Journal of Ceramic Processing Research Vol.17 No.4

We fabricated and characterized a highly hydrophilic membrane support using only perlite as an ore without altering itschemical and physical properties. Tubular-type microfiltration supports were fabricated by an extrusion technique. Plasticperlite paste was obtained by adding organic additives and water. The extruded samples were carefully dried to prevent cracksduring the drying period of 6 days with a controlled drying temperature and humidity. Green bodies were sintered attemperatures of 1000 oC, 1025 oC, and 1050 oC for 1, 3, and 6 hours. Tubular membrane supports were characterized in termsof microstructure, porosity, pore size distribution and crystalline phases. Additionally, the hydrophilicity of the samples wasdetermined by a thin layer wicking (TLW) approach. The water contact angles of the samples sintered at 1025 oC for 3 hourswere determined to be 20 o, and the porosity and mean pore size of the sample were 23.54% and 13 µm, respectively. The cleanwater permeability of the sample was 10.677 L/h.m2bar. According to the results, the obtained sample functions well as a highlyhydrophilic membrane support, and it is also a good candidate for a filter used in macro- and microfiltration processes. Filtration tests indicated that the median particle size of the solids in waste water is 500 nm, with a turbidity of 100 NTU, andthe waste water can be cleaned by the newly fabricated perlite tubular ceramics up to a turbidity level of 0.35 NTU, whichis acceptable in various industries

Impact of Physician’s Education on Adherence to Tuberculosis Treatment for Patients of Low Socioeconomic Status in Bangladesh

이신원,Omar Faruk Khan,서정호,김동연,박경화,정숙인,정은경,장희창 전남대학교 의과학연구소 2013 전남의대학술지 Vol.49 No.1

Successful tuberculosis control depends on good adherence to treatment. Yet, limited data are available on the efficacy of methods for improving the adherence of patients of low socioeconomic status. We evaluated the impact of physician-provided patient education on adherence to anti-tuberculosis medication in a low socioeconomic status and resource-limited setting. A pre-/post-intervention study was conducted at a suburban primary health care clinic in Bangladesh where an intensive education strategy was established in May 2006. Treatment outcomes of tuberculosis patients from March 2005 to April 2006 (pre-intervention) and from May 2006 to December 2007 (post-intervention)were compared. Among 354 patients, 198 (56%) were treated before intervention and 156 (44%) were treated after intervention. Cumulative adherence to anti-tuberculosis medication was significantly greater in the intervention group than in the control group in univariate and multivariate analyses. Physician’s education can contribute to increasing the adherence of patients in resource-limited settings.

Predicting compressive strength of bended cement concrete with ANNs

Uneb Gazder,Omar Saeed Baghabara Al-Amoudi,Saad Muhammad Saad Khan,Mohammad Maslehuddin 사단법인 한국계산역학회 2017 Computers and Concrete, An International Journal Vol.20 No.6

Predicting the compressive strength of concrete is important to assess the load-carrying capacity of a structure. However, the use of blended cements to accrue the technical, economic and environmental benefits has increased the complexity of prediction models. Artificial Neural Networks (ANNs) have been used for predicting the compressive strength of ordinary Portland cement concrete, i.e., concrete produced without the addition of supplementary cementing materials. In this study, models to predict the compressive strength of blended cement concrete prepared with a natural pozzolan were developed using regression models and single- and 2-phase learning ANNs. Back-propagation (BP), Levenberg-Marquardt (LM) and Conjugate Gradient Descent (CGD) methods were used for training the ANNs. A 2-phase learning algorithm is proposed for the first time in this study for predictive modeling of the compressive strength of blended cement concrete. The output of these predictive models indicates that the use of a 2-phase learning algorithm will provide better results than the linear regression model or the traditional single-phase ANN models.

Durability performance of concrete containing Saudi natural pozzolans as supplementary cementitious material

Al-Amoudi, Omar S. Baghabra,Ahmad, Shamsad,Khan, Saad M.S.,Maslehuddin, Mohammed Techno-Press 2019 Advances in concrete construction Vol.8 No.2

This paper reports an experimental investigation conducted to evaluate the durability performance of concrete mixtures prepared utilizing blends of Type I Portland cement (OPC) and natural pozzolans (NPs) obtained from three different sources in Saudi Arabia. The control concrete mixture containing OPC alone as the binder and three concrete mixtures incorporating NPs were prepared keeping water/binder ratio of 0.4 (by weight), binder content of $370kg/m^3$, and fine/total aggregate ratio of 0.38 (by weight) invariant. The compressive strength and durability properties that included depth of water penetration, depth of carbonation, chloride diffusion coefficient, and resistance to reinforcement corrosion and sulfate attack were determined. Results of this study indicate that at all ages, the compressive strength of NP-admixed concrete mixtures was slightly less than that of the concrete containing OPC alone. However, the concrete mixtures containing NP exhibited lower depth of water penetration and chloride diffusion coefficient and more resistance to reinforcement corrosion and sulfate attack as compared to OPC. NP-admixed concrete showed relatively more depth of carbonation than OPC when subjected to accelerated carbonation. The results of this investigation indicates the viability of utilizing of Saudi natural pozzolans for improving the durability characteristics of concrete subjected to chloride and sulfate exposures.

A Group Chain Acceptance Sampling Plan for Lifetimes Following Beta Burr Type-X Distribution with Minimum Angle Approach

Majid Liaqat,Nadia Saeed,Moustafa Omar Ahmed Abu-Shawie,Rehan Ahmad Khan Sherwani 대한산업공학회 2021 Industrial Engineeering & Management Systems Vol.20 No.3

The group chain acceptance sampling plans are widely used in industrial sectors when we want to minimize the inspection by selecting number of batches representing the whole lot. The research is based on the construction of plan parameters of group chain acceptance sampling (GCAS) plan when life of the items follows Beta Burr Type-X (BB-X) distribution. The various design parameters i.e. optimum number of groups, minimum mean ratio, operating characteristic (OC) values and minimum angles are calculated by satisfying and obeying producer’s and consumer’s risks at a certain specified quality level. Assuming prefixed number of item, the scale parameters and termination time, the plan parameters are calculated. The application of proposed plan is provided on real life data set and the results of tables with the help of classical examples are also discussed for illustrative purpose.

Spectroscopic and cloud point studies of the interaction and thermodynamics of ciprofloxacin hydrochloride+surfactants mixture in different solvents: Effect of temperature and composition

Md. Anamul Hoque,Md. Mofaqkharur Rahman,Shamim Mahbub,Mezbah Hossain,Mohammed Abdullah Khan,Md. Ruhul Amin,Ali S. Alqahtani,Mohammad Z. Ahmed,Mohammed S. Alqahtani,Omar M. Almarfadi 한국화학공학회 2021 Korean Journal of Chemical Engineering Vol.38 No.7

Surfactant is one of the most important chemical entities in drug formulation which can bind with drug molecules. Herein, the binding interaction of ciprofloxacin hydrochloride (CFH) drug with two different surfactants (sodium dodecyl sulfate (SDS) and Triton X-100 (TX-100)) has been investigated through UV-Visible spectroscopic and cloud point measurement techniques at different conditions. The absorption spectrum of CFH was found to be dependent on presence of additives/temperature change. The binding constant (Kb) of CFH+SDS/CFH+TX-100 was found to be increased primarily, reached a maximum value and then decreased with the increase of temperature, except in water medium (pH=2.0) and 30% (v/v) methanol. The Kb values for CFH+SDS were found to be higher in the aqueous medium than almost all medium studied herein, while better binding was observed in the alcoholic medium in the case of the CFH+TX-100 system. The Gibbs free energy of binding (Gb o) for both CFH+SDS and CFH+TX- 100 systems were attained negative in each case studied, inferring the spontaneous binding phenomenon. The cloud point (CP) value of CFH+TX-100 mixture was lessened in ZnSO4·7H2O solution and the CP values exhibited a gradual reduction through the upsurge of electrolyte concentration. The positive values of the Gibbs free energy of clouding indicated the nonspontaneous clouding phenomena. To disclose the interaction between drug and surfactant, other thermodynamic parameters, e.g., enthalpy (Hb o) and entropy (Sb o), different transfer energies as well as entropyenthalpy compensation parameters of binding/clouding were evaluated and clarified with proper explanation.