<?xml version="1.0" encoding="UTF-8"?>
<feed xmlns="http://www.w3.org/2005/Atom" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <title>DSpace Collection: Sociology Department</title>
  <link rel="alternate" href="http://digitalrepository.fccollege.edu.pk/handle/123456789/472" />
  <subtitle>Sociology Department</subtitle>
  <id>http://digitalrepository.fccollege.edu.pk/handle/123456789/472</id>
  <updated>2026-06-23T20:33:21Z</updated>
  <dc:date>2026-06-23T20:33:21Z</dc:date>
  <entry>
    <title>Predicting high risk pregnancies in Pakistan- a demographic assessment using predictive machine learning</title>
    <link rel="alternate" href="http://digitalrepository.fccollege.edu.pk/handle/123456789/2775" />
    <author>
      <name>Jafree, Dr. Sara Rizvi</name>
    </author>
    <id>http://digitalrepository.fccollege.edu.pk/handle/123456789/2775</id>
    <updated>2025-10-24T11:07:16Z</updated>
    <published>2025-05-21T00:00:00Z</published>
    <summary type="text">Title: Predicting high risk pregnancies in Pakistan- a demographic assessment using predictive machine learning
Authors: Jafree, Dr. Sara Rizvi
Abstract: Pakistan is unable to meet its maternal and child health targets. Predictive machine learn-&#xD;
ing has the potential to predict high risk pregnancies based on data from women who have&#xD;
&#xD;
had a miscarriage or stillbirth. This would help advise better healthcare plans at primary&#xD;
and tertiary level and help achieve Sustainable Development Goal targets in the country.&#xD;
The aim of this study was to evaluate several machine learning models to measure their&#xD;
ability to detect high risk pregnancies. The Pakistan Demographic Health Survey (2018)&#xD;
has been used which includes data from 15,068 women across Pakistan. Fourteen machine&#xD;
&#xD;
learning classifiers have been employed to predict high risk pregnancies, with the follow-&#xD;
ing evaluation metrics reported: precision, recall, false positive rate (FPR), accuracy, and &#xD;
F1-score. We find that five models have the highest overall performance: (i) Deep Neural&#xD;
Network, (ii) SELU Network, (iii) Multilayer Perceptron, (iv) Gradient Boosting, and (v)&#xD;
AdaBoost, exhibiting near good precision (73.0-76.0%), effective recall (83.0-86.0%), ro-&#xD;
bust accuracy (89.0-90.0%), and decent F1-Scores (79.0-80.0%). This study recommends&#xD;
the integration of low-cost online models to predict high risk pregnancies as a critical tool&#xD;
to help achieve maternal health targets in the country.</summary>
    <dc:date>2025-05-21T00:00:00Z</dc:date>
  </entry>
  <entry>
    <title>Empowered by survival: women street vendors in Pakistan’s informal patriarchal economy</title>
    <link rel="alternate" href="http://digitalrepository.fccollege.edu.pk/handle/123456789/2774" />
    <author>
      <name>Jafree, Dr. Sara Rizvi</name>
    </author>
    <id>http://digitalrepository.fccollege.edu.pk/handle/123456789/2774</id>
    <updated>2025-10-24T10:09:44Z</updated>
    <published>2025-06-08T00:00:00Z</published>
    <summary type="text">Title: Empowered by survival: women street vendors in Pakistan’s informal patriarchal economy
Authors: Jafree, Dr. Sara Rizvi
Abstract: Street vending in Pakistan serves as a vital survival enterprise for many&#xD;
women marginalised by the formal education sector and employment&#xD;
structures, driven by poverty and the urgent need to support their&#xD;
households. Operating within the informal economy, these women lack&#xD;
social security and institutional protection. This study aimed to highlight&#xD;
their challenges and inform protective policy measures. Purposive in-depth&#xD;
interviews were conducted with 17 women street vendors from Lahore&#xD;
and Gujranwala, two major cities in Central Punjab. Findings reveal 16 key&#xD;
challenges grouped into five core areas: (1) financial instability, (2) work&#xD;
environment challenges, (3) safety and harassment issues, (4) work-family&#xD;
problems, and (5) health concerns. The study underscores the need for&#xD;
targeted interventions by the state, private sector, and civil society actors,&#xD;
including subsidisation, rent caps, increased surveillance and prompt&#xD;
accountability measures, deployment of women security personnel, and&#xD;
childcare support. These recommendations have broader implications,&#xD;
extending beyond women street vendors to benefit the wider informal&#xD;
workforce in Pakistan and other developing regions.</summary>
    <dc:date>2025-06-08T00:00:00Z</dc:date>
  </entry>
  <entry>
    <title>Predictors of health-seeking behavior in patients with chronic liver disease and a comparison of health-seeking based on patient-type</title>
    <link rel="alternate" href="http://digitalrepository.fccollege.edu.pk/handle/123456789/2773" />
    <author>
      <name>Jafree, Dr. Sara Rizvi</name>
    </author>
    <id>http://digitalrepository.fccollege.edu.pk/handle/123456789/2773</id>
    <updated>2025-10-24T09:46:22Z</updated>
    <published>2025-01-01T00:00:00Z</published>
    <summary type="text">Title: Predictors of health-seeking behavior in patients with chronic liver disease and a comparison of health-seeking based on patient-type
Authors: Jafree, Dr. Sara Rizvi
Abstract: Background Pakistan has one of the highest rates of chronic liver disease (CLD) burden in the world. Poor and&#xD;
underserved patients of CLD in the country may suffer from limited health-seeking behaviors, but there is not much&#xD;
research in this area. The aim of this study is to better plan support for CLD patients by identifying: (i) Health-seeking&#xD;
behaviors (HSB) according to patient-type; and (ii) the relationship of HSB with patient socio-demographic variables&#xD;
and independent study domains.&#xD;
Methods We conducted a cross-sectional study. Data was collected over a four-month period from May 2022 to&#xD;
August 2022. A total of 850 patients visiting the Pakistan Kidney and Liver Institute and Research Centre were part&#xD;
of the study. We used correlation tests and multivariate logistic regression to investigate the relationship between&#xD;
the health-seeking behavior and the independent study domains (economic stability, health literacy, social support,&#xD;
experiencing grief, mental health, healthcare service quality, and coping strategies).&#xD;
Results Main results suggest that patients with hepatocellular carcinoma, non-viral liver disease, and cirrhosis have&#xD;
less HSB, compared to patient with chronic viral hepatitis. Multivariate logistic regression results reveal that the&#xD;
following groups have lower odds for health-seeking behavior: (i) illiterate people; (ii) those living in rented homes; (iii)&#xD;
those belonging to nuclear families; and (iv) those with low monthly household income. The following study domains&#xD;
also show lower odds for HSB: (i) health illiteracy; (ii) low health service quality; (iii) low ability to use coping strategies;&#xD;
(iv) grief; (v) lack of social support; (vi) mental health challenges; and (vii) economic instability.&#xD;
Conclusions Our study highlights that the majority of CLD patients are poor, illiterate, or semi-literate and in urgent&#xD;
need of holistic care with respect to health literacy, mental health counseling, financial help, and improved support&#xD;
from provider and families. This is only possible through the integration of social policy officers and social workers in&#xD;
the tertiary health sector of the country.</summary>
    <dc:date>2025-01-01T00:00:00Z</dc:date>
  </entry>
  <entry>
    <title>Christian Religious Minorities of Pakistan and their Satisfaction with Higher Education and Mental Wellbeing</title>
    <link rel="alternate" href="http://digitalrepository.fccollege.edu.pk/handle/123456789/2772" />
    <author>
      <name>Jafree, Dr. Sara Rizvi</name>
    </author>
    <id>http://digitalrepository.fccollege.edu.pk/handle/123456789/2772</id>
    <updated>2025-10-24T08:00:31Z</updated>
    <published>2025-04-01T00:00:00Z</published>
    <summary type="text">Title: Christian Religious Minorities of Pakistan and their Satisfaction with Higher Education and Mental Wellbeing
Authors: Jafree, Dr. Sara Rizvi
Abstract: The persecution of the Christian religious minorities in Pakistan has implications&#xD;
on exclusion faced in higher educational institutes and mental wellbeing, which&#xD;
ultimately may prevent Christian youth agency. This is one of the first studies in the&#xD;
country that aimed to investigate the relationship between satisfaction with higher&#xD;
education and mental health of Christian students (N = 100) from a large urban city.&#xD;
Mean comparisons suggest that females, those attending public sector institutes,&#xD;
and unemployed Christian students have lower satisfaction with higher education&#xD;
institutes and lower mental wellbeing. Multiple linear regression reveals that mental&#xD;
health is predicted by two domains of satisfaction with higher education- (i) teaching&#xD;
and learning (t = 1.62, p = 0.049); and (ii) student management and guidance by&#xD;
administration. Our study concludes that Christian minorities with intersectional&#xD;
disadvantages who are dissatisfied with higher education face more mental health&#xD;
issues and need targeted interventions to improve educational inequalities and mental&#xD;
wellbeing.</summary>
    <dc:date>2025-04-01T00:00:00Z</dc:date>
  </entry>
</feed>

