Feasibility, Sustainability, and Effectiveness of the Implementation of "Facility-Team-Driven" Approach for Improving the Quality of Newborn Care in South India.

OBJECTIVES: The primary objective of the study was to assess the feasibility and sustainability of the implementation of the point of care quality improvement (POCQI) methodology for improving the quality of neonatal care at the level 2 special newborn care unit (SNCU). Additional objective was to evaluate the effectiveness of the quality improvement (QI) and preterm baby package training model. METHODS: This study was conducted in a level-II SNCU. The study period was divided into baseline; intervention and sustenance phases. The primary outcome i.e., feasibility was defined as completion of training for 80% or more health care professionals (HCPs) through workshops, their attendance in subsequent review meetings and, successful accomplishment of at least two plan-do-study-act (PDSA) cycles in each project. RESULTS: Of the total, 1217 neonates were enrolled during the 14 mo study period; 80 neonates in the baseline, 1019 in intervention and 118 in sustenance phases. Feasibility of training was achieved within a month of initiation of intervention phase; 22/24 (92%) nurses and 14/15 (93%) doctors attended the meetings. The outcomes of individual projects suggested an improvement in proportion of neonates being given exclusive breast milk on day 5 (22.8% to 78%); mean difference (95% CI) [55.2 (46.5 to 63.9)]. Neonates on any antibiotics declined, proportion of any enteral feeds on day one and duration of kangaroo mother care (KMC) increased. Proportion of neonates receiving intravenous fluids during phototherapy decreased. CONCLUSIONS: The present study demonstrates the feasibility, sustainability, and effectiveness of a facility-team-driven QI approach augmented with capacity building and post-training supportive supervision.

Predictive modeling for corrective maintenance of imaging devices from machine logs.

In the cost sensitive healthcare industry, an unplanned downtime of diagnostic and therapy imaging devices can be a burden on the financials of both the hospitals as well as the original equipment manufacturers (OEMs). In the current era of connectivity, it is easier to get these devices connected to a standard monitoring station. Once the system is connected, OEMs can monitor the health of these devices remotely and take corrective actions by providing preventive maintenance thereby avoiding major unplanned downtime. In this article, we present an overall methodology of predicting failure of these devices well before customer experiences it. We use data-driven approach based on machine learning to predict failures in turn resulting in reduced machine downtime, improved customer satisfaction and cost savings for the OEMs. One of the use-case of predicting component failure of PHILIPS iXR system is explained in this article.

A machine learning framework for auto classification of imaging system exams in hospital setting for utilization optimization.

In clinical environment, Interventional X-Ray (IXR) system is used on various anatomies and for various types of the procedures. It is important to classify correctly each exam of IXR system into respective procedures and/or assign to correct anatomy. This classification enhances productivity of the system in terms of better scheduling of the Cath lab, also provides means to perform device usage/revenue forecast of the system by hospital management and focus on targeted treatment planning for a disease/anatomy. Although it may appear classification of each exam into respective procedure/anatomy a simple task. However, in real-life hospital settings, it is well-known that same system settings are used to perform different types of procedures. Though, such usage leads to under-utilization of the system. In this work, a method is developed to classify exams into respective anatomical type by applying machine-learning techniques (SVM, KNN and decision trees) on log information of the systems. The classification result is promising with accuracy of greater than 90%.

A method to detect tortuosity of vessel using non imaging ultrasound approach in carotid structure.

Stroke is a leading cause of functional impairments. The typical screening mechanism is to measure localized Peak Systolic Velocity (PSV) and diagnose impending risk associated with stoke by characterizing the PSV values. However, an accurate measurement of PSV using Doppler ultrasound is affected due to the tortuous nature of carotid artery in elder population group as the angle at which acoustic beam strikes the vessel is over or under estimated resulting in improper measure the blood flow velocity. Hence, the proposed approach estimates the degree of tortuosity of the carotid vessel and includes this as calibration parameter to compute an accurate PSV. The proposed system consists of low cost custom-built ultrasound probe and algorithms for computation of tortuosity and calibration of PSV. The method is proposed on a phantom as well as data acquired on the human subjects using non-imaging probe. The results obtained are compared with the ultrasound imaging systems and it is observed to have an error tolerance of ± 2 SD units from ground truth. The proposed approach can be used as point of care non imaging device to screen at risk stroke patients more accurately.

An analytics based clinical decision support system for CVD risk assessment and management.

Cardiovascular disease (CVD) is a major cause of disability and premature death throughout the world. Acute coronary events and other cardiovascular events frequently occur suddenly, and are often fatal before medical care can be given. Risk factor modification can reduce clinical events and premature death in people with established cardiovascular disease as well as in those who are at high cardiovascular risk due to one or more risk factors. In this work, India specific World Health Organization-International Society of Hypertension (WHO-ISH) guidelines has been implemented to stratify the subjects by their risk profile. It provides simplified approach to detect those people at high risk and provides guidance on what should be done for prevention of heart attack. Further, based on the risk stratification, lifestyle coaching, medication management and the next tests are advised to the subjects. This approach will help in early detection of cardiovascular risk subjects and provide necessary interventions at appropriate time frame. Also, it acts as motivation to the individuals to comply with recommended lifestyle changes.

A method for localized computation of Pulse Wave Velocity in carotid structure.

Pulse Wave Velocity (PWV) promises to be a useful clinical marker for noninvasive diagnosis of atherosclerosis. This work demonstrates the ability to perform localized carotid PWV measurements from the distention waveform derived from the Radio Frequency (RF) ultrasound signal using a carotid phantom setup. The proposed system consists of low cost custom-built ultrasound probe and algorithms for envelope detection, arterial wall identification, echo tracking, distension waveform computation and PWV estimation. The method is proposed on a phantom data acquired using custom-built prototype non-imaging probe. The proposed approach is non-image based and can be seamlessly integrated into existing clinical ultrasound scanners.

Temporal and spectral analysis of internal carotid artery Doppler signal for normal and abnormal flow detection.

Detection of carotid artery stenosis is presently highly dependent on ultrasound imaging systems. This work presents a method that can detect the normal and abnormal blood flow in the carotid structure independent of Doppler angle by analysing the time and spectral domain representation of Doppler signal. In the proposed approach, time and spectral domain based features are extracted from the Doppler signals of internal carotid arteries. Further, these features are used in supervised machine learning approach to identify the presence of abnormal blood flow. The proposed method is evaluated on 100 subjects (200 signals) with equal number of normal and abnormal flow profiles. Experimental results show that the maximum classification accuracies of 79.3% and 82.9% are observed with k-nearest neighbours and support vector machine classifiers, respectively.

Gaussian mixture model based identification of arterial wall movement for computation of distension waveform.

This work proposes a novel Gaussian Mixture Model (GMM) based approach for accurate tracking of the arterial wall and subsequent computation of the distension waveform using Radio Frequency (RF) ultrasound signal. The approach was evaluated on ultrasound RF data acquired using a prototype ultrasound system from an artery mimicking flow phantom. The effectiveness of the proposed algorithm is demonstrated by comparing with existing wall tracking algorithms. The experimental results show that the proposed method provides 20% reduction in the error margin compared to the existing approaches in tracking the arterial wall movement. This approach coupled with ultrasound system can be used to estimate the arterial compliance parameters required for screening of cardiovascular related disorders.

Analysis of sub-anatomic diffusion tensor imaging indices in white matter regions of Alzheimer with MMSE score.

In this study, an attempt has been made to find the correlation between diffusion tensor imaging (DTI) indices of white matter (WM) regions and mini mental state examination (MMSE) score of Alzheimer patients. Diffusion weighted images are obtained from the ADNI database. These are preprocessed for eddy current correction and removal of non-brain tissue. Fractional anisotropy (FA), mean diffusivity (MD), radial diffusivity (RD) and axial diffusivity (DA) indices are computed over significant regions (Fornix left, Splenium of corpus callosum left, Splenium of corpus callosum right, bilateral genu of the corpus callosum) affected by Alzheimer disease (AD) pathology. The correlation is computed between diffusion indices of the significant regions and MMSE score using linear fit technique so as to find the relation between clinical parameters and the image features. Binary classification has been employed using support vector machine, decision stumps and simple logistic classifiers on the extracted DTI indices along with MMSE score to classify Alzheimer patients from healthy controls. It is observed that distinct values of DTI indices exist for the range of MMSE score. However, there is no strong correlation (Pearson's correlation coefficient 'r' varies from 0.0383 to -0.1924) between the MMSE score and the diffusion indices over the significant regions. Further, the performance evaluation of classifiers shows 94% accuracy using SVM in differentiating AD and control. In isolation clinical and image features can be used for prescreening and diagnosis of AD but no sub anatomic region correlation exist between these features set. The discussion on the correlation of diffusion indices of WM with MMSE score is presented in this study.

Identification of brain white matter regions for diagnosis of Alzheimer using Diffusion Tensor Imaging.

Diffusion Tensor Imaging (DTI) technique is widely used to probe the white matter (WM) tracts, which is affected most by neurological disorders. The fractional anisotropy (FA) metric has been used predominantly to study changes in the WM tracts. Here an attempt is made to delineate specific regions of interest in the WM that may be probable indicators for the diagnosis of Alzheimer disease (AD). Genetic algorithm has been used as feature reduction method along with Adaptive Boosting (AdaBoost) machine learning technique to determine the most prominent regions in the WM that are indicators of AD. It is found in this study that Fornix region of WM is most affected by Alzheimer. Further, classification was done to differentiate between Alzheimer and Normal controls with accuracy of 84.5%. The results obtained were validated by comparing with the existing literature on Alzheimer.