Dataset Information

Using machine learning to estimate the incidence rate of intimate partner violence.

ABSTRACT: It is difficult to accurately estimate the incidence rate of intimate partner violence (IPV) using traditional social survey methods because IPV victims are often reluctant to disclose their experiences, leading to an underestimation of the incidence rate. To address this issue, we applied machine learning algorithms to predict the incidence rate of IPV in China based on data from the Third Wave Survey on the Social Status of Women in China (TWSSSCW 2010). Specifically, we examined five unbalanced sample-processing methods and six machine learning algorithms, choosing the random under-sampling ensemble method and the random forest algorithm to impute the missing data. Analysis of the complete data showed that the incidence rates of physical violence, verbal violence, and cold violence were 7.10%, 13.74%, and 21.35%, respectively, which were higher than the incidence rates in the original dataset (4.05%, 11.21%, and 17.95%, respectively). The robustness of our findings was further confirmed by analysis using different training sets. Overall, this study demonstrates that better tools need to be developed to accurately estimate the incidence rates of IPV. It also serves as a useful guide for future research that imputes missing data using machine learning.

SUBMITTER: Chen Z

PROVIDER: S-EPMC10073277 | biostudies-literature | 2023 Apr

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Using machine learning to estimate the incidence rate of intimate partner violence.

Chen Zhuo Z Ma Wen W Li Ying Y Guo Wei W Wang Senhu S Zhang Wansu W Chen Yunsong Y

Scientific reports 20230404 1

It is difficult to accurately estimate the incidence rate of intimate partner violence (IPV) using traditional social survey methods because IPV victims are often reluctant to disclose their experiences, leading to an underestimation of the incidence rate. To address this issue, we applied machine learning algorithms to predict the incidence rate of IPV in China based on data from the Third Wave Survey on the Social Status of Women in China (TWSSSCW 2010). Specifically, we examined five unbalanc ...[more]

PMID: 37015976

Similar Datasets

Project description:Lifelong brain health consequences of traumatic brain injury (TBI) include the risk of neurodegenerative disease. Up to one-third of women experience intimate partner violence (IPV) in their lifetime, often with TBI, yet remarkably little is known about the range of autopsy neuropathologies encountered in IPV. We report a prospectively accrued case series from a single institution, the New York City Office of Chief Medical Examiner, evaluated in partnership with the Brain Injury Research Center of Mount Sinai, using a multimodal protocol comprising clinical history review, ex vivo imaging in a small subset, and comprehensive neuropathological assessment by established consensus protocols. Fourteen brains were obtained over 2 years from women with documented IPV (aged 3rd-8th decade; median, 4th) and complex histories including prior TBI in 6, nonfatal strangulation in 4, cerebrovascular, neurological, and/or psychiatric conditions in 13, and epilepsy in 7. At autopsy, all had TBI stigmata (old and/or recent). In addition, white matter regions vulnerable to diffuse axonal injury showed perivascular and parenchymal iron deposition and microgliosis in some subjects. Six cases had evidence of cerebrovascular disease (lacunes and/or chronic infarcts). Regarding neurodegenerative disease pathologies, Alzheimer disease neuropathologic change was present in a single case (8th decade), with no chronic traumatic encephalopathy neuropathologic change (CTE-NC) identified in any. Findings from this initial series then prompted similar exploration in an expanded case series of 70 archival IPV cases (aged 2nd-9th decade; median, 4th) accrued from multiple international institutions. In this secondary case series, we again found evidence of vascular and white matter pathologies. However, only limited neurodegenerative proteinopathies were encountered in the oldest subjects, none meeting consensus criteria for CTE-NC. These observations from this descriptive exploratory study reinforce a need to consider broad co-morbid and neuropathological substrates contributing to brain health outcomes in the context of IPV, some of which may be potentially modifiable.

Project description:BackgroundIntimate partner violence (IPV) is a serious public health issue that consists of physical, sexual, and psychological violence perpetrated by a current or former partner. Informal supporters (e.g., family and friends) of survivors are more often witness to IPV or are the first people a survivor will disclose abuse to and are more able to provide consistent ongoing support than professional services. Therefore, greater understanding of informal supporters is warranted to aid in reducing the risks experienced by survivors. This systematic review aimed to: (1) identify factors associated with either an increase or decrease in helping behaviour toward a survivor, (2), identify the most effective self-care strategies employed by informal supporters, and (3) consider the current theoretical approaches used to understand informal supporters help-giving behavioural intention.MethodsA systematic literature search was conducted following the PRISMA guidelines. The search included English language articles published between 2005 and 2021 in the databases Psych Articles, Scopus, Proquest Social Services Abstracts, and Ebscohost. Studies were included if the primary research aims explored the motivators and inhibitors of helping intention or self-care strategies of adult social network members of adult IPV survivors. Two reviewers independently screened all identified articles for inclusion suitability.ResultsOne hundred and twenty articles were subjected to full text screening resulting in 31 articles being identified as meeting inclusion criteria. Synthesis of the findings identified the following three key areas associated with help-giving behavioural intentions: normative factors, individual factors, and situational factors. There were no articles identified that considered self-care of informal supporters. Of the 31 articles, 22 had a theoretical underpinning. None of the utilised theories explained all three of the identified factors of help-giving behavioural intention.ConclusionThese results are integrated into a proposed Intimate Partner Violence Model of Informal Supporter Readiness (IPV-MISR), incorporating the identified factors associated with help-giving behavioural intention. This model provides a framework for conceptualising the readiness of an informal supporter to provide adequate support to IPV survivors. The model extends existing theoretical standpoints and has utility in both practice and research.

Project description:HIV/AIDS is an ongoing global pandemic, with an estimated 39 million infected worldwide. Early detection is anticipated to help improve outcomes and prevent further infections. Point-of-care diagnostics make HIV/AIDS diagnoses available both earlier and to a broader population. Wide-spread and automated HIV risk estimation can offer objective guidance. This supports providers in making an informed decision when considering patients with high HIV risk for HIV testing or pre-exposure prophylaxis (PrEP). We propose a novel machine learning method that allows providers to use the data from a patient's previous stays at the clinic to estimate their HIV risk. All features available in the clinical data are considered, making the set of features objective and independent of expert opinions. The proposed method builds on association rules that are derived from the data. The incidence rate ratio (IRR) is determined for each rule. Given a new patient, the mean IRR of all applicable rules is used to estimate their HIV risk. The method was tested and validated on the publicly available clinical database MIMIC-IV, which consists of around 525,000 hospital stays that included a stay at the intensive care unit or emergency department. We evaluated the method using the area under the receiver operating characteristic curve (AUC). The best performance with an AUC of 0.88 was achieved with a model consisting of 53 rules. A threshold value of 0.66 leads to a sensitivity of 98% and a specificity of 53%. The rules were grouped into drug abuse, psychological illnesses (e.g., PTSD), previously known associations (e.g., pulmonary diseases), and new associations (e.g., certain diagnostic procedures). In conclusion, we propose a novel HIV risk estimation method that builds on existing clinical data. It incorporates a wide range of features, leading to a model that is independent of expert opinions. It supports providers in making informed decisions in the point-of-care diagnostics process by estimating a patient's HIV risk.

Dataset Information

Using machine learning to estimate the incidence rate of intimate partner violence.

Publications

Using machine learning to estimate the incidence rate of intimate partner violence.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets