The Development of a Short Version of the SIMS Using Machine Learning to Detect Feigning in Forensic Assessment
- PDF / 827,554 Bytes
- 12 Pages / 595.276 x 790.866 pts Page_size
- 53 Downloads / 149 Views
The Development of a Short Version of the SIMS Using Machine Learning to Detect Feigning in Forensic Assessment Graziella Orrù1 · Cristina Mazza2 · Merylin Monaro3 · Stefano Ferracuti4 · Giuseppe Sartori3 · Paolo Roma4 Received: 4 May 2020 / Accepted: 14 September 2020 © The Author(s) 2020
Abstract In the present study, we applied machine learning techniques to evaluate whether the Structured Inventory of Malingered Symptomatology (SIMS) can be reduced in length yet maintain accurate discrimination between consistent participants (i.e., presumed truth tellers) and symptom producers. We applied machine learning item selection techniques on data from Mazza et al. (2019c) to identify the minimum number of original SIMS items that could accurately distinguish between consistent participants, symptom accentuators, and symptom producers in real personal injury cases. Subjects were personal injury claimants who had undergone forensic assessment, which is known to incentivize malingering and symptom accentuation. Item selection yielded short versions of the scale with as few as 8 items (to differentiate between consistent participants and symptom producers) and as many as 10 items (to differentiate between consistent and inconsistent participants). The scales had higher classification accuracy than the original SIMS and did not show the bias that was originally reported between false positives and false negatives. Keywords SIMS · Psychic damage · Malingering · Machine learning · Feature selection
Introduction Malingering is the dishonest and intentional production or exaggeration of physical or psychological symptoms in order to obtain external gain (Tracy & Rix, 2017). Although malingering is coded in both the ICD-11 (World Health Organization, 2019) and the DSM-5 (American Psychiatric Association, 2013), it is not a binary “present” or “absent” phenomenon: it may exist in specific domains (e.g., psychological, cognitive, and medical domains), it is often comorbid with formal disorders (Mazza et al., 2019c; Rogers & Bender, 2018), and it can be classified into several types (Akca et al., 2020; Lipman, 1962; Resnick, 1997). Due to * Cristina Mazza [email protected] 1
Department of Surgical, Medical Molecular & Critical Area Pathology, University of Pisa, Pisa, Italy
2
Department of Neuroscience, Imaging and Clinical Sciences, G. D’Annunzio University, Chieti‑Pescara, Italy
3
Department of General Psychology, University of Padova, Padova, Italy
4
Department of Human Neuroscience, Sapienza University of Rome, Rome, Italy
the considerable variation produced by these nuances, it is difficult to measure the prevalence of malingering in clinical and forensic populations. According to forensic practitioners, malingering likely occurs in 15–17% of forensic cases (Rogers & Bender, 2018; Young, 2014). However, some studies have estimated a much higher prevalence, especially in forensic and non-forensic neuropsychological settings, with approximate rates ranging from 30 to 50% (Ardolf et al., 2007; Chafe
Data Loading...
