Algorithmic prediction of individual diseases

The enormous and increasing cost of health care is burdensome for most low- to middle-income families, especially those families whose members are battling chronic diseases. If effective interventions can be conducted at earlier stages, many costs are avoidable. Correspondingly, predicting the future disease one patient may develop with accuracy is a crucial step towards solving this problem. We have developed a system called CAC, which integrates Clustering, Association analysis and Collaborative filtering to predict patients’ future conditions. The data-set used in this study is health insurance data collected from a provincial capital city of China. Specifically, the data-set includes 151,237 insured patients who have reimbursement records between 2007 and 2014. The patients are artificially classified into acute patients and chronic patients. For both sets of patients, we utilise a training set to generate the prediction rules and a testing set to test the prediction results. The results show that for 71% of acute patients and 82% of chronic patients, their future conditions are predictable.     

The effects of age,gender, and crash types on drivers’ injury-related health care costs

There are many studies that evaluate the effects of age, gender, and crash types on crash related injury severity. However, few studies investigate the effects of those crash factors on the crash related health care costs for drivers that are transported to hospital. The purpose of this study is to examine the relationships between drivers’ age, gender, and the crash types, as well as other crash characteristics (e.g., not wearing a seatbelt, weather condition, and fatigued driving), on the crash related health care costs. The South Carolina Crash Outcome Data Evaluation System (SC CODES) from 2005 to 2007 was used to construct six separate hierarchical linear regression models based on drivers’ age and gender. The results suggest that older drivers have higher health care costs than younger drivers and male drivers tend to have higher health care costs than female drivers in the same age group. Overall, single vehicle crashes had the highest health care costs for all drivers. For males older than 64-years old sideswipe crashes are as costly as single vehicle crashes. In general, not wearing a seatbelt, airbag deployment, and speeding were found to be associated with higher health care costs. Distraction-related crashes are more likely to be associated with lower health care costs in most cases. Furthermore this study highlights the value of considering drivers in subgroups, as some factors have different effects on health care costs in different driver groups. Developing an understanding of longer term outcomes of crashes and their characteristics can lead to improvements in vehicle technology, educational materials, and interventions to reduce crash-related health care costs.     

The epidemiology and cost of falls requiring hospitalisation in children in Western Australia: a study using linked administrative data

OBJECTIVE: The aim of this study was to examine the epidemiology and health system cost of children's falls resulting in hospitalisation in 2003 in Western Australia. METHODS: The Injury Cost Database was used to identify children who were admitted to hospital with a falls related injury. Adjusted incidence rate ratios (IRR) of hospitalisation were modelled using Poisson regression. In-patient hospital costs were assigned using the published DRG costs for Western Australia. These costs were then extrapolated to health system costs based on previously published relative proportions. RESULTS: When adjusted for other covariates in the model males had a 53% higher incidence of falls requiring hospitalisation compared with females. Aboriginal children had a 36% higher incidence compared with their non-Aboriginal counterparts, and the incidence of falls reduced with increasing age. The total cost of in-patient hospitalisation associated with children's falls in Western Australia was A$4,554,000 with an average cost of A$1876 per case. In children aged 0-4 years and 10-14 years the highest cost resulted from falls on the flat (slips and trips). However, in children aged 5-9 years injuries resulting from falls from playground equipment resulted in both the highest cost group (A$539,000) and the highest cost per case (A$1917). The total cost to the health system of children's falls in Western Australia in 2003 were estimated to be A$21.5 million, with the total cost to the community estimated at A$108.5 million. CONCLUSION: Children's falls impose a considerable burden and cost to both the health care system and the community. This study has provided information on where the burden of risk and the majority of costs lie, namely males, Aboriginal children and for children aged 5-9 years, unlike their younger and older peers, playground equipment.     

Optimization of folding box manufacture: Part one

The cost of producing folding boxboard cartons is dependent on a number of factors, among the most important of which are: machine costs, material costs and overheads. In estimating costs, decisions must be made that are often based on experience rather than on a precise knowledge of he facts. The use of an expert system can provide a more effective tool and procedure than that used currently. Part one of this report illustrates the effects of some of the variables, while part two describes the OPTICALC expert system devised by the authors.     

Optimization of folding box manufacture: Part two

The cost of producing folding boxboard cartons is dependent on a number of factors, among the most important of which are: machine costs, material costs and overheads. In estimating costs, decisions must be made that are often based on experience rather than on a precise knowledge of the facts. The use of an expert system can provide a more effective tool and procedure than that used currently. Part one outlined the effect of the variables. This part of the report describes the OPTICALC expert system devised by the authors.     

Employer acquisition of health care facilities: a possible outcome of escalating premiums?

The price of health care is rising faster than most other prices; the increasing number of employer-financed health insurance plans means that insurance premiums are a significantly growing expense. Some companies might save money without sacrificing the quality of care by building or buying health care facilities. The authors analyze hospital costs and corporate experience with in-house care.     

The economic burden of injury: Health care and productivity costs of injuries in the Netherlands

BackgroundDetailed information on health care costs and productivity costs for the whole spectrum of injuries is lacking. We measured the total costs of injuries by external-cause, injury groupings, age and sex.MethodInjury patients visiting an Emergency Department in the Netherlands were included. Health service use and work absenteeism were estimated with national database data and a prospective follow-up study. Health care costs (direct costs) and productivity costs (indirect costs) were determined using the incidence-based Dutch Cost of Injury Model.ResultsTotal costs of injuries were €3.5 billion annually (€210/capita and €4300/patient); €2.0 billion healthcare costs and €1.5 billion productivity costs. Home and leisure injury subcategory falls caused 41% of total costs. Traffic injury was prominent in the 15–54 age group, mainly due to bicycle injuries. Sports injuries, in special football/soccer injuries, resulted in high costs in the 15–24 age group. Although costs per patient were comparable between males and females, health care costs were higher in females, whereas males have more than twice as high productivity costs. Health care costs were highest for hip fractures (€20,000/patient). Extremity fractures had high costs due to high incidences and high productivity costs per patient.ConclusionOur detailed cost model identified known risk groups, such as elderly females with hip fractures resulting from falls, as well as less obvious important high risk groups, such as young children falling from furniture, young males who sustained football/soccer injuries and bicycle injuries among all ages. This information is essential to assess additional priority areas for prevention.     

Performance prediction of a specific wear rate in epoxy nanocomposites with various composition content of polytetrafluoroethylen (PTFE), graphite,short carbon fibers (CF) and nano-TiO2 using adaptive neuro-fuzzy inference system (ANFIS)

Specific wear rate of composite materials plays a significant role in industry. The processes to measure it are both time and cost consuming. It is essential to suggest a modeling method to predict and analyze the effectiveness of parameters of specific wear rate. Nowadays, computational methods such as Artificial Neural Network (ANN), Fuzzy Inference System (FIS) and adaptive neuro-fuzzy inference system (ANFIS) are mainly considered as applicable tools from modeling point of view. ANFIS present integrate performance of neural network (NN) and fuzzy system (FS). Present paper investigates performance prediction of a specific wear rate of epoxy composites with various composition using ANFIS. The obtained results showed that ANFIS is a powerful tool in modeling specific wear rate. The obtained mean of squared error (MSE) for testing sets in present paper obtained 0.0071.     

Alcohol consumption as an incremental factor in health care costs for traffic accident victims: Evidence in a medium sized Colombian city

Objectives

Identify the possibility that alcohol consumption represents an incremental factor in healthcare costs of patients involved in traffic accidents.

Methods

Data of people admitted into three major health institutions from an intermediate city in Colombia was collected. Socio-demographic characteristics, health care costs and alcohol consumption levels by breath alcohol concentration (BrAC) methodology were identified. Generalized linear models were applied to investigate whether alcohol consumption acts as an incremental factor for healthcare costs.

Results

The average cost of healthcare was 878 USD. In general, there are differences between health care costs for patients with positive blood alcohol level compared with those who had negative levels. Univariate analysis shows that the average cost of care can be 2.26 times higher (95% CI: 1.20–4.23), and after controlling for patient characteristics, alcohol consumption represents an incremental factor of almost 1.66 times (95% CI: 1.05–2.62).

Conclusions

Alcohol is identified as a possible factor associated with the increased use of direct health care resources. The estimates show the need to implement and enhance prevention programs against alcohol consumption among citizens, in order to mitigate the impact that traffic accidents have on their health status. The law enforcement to help reduce driving under the influence of alcoholic beverages could help to diminish the economic and social impacts of this problem.     

Failure Prediction,Lead Time Estimation and Health Degree Assessment for Hard Disk Drives Using Voting Based Decision Trees

Hard Disk drives (HDDs) are an essential component of cloud computing and big data, responsible for storing humongous volumes of collected data. However, HDD failures pose a huge challenge to big data servers and cloud service providers. Every year, about 10% disk drives used in servers crash at least twice, lead to data loss, recovery cost and lower reliability. Recently, the researchers have used SMART parameters to develop various prediction techniques, however, these methods need to be improved for reliability and real-world usage due to the following factors: they lack the ability to consider the gradual change/deterioration of HDDs; they have failed to handle data unbalancing and biases problem; they don’t have adequate mechanisms for health status prediction of HDDs. This paper introduces a novel voting-based decision tree classifier to cater failure prediction, a balance splitting algorithm for the data unbalancing problem, an advanced procedure for lead time estimation and R-CNN based approach for health status estimation. Our system works robustly by considering a gradual change in SMART parameters. The system is rigorously tested on 3 datasets and it delivered benchmarks results as compared to the state of the art.     

Modelling crash propensity of carshare members

Carshare systems are considered a promising solution for sustainable development of cities. To promote carsharing it is imperative to make them cost effective, which includes reduction in costs associated to crashes and insurance. To achieve this goal, it is important to characterize carshare users involved in crashes and understand factors that can explain at-fault and not-at fault drivers. This study utilizes data from GoGet carshare users in Sydney, Australia. Based on this study it was found that carshare users who utilize cars less frequently, own one or more cars, have less number of accidents in the past ten years, have chosen a higher insurance excess and have had a license for a longer period of time are less likely to be involved in a crash. However, if a crash occurs, carshare users not needing a car on the weekend, driving less than 1000 km in the last year, rarely using a car and having an Australian license increases the likelihood to be at-fault. Since the dataset contained information about all members as well as not-at-fault drivers, it provided a unique opportunity to explore some aspects of quasi-induced exposure. The results indicate systematic differences in the distribution between the not-at-fault drivers and the carshare members based on the kilometres driven last year, main mode of travel, car ownership status and how often the car is needed. Finally, based on this study it is recommended that creating an incentive structure based on training and experience (based on kilometres driven), possibly tagged to the insurance excess could improve safety, and reduce costs associated to crashes for carshare systems.     

Occupational stress, social support, and the costs of health care.

Relationships among health care costs, social support, and occupational stress are investigated. Health care cost data were collected over two years for 260 working individuals. Multiple regression analyses were used to control for initial health care costs, age, and gender in predicting later costs; independent variables were stress, strain, social support, and their interactions. Main effects and interactions each accounted for significant proportions of the variance in various health care costs.     

Road traffic injuries in an urban area in Mexico. An epidemiological and cost analysis

The objective of this study was to do an epidemiological and costs analysis of the impact of road traffic injuries on the demand for emergency room services at hospitals located in the city of Cuernavaca, Mexico. The studied population included injured people who demanded medical attention at the emergency room for injuries due to events in public places, occurring between February and April 2001. Trained interviewers collected the data at the emergency room, 24h a day. The statistical analysis included simple and bivariate analysis using chi(2) odds ratio (OR), and a confidence interval of 95%. The costs analysis included the expenses during the process of searching for and finding care for injuries. There were 433 injured people, 233 (54%) were victims of road traffic accidents, 72% of crashes, and 28% were injured pedestrian and cyclists. Variables associated with the demand of emergency care due to road traffic injuries in comparison with other accidents, were: severity of injuries (OR 2.60, CI 1.44-4.71), and thorax injury (OR 4.64, CI 1.03-20.89). Pedestrians had higher costs for health care and 80% of them had to pay out-of-pocket (P<0.05). Differences between patients injured by crashes or as a pedestrian, were: age under 14 years (OR 5.9, CI 2.5-13.9), being unemployed (OR 2.1, CI 1.20-3.96), and being an elementary school student (OR 13.9, CI 3.08-63.13). The present study is, so far, the only one in Mexico to include an epidemiological and costs analysis in approaching the problem of road traffic injuries. Similar methods must be used, especially in developing countries, to reduce this important public health problem.     

From computers to ubiquitous computing by 2010: health care

Over the past decade, miniaturization and cost reduction in semiconductors have led to computers smaller in size than a pinhead with powerful processing abilities that are affordable enough to be disposable. Similar advances in wireless communication, sensor design and energy storage have meant that the concept of a truly pervasive 'wireless sensor network', used to monitor environments and objects within them, has become a reality. The need for a wireless sensor network designed specifically for human body monitoring has led to the development of wireless 'body sensor network' (BSN) platforms composed of tiny integrated microsensors with on-board processing and wireless data transfer capability. The ubiquitous computing abilities of BSNs offer the prospect of continuous monitoring of human health in any environment, be it home, hospital, outdoors or the workplace. This pervasive technology comes at a time when Western world health care costs have sharply risen, reflected by increasing expenditure on health care as a proportion of gross domestic product over the last 20 years. Drivers of this rise include an ageing post 'baby boom' population, higher incidence of chronic disease and the need for earlier diagnosis. This paper outlines the role of pervasive health care technologies in providing more efficient health care.     

The replacement of machines in a serially dependent multi-machine production system

In this paper a heuristic procedure is developed for solving the problem of planning machine replacements for a serially dependent production system. Given a finite planning horizon, the decision-maker wishes to decide (1) which periods, if any, that the entire production system must be shut down in order to make replacements, and (2) what specific machine or machines in the system should be scheduled for replacement during each of these downtime periods. The problem involves a balancing of costs. If the production system is brought down to make one or more replacements a fixed downtime cost is incurred; this cost is independent of the machines replaced during the downtime. In addition, other fixed coats are incurred for each of the machines replaced. Our motivation for scheduling these replacements is to realize lower variable costs for operating the machines. The variable operating costs are assumed to increase as the age or vintage of the machines increases. An optimal replacement policy is one in which the total of the present-value fixed and operating costs are minimized for the entire planning horizon. The paper also presents computational results using the heuristic to solve a large number of randomly generated test problems of varying numbers of machines and periods. These heuristic solutions are compared to known optimal solutions for a number of the problems. One of the important advantages of the heuristic procedure is that it is capable of producing several solutions to a given problem, all rank ordered by increasing cost. Thus, the decision-maker is afforded alternative choices from which he or she may select a replacement policy.     

Adaptive neuro-fuzzy approach for predicting hardness of deposited TiN/ZrN multilayer coatings

This paper presents an adaptive neuro-fuzzy approach based on first order function of fuzzy model for establishing the relationship between control factors and thin films properties of TiN/ZrN coatings on Si(100) wafer substrates. A statistical model was designed to explore the space of the processes by an orthogonal array scheme. Eight control factors of closed unbalance magnetron sputtering system were selected for modeling the process, such as interlayer material, argon and nitrogen flow rate, titanium and zirconium target current, rotation speed, work distance, and bias voltage. Analysis of variance (ANOVA) was carried out for determining the influence of control factors. In this study, with the application of ANOVA, the smallest effect of control factors was eliminated. The adaptive neuro-fuzzy inference system (ANFIS) was applied as a tool to model the deposited process with five significant control factors. The experimental results show that ANFIS demonstrates better accuracy than additive model for the film hardness. The root mean square error between prediction values and experimental values were archived to 0.04.     

Tableting Production Times, Costs and Risks Through-Simulation

As the methods of preparation of pharmaceutical compressed tablets are examined, it becomes evident that there are a number of cost factors which may be significant. These cost factors my be of paramount importance in decision making as to the method of preparation. A comparative study was done to evaluate costs involved in the preparation of tablets by direct compression or the wet granulation procedure at two batch sizes. A simulation model for the processing was used for analysis of the system to optimize batch size, procedure and cost.     

The organizational costs of preventable medical errors

BACKGROUND: Preventable medical errors are associated with additional costs that tend to be borne by patients, but little is known about organizational costs associated with such errors. Two composite case studies (a fall and a delay in diagnosis) were used to identify the organizational costs of preventable medical errors. ANALYSIS: Legal, marketing, and organizational costs--direct, indirect, and long term--were associated with each of the preventable medical errors. A model was generated to examine the theoretical relationship between the costs and four determinants of corporate performance--price, wages, cost of capital, and efficiency. DISCUSSION: Organizations may also have a financial incentive to improve patient safety, for beyond patient and societal costs, preventable medical errors appear to account for significant legal, marketing, and operational costs for the organizations that deliver health care. Some of these costs are not so much the cost of the error but the costs of organizational responses to the error. Three broad areas of inquiry could be used to test the model and improve our understanding of the organizational costs of errors: market response to patient safety interventions, before/after studies of interventions, and case-control studies. SUMMARY AND CONCLUSION: Health care leaders have a moral imperative to implement systems that reduce medical errors and improve patient safety. An understanding of the costs associated with medical errors may help leaders understand the importance of patient safety from a financial perspective, develop measures to evaluate the impact of patient safety initiatives, and efficiently allocate resources to address this important health concern.     

Economic costs of traffic accidents in Jordan.

The objectives of this study were to estimate the economic costs of traffic accidents in Jordan during the year of 1996 and to derive unit accident costs for various accident severity levels. The related data were acquired from different sources, including traffic police records, insurance companies, private hospitals and medical centers. In this study, a framework for applying unit casualty class costs, unit property damage cost, as well as police activities and insurance administration costs to accidents of various severity levels was suggested. The loss-of-output, the loss quality of life, the community and family losses, the temporary and permanent losses, and hospitalization and medical treatment costs were estimated in computing the unit cost for fatalities or injuries of different casualty classes. The vehicle repair cost, detention period cost, and public and private costs were accounted for in estimating the unit cost of property damages. The results indicate that the 1996 traffic accidents cost the country about JD 103 million ($US 146.3 million).