Login  |  Join Us  |  Subscribe to Newsletter
Login to View News Feed and Manage Profile
☰
Login
Join Us
Login to View News Feed and Manage Profile
Agency
Agency
  • Home
  • Information
    • Discussion
    • Articles
    • Whitepapers
    • Use Cases
    • News
    • Contributors
    • Subscribe to Newsletter
  • Courses
    • Data Science & Analytics
    • Statistics and Related Courses
    • Online Data Science Courses
  • Prodigy
    • Prodigy Login
    • Prodigy Find Out More
    • Prodigy Free Services
    • Prodigy Feedback
    • Prodigy T&Cs
  • Awards
    • Contributors Competition
    • Data Science Writer Of The Year
  • Membership
    • Individual
    • Organisational
    • University
    • Associate
    • Affiliate
    • Benefits
    • Membership Fees
    • Join Us
  • Consultancy
    • Professional Services
    • Project Methodology
    • Unlock Your Data
    • Advanced Analytics
  • Resources
    • Big Data Resources
    • Technology Resources
    • Speakers
    • Data Science Jobs Board
    • Member CVs
  • About
    • Contact
    • Data Science Foundation
    • Steering Group
    • Professional Standards
    • Government And Industry
    • Sponsors
    • Supporter
    • Application Form
    • Education
    • Legal Notice
    • Privacy
    • Sitemap
  • Home
  • Information
    • Discussion
    • Articles
    • Whitepapers
    • Use Cases
    • News
    • Contributors
  • Courses
    • Data Science & Analytics
    • Statistics and Related Courses
    • Online Data Science Courses
  • Prodigy
    • Prodigy Login
    • Prodigy Find Out More
    • Prodigy Free Services
    • Prodigy Feedback
    • Prodigy T&Cs
  • Awards
    • Contributors Competition
    • Data Science Writer
  • Membership
    • Individual
    • Organisational
    • University
    • Associate
    • Affiliate
    • Benefits
    • Membership Fees
    • Join Us
  • Consultancy
    • Professional Services
    • Project Methodology
    • Unlock Your Data
    • Advanced Analytics
  • Resources
    • Big Data Resources
    • Technology Resources
    • Speakers
    • Data Science Jobs Board
    • Member CVs
  • About
    • Contact
    • Data Science Foundation
    • Steering Group
    • Professional Standards
    • Government And Industry
    • Sponsors
    • Supporter
    • Application Form
    • Education
    • Legal Notice
    • Privacy
    • Sitemap
  • Subscribe to Newsletter

Piecewise hazard model for under-five child mortality

A DSF Whitepaper
09 November 2020
Rakesh Saroj
Author Profile
Other Articles
Follow (6)

Share with your network:

Introduction: The application of piecewise hazard model in mortality data becomes more useful in survival methods. This method is used to find the number and location cut points and to estimate the hazard model. The objective of this paper is to illustrate the piecewise constant hazard model and to find significant factors for under-five child mortality.

Materials and Methods: The piecewise hazard model is illustrated on secondary data National Family health Survey (NFHS-IV). The piecewise constant hazard model is fitted on mortality data by using socio-demographic, biological and proximate co-factors. Free R software is used for analysis purpose.

Results: It is found that women’s age in years, total children ever born, present breastfeeding, smoking, size of child, delivery by caesarean section, ANC visits, and birth orders are important factors and six month time interval is very crucial for child till completing the five year of the age.

Conclusion: Piecewise hazard model is found very important for the under-five child mortality, through various times cut points. The Piecewise hazard model can be useful for clinicians, researchers and public health experts. Time is very important factor for reducing the child mortality.

Introduction

he survival analysis is a technique to estimate the patient's survival that after treatment in a specifics infection. The survival analysis uses in life the survival status of patients. The survival probability S (t) also known as survivor function, and it described the individuals survival time in specified time period t. The second term hazard is represented by h (t) or λ (t) and hazard rate is defined as instantaneous failure rate for the survivors to time t during the next instant of time. The survival probability is evaluated by nonparametric methods from observed survival times for uncensored and censored cases with the help of KM or product-limit method.[1] The Cox PH regression technique is used to find the association between survival time of patients and one or more indicator variables.[2] The Cox PH regression models characteristic log of the risk at time t, denoted by h(t), as a function of the baseline hazard (h0(t))and a few indicator factors x1,x2.....xn The model is given by

 

Take the exponentiation both sides of the equation, and limit the right hand side to just a single categorical exposure variable (x1) with two groups (x1=1 for exposed and x1=0 for unexposed), the equation becomes:

 

After solving the equation estimate the hazard ratio, comparing the exposed to the unexposed individuals at time t is given by

The eβ1 is the hazard ratio and other constant over time t. The β is the regression co-efficient that estimate from model and represent the log(Hazard Ratio) for each unit increase in the corresponding predictor variable.

Let x be the row vector of explanatory variables, and β be the corresponding column vector of coefficients. The λ(t,x,β)hazard model is given by,

 

λ0(t) is called the baseline hazard. There are several choices for the baseline hazard models are exponential hazard model, Weibull hazard model and Piecewise-constant hazard model.

PIECEWISE-CONSTANT HAZARD MODEL

An essential expansion of the exponential model is known as piece-wise exponential model or piecewise- constant hazard model. This model originates from an appropriation whose hazard rate is a step function. The model, need to segment the survival into a numerous pieces. In this model accept that inside each segment, the hazard is constant but between segments, hazard could be different.

The hazard function can be written as:

 

In this study assessing the basic hazard function with possible time change points. It will demonstrate the survival pattern of the patients and which time points is more failure or more censored. Assessing the survival trend for entire population will give better understanding of how changing treatment, patients monitoring, health facilities of patients, and public health services. Past researches have proposed strategies for estimating a single change point in a piecewise constant hazard function when the observed variables are subject to random censoring.[3] The research is shown multiple change points in piecewise constant hazard functions.[4] The study suggested a piecewise-exponential methodology where Poisson regression model parameters are estimated from pseudo likelihood and comparing differences were determined by Taylor linearization strategies.[5] In study, It is estimated that the population attributable fraction for mortality in a cohort study using a piecewise constant hazards model.[6] Another study is demonstrated the cancer research using a reduced piecewise exponential approach.[7] The research considers parameter estimation in the hazard rate with multiple change points in the presence of long-term survivors.[8] In research article, it is shown that a survival analysis in context of new method suggest to estimate the piecewise constant hazard rate model.[9] Another study has been done to find the survival status of under-five child mortality in Uttar Pradesh.[10] Recent articles use the survival parametric models to estimate the factors of under five child mortality data.[11]

However, previous studies did not determine the impact of factors on under-five child mortality with the help of piecewise constant hazard model.

The key interest of this paper is to determine the potential determinants of under-five child mortality of data of Uttar Pradesh using piecewise constant hazard model. In this model, the various time points are used to find the crucial time points and explain the important factors for reducing the under-five child mortality.

Material and Methods

This paper investigates the determinants of under-five child mortality in Uttar Pradesh using the (NFHS-IV) data. The piecewise hazards model is used to evaluate the comparative impact of the hypothesized factors on under-five child mortality. For analysis purpose, the age of the children in months is ascertained as pursues: age = V008 – B3, where V008 is the century month code (CMC) of the date of meeting, and B3 is the CMC for date of birth of the kid. The responsible factors for under-five child mortality are selected according by the citation. [12]

These components are sorted into the additional four categories; Social demographic and social economic, environmental and proximate or biological factors but in this paper used the analysis based on three social demographic and social economic, proximate and biological factors only. There are several kinds of hazard model available and a piecewise constant proportional hazards model is used in this study.

Let X1,X2.....Xn denote independent identically distributed survival times, and C1,C2.....Cn be the censoring times which are assumed to be independent of X. We have only observed the pairs, (Ti,δi),i= 1,2,....n,where Ti = min(Xi,Ci) and if and zero otherwise. Consider the following change point model:

 

,0 < τ1 <.....< τk, where, K is the number of change points in the model, αj and is the value of the hazard function between the time points τj-1 and τj. The τ0j. can be thought of as the order statistics for the change points in the hazard function. The time axis is split into sections in a piecewise constant model and a constant hazard is presumed within each section. In this analysis the time axis is divided into nine groups: 0-6 months, 6-12 months, 12-18 months, 18-24 months, 24-30 months, 31-36 months,36-42 months ,42-48 months and 48-59 months. The baseline hazard λ(t)describes how the mortality rate changes with the age of the child. This is parameterized as a piecewise constant function.

 

Remark: The significant factors are calculated for under-five child mortality through Cox –regression analysis. These important factors are used in the piece-wise constant hazard analysis in this paper.

Results

Table 1.1 shows that survival status of under-five year children. In this table shows that total 93% cases censored because child death considered as main event. Total survival time of children is 59 months shows in Figure 1.1 and plot shows the survival probability and censor cases report of children, where plus (+) symbols represented as the censored.

In this paper, the hazard rate is calculated for under-five child mortality at different time points for piecewise hazard analysis. The time points have been distributed in six months, ten months, eleven months and twelve months in Table 1.2. The hazard rate variation shows in Figure 1.2 at the six, ten, eleven and twelve month’s interval. The figure clearly shows that maximum number of disparity of hazard rate in six month intervals therefore the six month time interval has been selected for piecewise hazard analysis. The piecewise constant hazards model is used at different time intervals and significant factors are examined and compared with the estimates obtained by means and hazard function at various seven time points. The hazard function value comes between defined pieces or interval time in months of all patients. For specifying the model with a smooth hazard function, the follow-up period is divided in seven consecutive intervals of fifty-nine months length. The first piecewise hazard model includes educational level, religion and women's age in years for the analysis of under-five child mortality status. This model breaks the data into pieces, where may fit constant hazards within these pieces. Table 1.3 shows the result of piecewise constant hazards model and it is found that educational level and women's age are found significant factor in piecewise hazard model. Figure 1.3 shows the detail of first model including factors with a piecewise constant hazard function, piecewise constant cumulative hazard function, piecewise constant density function and piecewise constant survivor seven consecutive intervals till fifty-nine months. In this figure peak of the hazards continuously increasing respect to increasing time. The second piecewise constant hazards model includes proximate and biological factor for under-five child mortality.

Table 1.4 shows the output of proximate and biological factors role in under-five child mortally status and this model result found that all the factors have significant effects on under-five child mortality.

Figure 1.4 shows the piecewise constant hazard function, piecewise constant cumulative hazard function, piecewise constant density function and piecewise constant survivor seven consecutive intervals till fifty-nine months including proximate and biological factors. Finally selected all significant factors and combined together to check effect of the factors in under-five child mortality status through piecewise constant hazard model. Table 1.5 shows that the factors women's age in years, total children ever born, birth in last five years, number of living children, present breastfeeding, smoking, desire for more children, size of child, delivery by caesarean section, ANC visits and birth orders have significant effect in under-five child mortality in the pricewise constant hazard model. Figure 1.5 shows the piecewise constant hazard function, piecewise constant cumulative hazard function, piecewise constant density function and piecewise constant survivor seven consecutive intervals till fifty-nine months including all factors.

Discussion

This paper is analyzed the determinants and critical time point of under-five child mortality in Uttar Pradesh using the (NFHS-IV) data through piecewise constant hazard model. This is the first time this kind of analysis has been done and the results are really significant in gaining an overall insight into under-five child mortality differentials in Uttar Pradesh. This analysis shows that six months of the children increase the risk of death under age five year. The hazard rate is supposed to be constant on some pre-defined time intervals and plotting the hazard rate gives a quick idea of the progress of the event of interest through time. Different time periods for evaluation of mortality, extend from 28 days to a half year and including 35 days, 60 days, and 90 days. It has been utilized in earlier clinical trials [13], while this model used in a nonparametric setting, usually utilized in mix with covariates impacts. [14] The applicability in the situation for the popular Poisson regression model, [15] and to find the relative impact on the covariates and a piecewise constant hazard model for the baseline hazard. [16] Proposed an imaginative strategy to evaluate the hazard rate in a piecewise constant model. This technique gives a programmed strategy to locate the number of cut points and to estimate the hazard on each cut interval. This model is exceptionally helpful to find the patient hazard in various time points.

Conclusion

In conclusion, piece-wise constant hazard model has been used for finding the crucial month period and significant factors in under-five child mortality. In study, it is found that proximate and biological factors are more critical for under-five child mortality and half year or six months are extremely urgent for children till completing five years of age. These outcomes can advise the determination of time points for evaluating survival status of under-five child mortality. The results suggest to focus on different significant factors for achieving a decline in under-five child mortality. This model would be useful in health care policy makers and with an upgraded comprehension of the adjustments in population death rates can recognize gaps, seek solutions, improve performance, and ultimately, better the public’s health. The government should also put more emphasis on programmes aimed at population with under-five child mortality.

Funding: There is no financial support for this study/paper

Declaration of conflicting interests: The authors declare no conflict of interest.

Table 1.1 Status of child survival of under-five year

Total N N of Events (Deaths) Censored
N Percent
41751 2830 38921 93.20%

Table 1.2 Hazard rate of the under-five year age of children

Time Hazard
Hazard Rate for 6 months intervals
0-6 0.064
7-12 0.078
13-18 0.065
19-24 0.07
25-30 0.075
31-36 0.07
37-42 0.069
43-48 0.079
49-54 0.069
55-59 0.07
Hazard Rate for 10 months intervals
0-10 0.067
11-20 0.066
21-30 0.073
31-40 0.078
41-50 0.077
51-59 0.068
Hazard Rate for 11 months intervals
Time Hazard
0-11 0.07
12-22 0.066
23-33 0.068
34-44 0.068
45-59 0.068
Hazard Rate for 11 months intervals
0-12 0.074
13-24 0.067
25-36 0.069
37-48 0.074
49-59 0.068

Table 1.3 Piecewise constant hazards model with socio-economic and demographic factors

S.No. Covariate W.mean Coef Exp(Coef) Wald p
1 Education Status 1.05 -0.145 0.086 0
2 Religion 1.22 -0.082 0.921 0.06
3 Women's age in years 28.53 -0.042 0.959 0

Table 1.4 Piecewise constant hazards model with proximate and biological factors

S.No. Covariate W.mean Coef Exp(Coef) Wald p
1 Currently Breastfeeding 0.55 -0.75 0.468 0
2 Anemia level 3.25 -0.09 0.911 0
3 Desire for more children 4.2 -0.33 0.716 0
4 Size of child 3.12 0.15 0.16 0
5 Child Birth weight (kg) 6348.05 0 1 0.003
6 ANC Visits 0.12 -0.53 0.58 0
7 Birth order 1.95 -0.09 0.91 0.026
8 Smokes 0 1.37 3.96 0.017
9 Delivery by caesarean section 0.08 0.27 1.31 0
10 Total children ever born/td> 3.23 0.19 1.21 0

Table 1.5 Piecewise constant hazards model with combined variables

S.No. Covariate W.mean Coef Exp(Coef) Wald p
1 Women's age in years 28.54 -0.04 0.95 0
2 Education 1.05 -0.02 0.98 0.32
3 Religion 1.22 -0.005 0.99 0.91
4 Total children ever born 3.23 0.48 1.63 0
5 Birth in last five years 1.72 0.32 1.38 0.003
6 Number of living children 2.88 -0.99 0.36 0
7 Currently Breastfeeding 0.55 -0.41 0.65 0
8 Smoking 0 1.97 7.19 0.001
9 Desire for more children 4.19 -0.16 0.85 0
10 Size of child 3.12 0.17 1.18 0
11 Delivery by caesarean section/td> 0.08 0.14 1.15 0.03
12 ANC Visits 0.12 -0.4 0.66 0
13 Birth order 1.95 0.57 1.78 0

Figure 1.1:Under-Five child mortality survival status

 

Figure 1.2 Hazard rate graph of according to various month intervals

 
 
 
 

Figure 1.3 Piecewise constant hazards, cumulative hazard, density and survivor function with covariates

 

Figure 1.4 Piecewise constant hazards, cumulative hazard, density and survivor function with covariates

 

Figure 1.5 Piecewise constant hazards, cumulative hazard, density and survivor function with covariates

 

REFERENCES:

  1. Kaplan, E. L., and Meier, P. Non-parametric Estimation from Incomplete Observations. Journal of the American Statistical Association; 1958:53 (282), 457 – 481.
  2. Cox, D.R. Regression models and life tables (with Discussion). Journal of the Royal Statistical Society; 1972: 34,187-220.
  3. Gijbels I, GürlerU. Estimation of a change point in a hazard function based on censored data. Lifetime Data Anal; 2003: 9,395–411.
  4. Melody S. Goodman, Yi Li, and Ram C. Tiwari, Detecting multiple change points in piecewise constant hazard functions, Journal of Applied Statistics; 2011: 38(11), 2523–2532.
  5. LiY., Gail M.H., Preston D.L., Graubard B.I., Lubin J.H. Piecewise exponential survival times and analysis of case-cohort data. Statistics in Medicine; 2012:31(13), 1361–1368.
  6. Maarit A. Laaksonen Paul, Knekt Tommi ,Härkänen Esa, Virtala Hannu Oja Estimation of the population attributable fraction for mortality in a cohort study using a piecewise constant hazards model, American Journal of Epidemiology; 2010) : 71(7), 837–847.
  7. Gang Han Michael J. Schell Jongphil Kim. Improved survival modeling in cancer research using a reduced piecewise exponential approach, Statistics in Medicine: Statistical Methods in Medical Research; 2014: 33, 1.
  8. Wei Zhang, Lianfen Qian & Yunxia Li. Semi parametric Sequential Testing for Multiple Change Points in Piecewise Constant Hazard Functions with Long-Term Survivors, Communications in Statistics - Simulation and Computation;2014: 43(7),1685-1699.
  9. Bouaziz, O. and Nuel, G. L0 Regularization for the estimation of piecewise constant hazard rates in survival analysis. Applied Mathematics; 2017: 8 (3), 377-394.
  10. Saroj R., Murthy K.N., Kumar M. Survival analysis for under-five child mortality in Uttar Pradesh, International Journal of Research and Analytical Reviews;2018:5,3.
  11. Saroj RK, Murthy K H, Kumar M, Singh R, Kumar A. Survival parametric models to estimate the factors of under-five child mortality. Journal of Health Research and Reviews; 2019; 6:82-8.
  12. Mosley W, Chen L. An analytical framework for the study of child survival in developing countries. Population and Development Review; 1984:10, 24-45.
  13. Ronco C, Bellomo R, Homel P, Brendolan A, Dan M, Piccinni P, La Greca G. Effects of different doses in continuous veno-venous haemofiltration on outcomes of acute renal failure: A prospective randomized trial. Lancet; 2000: 356, 26–30.
  14. Gastaldello K, Melot C, Kahn R-J, Vanherweghem J-L, Vincent J-L, Tielemans. Comparison of cellulose diacetate and polysulfone membranes in the outcome of acute renal failure. A prospective randomized study. Nephrology Dialysis Transplantation; 2000: 15, 224–230.
  15. Clayton, D., Hills, M. & Pickles, A. Statistical models in epidemiology; 1993: 161.
  16. Aalen, O.O.,Borgan, & Gjessing, H. K. Survival and Event History Analysis. Statistics for Biology and Health. Springer; 2008.
Rate this Whitepaper
Rate 1 - 10 by clicking on a star
(2 Ratings) (0 Comments) (2454 Views)
Download

If you found this Whitepaper interesting, why not review the other Whitepapers in our archive.

Login to Comment and Rate

Email a PDF Whitepaper

Comments:

Categories

  • Data Science
  • Data Security
  • Analytics
  • Machine Learning
  • Artificial Intelligence
  • Robotics
  • Visualisation
  • Internet of Things
  • People & Leadership Skills
  • Other Topics
  • Top Active Contributors
  • Balakrishnan Subramanian
  • Abhishek Mishra
  • Mayank Tripathi
  • Michael Baron
  • Santosh Kumar
  • Recent Posts
  • AN ADAPTIVE MODEL FOR RUNWAY DETECTION AND LOCALIZATION IN UNMANNED AERIAL VEHICLE
    12 November 2021
  • Deep Learning
    05 November 2021
  • Machine Learning
    05 November 2021
  • Data is a New oil : A step into WSN enabled IoT and security
    26 October 2021
  • Highest Rated Posts
  • Piecewise hazard model for under-five child mortality
  • TOP 10 BEST FREE AND OPEN SOURCE BACKUP SOLUTIONS
  • DEEP LEARNING: FIGHTING COVID-19 WITH NEURAL NETWORKS
  • The transformational shift in educational outcomes in London 2003 to 2013: the contribution of local authorities
  • Understanding Imbalanced Datasets and techniques for handling them
To attach files from your computer

    Comment

    You cannot reply to your own comment or question. You can respond to another member's comment in this thread.

    Get in touch

     

    Subscribe to latest Data science Foundation news

    I have read and agree to the Data science Foundation Privacy Policy

    • Home
    • Information
    • Resources
    • Membership
    • Services
    • Legal
    • Privacy
    • Site Map
    • Contact

    © 2022 Data science Foundation. All rights reserved. Data S.F. Limited 09624670

    Site By-Peppersack

    We use cookies

    Cookie Information

    We are using cookies to provide statistics that help us to improve your experience of our site. You can choose to use the site without cookies. However, by continuing to use the site without changing your settings, you are agreeing to our use of cookies.

    Contact Form

    This member is participating in the Prodigy programme. This message will be directed to Prodigy Admin the Prodigy Programme manager. Find out more about Prodigy

    Complete your membership listing and tell others about your interests, experience and qualifications with a Personal Profile page.

    Add a Personal Profile

    Your Personal Profile page is missing information about your experience and qualifications that other members would find interesting. Click here to update.

    Login / Join Us

    Login to your membership account to view your personalised news feed, update your profile, manage your preferences. publish articles and to create a following.

    If you are not a member but work with or have an interest in Data Science, Machine Learning and Artificial Intelligence, join us today.

    Login | Join Us

    Support the work of the Data Science Foundation

    Help to fund our work and enable us to provide free communications and knowledge sharing services to members across the globe.

    Click here to set-up a donation of £30 per year

    Follow

    Login

    Login to follow this member

    Login