Screening Women for Intimate Partner Violence and Elderly and Vulnerable Adults for Abuse: Systematic Review to Update the 2004 U.S. Preventive Services Task Force Recommendation [Internet]

Excerpt

Background: Intimate partner violence (IPV) and abuse of elders and vulnerable persons is common in the United States and often undetected. Screening individuals without obvious signs of abuse in health care settings could identify those at risk and lead to interventions that reduce exposure to violence and abuse and improve health outcomes.

Purpose: To update the previous 2004 evidence report on screening for IPV and abuse of elders and vulnerable persons for the U.S. Preventive Services Task Force (USPSTF).

Data Sources: We reviewed the Cochrane Central Register of Controlled Trials and Cochrane Database of Systematic Reviews through the fourth quarter of 2011, and MEDLINE and PsycINFO from 2002 to January 9, 2012, for relevant English-language studies, systematic reviews, and meta-analyses. Reference lists of papers and citations of key studies were reviewed manually and by using Scopus.

Study Selection: The screening population included adults who have no obvious signs or symptoms of abuse who interact with health care providers in a number of health care settings. Studies were selected based on preestablished selection criteria using randomized, controlled trials to determine the effectiveness of screening and interventions to reduce abuse and improve health outcomes; studies of diagnostic accuracy to evaluate the ability of screening instruments to identify abused individuals; and studies of any design to determine harms of screening and interventions.

Data Extraction: For studies of screening and interventions, information about the patient populations, study designs, screening methods, types of interventions, followup, methods of analysis, and results were abstracted. For studies of screening instruments, details about the study designs, instruments, reference standards, populations, methods of administration, and results were abstracted. Predefined criteria developed by the USPSTF were used to rate the quality of studies as good, fair, or poor.

Data Synthesis: For IPV, a randomized, controlled trial comparing IPV screening versus no screening in Canadian health care settings indicated that both groups had reductions in IPV recurrence, post-traumatic stress disorder symptoms, and alcohol problems, as well as improvements in scores for quality of life, depression, and mental health after 18 months of followup; however, differences between groups were not statistically significant for these outcomes. Six instruments with 1 to 8 items demonstrated sensitivity and specificity >80 percent in clinical populations of asymptomatic women; results varied between studies and across instruments. A trial of pregnant women reported decreased violence and improved birth outcomes with counseling versus usual care. Two trials of home visitation versus no visitation for young mothers resulted in improved outcomes with visitation. Counseling resulted in decreased pregnancy coercion and resolution of unsafe relationships versus usual care in one trial. Two trials of counseling showed improved outcomes in intervention and control groups without differences between them (counseling vs. referral cards, nurse management vs. usual care in pregnancy).

For abuse of elder and vulnerable adults, few studies met inclusion criteria. A descriptive study of elderly abused veterans who were identified in primary care clinics and referred to case management found that 5 percent were reported to Adult Protective Services and 6 percent required nursing home placement or conservatorship arrangements. A single instrument, the Elder Abuse Suspicion Index, was evaluated for diagnostic accuracy and had sensitivity and specificity of 9 to 47 percent and 75 to 97 percent, respectively, depending on the number of positive responses to specific questions.

Limitations: Studies of IPV were limited by heterogeneity, lack of true control groups, high and/or differential loss to followup, self-reported measures, inadequate power, recall bias, missing data, Hawthorne effect among control participants, and reference standards that were not credible or replicable in diagnostic accuracy studies. Studies of elder and vulnerable adult abuse were lacking.

Conclusions: A trial of screening showed reductions in IPV recurrence and improvement in related outcomes for both screening and comparison groups, but interpretations are limited by high attrition and the Hawthorne effect. Trials of IPV interventions for pregnant women and young mothers showed improved outcomes for the intervention versus usual care groups. Several instruments have been developed for IPV screening; six instruments with 1 to 8 items demonstrated sensitivity and specificity >80 percent in clinical populations of asymptomatic women, although results varied between studies and across instruments. Studies were lacking to address screening elderly and vulnerable adults for abuse.