Using Social Signals to Predict Shoplifting: A Transparent Approach to a Sensitive Activity Analysis Problem.

Retail shoplifting is one of the most prevalent forms of theft and has accounted for over one billion GBP in losses for UK retailers in 2018. An automated approach to detecting behaviours associated with shoplifting using surveillance footage could help reduce these losses. Until recently, most state-of-the-art vision-based approaches to this problem have relied heavily on the use of black box deep learning models. While these models have been shown to achieve very high accuracy, this lack of understanding on how decisions are made raises concerns about potential bias in the models. This limits the ability of retailers to implement these solutions, as several high-profile legal cases have recently ruled that evidence taken from these black box methods is inadmissible in court. There is an urgent need to develop models which can achieve high accuracy while providing the necessary transparency. One way to alleviate this problem is through the use of social signal processing to add a layer of understanding in the development of transparent models for this task. To this end, we present a social signal processing model for the problem of shoplifting prediction which has been trained and validated using a novel dataset of manually annotated shoplifting videos. The resulting model provides a high degree of understanding and achieves accuracy comparable with current state of the art black box methods.

Self-employment, depression, and older individuals: A cross-country study.

BACKGROUND: Self-employment has become an increasingly popular occupational choice, and there are substantial mental health and well-being benefits that can accrue for individuals who remain active and engaged later in life. In this study, we examine the association between reduced depression symptoms and self-employment in aging workers. METHODS: Drawing from The Survey of Health, Ageing and Retirement in Europe (SHARE) data, our study examines a longitudinal sample of 35,717 individuals aged 50 years or older. RESULTS: Our results indicate that self-employment is negatively associated with depression among aging workers. Additionally, we find that this relationship weakens as aging self-employed individuals grow older, and that gender moderates this relationship such that older female self-employed individuals report lower depression symptoms than their male counterparts. LIMITATIONS: Our sample is limited to European workers aged 50 years and older, and as such might have limited generalizability to younger self-employed individuals from other geographic regions. Moreover, although we control for factors that could play a role in the association between depression symptoms and self-employment (e.g. quality of life, personality traits, etc.), additional research will be needed in order to determine the potential mediating and moderating roles such factors might have on this relationship. CONCLUSIONS: The results we present demonstrate the important and nuanced nature between self-employment and depression symptoms in aging workers. These findings call to light the need to continue to foster and develop systems and programs that help to facilitate self-employment for individuals as they transition into older ages.

Pregabalin Did Not Improve Pain Management After Spinal Fusions.

BACKGROUND: The treatment of postoperative pain is a challenge after posterior spinal fusions. Pain management using predominantly opioids is often associated with multiple adverse effects, while multimodal postoperative analgesia may provide adequate pain relief with fewer opioid side effects. QUESTIONS/PURPOSES: The purpose of this review is to determine whether addition of 150 mg pregabalin daily would reduce narcotic requirements and improve outcomes after posterior lumbar fusion (PLF). METHODS: The method used is a randomized, controlled trial of elective PLF patients who received pregabalin or placebo. With institutional review board (IRB) approval, 86 patients undergoing elective posterior lumbar fusion, ASA I-III, were randomized to receive either a placebo or pregabalin after obtaining written informed consent. Both arms, i.e., placebo and pregabalin, consisted of 43 patients each.The 86 patients for elective PLF were randomly assigned to receive 150 mg of pregabalin 1 h before surgery and then 150 mg daily, or a placebo tablet. All patients received a similar general anesthetic and in the post-anesthesia care unit (PACU), started on intravenous (IV) patient-controlled analgesia (PCA) of hydromorphone (0.2 mg/ml). Postoperative pain was assessed daily until discharge using a Numerical Rating Scale (NRS) at rest and with physical therapy (PT). Patients were also assessed twice daily for level of sedation and nausea and/or vomiting and expected PT milestones. All narcotics (IV, oral) were documented. RESULTS: Demographics and operative time between groups were similar. PCA hydromorphone administration and oral narcotic intake were not statistically different between the two groups. However, an increased incidence of nausea and vomiting in the placebo group reached statistical significance (p < 0.05). In addition, there was no statistical difference between groups with respect to achieving PT milestones and hospital discharge day. CONCLUSION: After PLF, patients receiving pregabalin 150 mg/day did not have reduced IV narcotic usage, improved PT milestones, or reduced length of hospital stay. We were unable to demonstrate an analgesic advantage to prescribing pregabalin to patients undergoing lumbar spinal fusions.

Patient-controlled epidural analgesia or multimodal pain regimen with periarticular injection after total hip arthroplasty: a randomized, double-blind, placebo-controlled study.

BACKGROUND: The optimal postoperative analgesia after primary total hip arthroplasty remains in question. This randomized, double-blind, placebo-controlled study compared the use of patient-controlled epidural analgesia (PCEA) with use of a multimodal pain regimen including periarticular injection (PAI). We hypothesized that PAI would lead to earlier readiness for discharge, decreased opioid consumption, and lower pain scores. METHODS: Forty-one patients received PAI, and forty-three patients received PCEA. Preoperatively, both groups were administered dexamethasone (6 mg, orally). The PAI group received a clonidine patch and sustained-release oxycodone (10 mg), while the PCEA group had placebo. Both groups received combined spinal-epidural anesthesia and used an epidural pain pump postoperatively; the PAI group had normal saline solution, while the PCEA group had bupivacaine and hydromorphone. The primary outcome, readiness for discharge, required the discontinuation of the epidural, a pain score of <4 (numeric rating scale) without parenteral narcotics, normal eating, minimal nausea, urination without a catheter, a dry surgical wound, no acute medical problems, and the ability to independently transfer and walk 12.2 m (40 ft). RESULTS: The mean time to readiness for discharge (and standard deviation) was 2.4 ± 0.7 days (PAI) compared with 2.3 ± 0.8 days (PCEA) (p = 0.86). The mean length of stay was 3.0 ± 0.8 days (PAI) compared with 3.1 ± 0.7 days (PCEA) (p = 0.46). A significant mean difference in pain score of 0.74 with ambulation (p = 0.01; 95% confidence interval [CI], 0.18 to 1.31) and 0.80 during physical therapy (p = 0.03; 95% CI, 0.09 to 1.51) favored the PCEA group. The mean opioid consumption (oral morphine equivalents in milligrams) was significantly higher in the PAI group on postoperative day 0 (43 ± 21 compared with 28 ± 23; p = 0.002) and postoperative days 0 through 2 (136 ± 59 compared with 90 ± 79; p = 0.004). Opioid-Related Symptom Distress Scale (ORSDS) composite scores for severity and bothersomeness as well as scores for nausea, vomiting, and itchiness were significantly higher in the PCEA group (p < 0.05). Quality of Recovery-40 scores and patient satisfaction were similar. CONCLUSIONS: PAI did not decrease the time to discharge and was associated with higher pain scores and greater opioid consumption but lower ORSDS scores compared with PCEA. The choice for analgesic regimen may depend on a particular patient's threshold for pain and the potential side effects.

Clinical outcomes in patients with pulmonary hypertension undergoing total hip arthroplasty.

BACKGROUND: Pulmonary hypertension (PH) is regarded as a risk factor for perioperative complications in patients undergoing noncardiac surgery. QUESTIONS/PURPOSES: The objective of this retrospective case-control study was to evaluate the adverse outcomes of pulmonary hypertension patients undergoing elective unilateral hip replacements. METHODS: We performed a retrospective case-control study of total hip replacement patients with pulmonary hypertension (cases) and without pulmonary hypertension (control). From the years 2003 to 2008, we identified a total of 132 patients undergoing primary total hip replacements with a diagnosis of pulmonary hypertension (right ventricular systolic pressure >35). The primary outcome assessed was the incidence of adverse events that occurred during the postoperative hospital stay. Secondary outcomes studied included length of hospital stay, mortality, and ability to reach certain physical therapy milestones. RESULTS: The PH group had significantly more adverse events than the control group. Nonlethal cardiac dysrhythmias comprised the most common adverse outcome among the PH group. Overall, the PH group had a morbidity rate of 34.7% while the control had a rate of 21%. The PH group had longer hospital stay (6.7 days vs. 5.9). Both groups had zero mortality during the hospital stay. The PH group had comparable rehabilitation recovery times than the control group. CONCLUSION: This retrospective case-control study demonstrates that pulmonary hypertension patients undergoing total hip arthroplasty are more prone to adverse outcomes, especially cardiac dysrhythmias, and longer hospital stays.

Nerve stimulator versus ultrasound guidance for placement of popliteal catheters for foot and ankle surgery.

STUDY OBJECTIVE: To determine whether ultrasound guidance improves the quality of continuous popliteal block when compared with a nerve stimulator after major foot and ankle surgery. DESIGN: Prospective, randomized, double-blinded clinical trial. SETTING: Operating room, Postanesthesia Care Unit (PACU), and hospital wards of a university-affiliated hospital. PATIENTS: 45 ASA physical status 1, 2, and 3 patients undergoing elective major foot and ankle surgery. INTERVENTIONS: Placement of a popliteal sciactic nerve catheter using either nerve stimulator or ultrasound guidance. In the PACU, a continuous infusion of ropivacaine 0.2% was started at a basal rate of 4 mL/hr and adjusted in a standardized fashion to maintain visual analog scale (VAS) pain scores < 4. All patients also received intravenous (IV) patient-controlled analgesia with hydromorphone and oral opioids. MEASUREMENTS: VAS pain scores at rest and with physical therapy, ropivacaine use, opioid use, and opioid-related side effects were recorded. MAIN RESULTS: Cummulative ropivacaine use was lower in patients whose catheter was placed by ultrasound than by nerve stimulator guidance (mean 50 vs 197 mL, P < 0.001). Pain scores at rest and during activity were similar between groups. Cumulative opioid consumption (mean 858 vs 809 mg oral morphine equivalents) and daily frequencies of nausea (5% to 33% vs 0 to 24%) and pruritus (0 to 21% vs 0 to 24%) were similar between groups. Length of hospital stay was similar between groups (3.5 vs 3.7 days). CONCLUSIONS: Ultrasound guidance was associated with less local anesthetic consumption than with the nerve stimulator; however, there was little clinical benefit, as all other outcomes were similar between groups.

Perioperative inflammatory response in total knee arthroplasty patients: impact of limb preconditioning.

BACKGROUND AND OBJECTIVES: Ischemic preconditioning of tissue that is to undergo procedure-induced underperfusion has been used in a number of surgical settings to reduce the subsequent inflammatory response and its sequelae. The objective of this prospective, randomized study was to evaluate the effect of ischemic preconditioning on the systemic inflammatory response, degree of lung catabolism, and postoperative-pain associated with total knee arthroplasty (TKA). MATERIALS: Thirty-four patients undergoing unilateral TKA under tourniquet ischemia were enrolled with half (n = 17) being randomized to an episode of limb preconditioning before induction of ischemia for surgery. Markers of inflammation (interleukin 6 [IL-6], C-reactive protein,tumor necrosis factor >, and leukocyte count) and elastin catabolism(desmosine) were measured at baseline and various points postoperatively.Pain scores and length of stay were recorded. RESULTS: A significant increase in the levels of IL-6, C-reactive protein,tumor necrosis factor >, and white blood cell count was observed after surgery in both groups. Despite trends toward decrease in the IL-6 level in the preconditioning group, no significant difference between groups was observed for all markers at any given time point. Urine desmosine-creatinine-ratios did not differ between groups, and no significant-changes from baseline were seen postoperatively. However, median pain scores and length of hospital stay were lower in the treatment group. CONCLUSIONS: Preconditioning of the lower extremity in the setting of TKA under regional anesthesia may have limited value in reducing the systemic inflammatory response and level of lung injury. However, preconditioning may be associated with beneficial effects such as reduction in postoperative pain levels, and thus, further investigations are warranted.

Trends in bilateral total knee arthroplasties: 153,259 discharges between 1990 and 2004.

UNLABELLED: Information regarding national trends in bilateral TKAs is needed for a rational allocation of resources, policy making, and research. Therefore, we analyzed data from the National Hospital Discharge Survey to elucidate temporal changes in the demographics, comorbidity profiles, hospital stay, and in-hospital complications of patients undergoing bilateral TKAs in the United States. We created three 5-year periods: 1990-1994, 1995-1999, 2000-2004. Procedure, healthcare system, and patient-related variables were analyzed for an estimated 153,259 discharges. Use of bilateral TKAs more than doubled for the entire civilian population and almost tripled among the female population, with the steepest increase seen during the last two study periods. A decline of nearly 50% in the use of bilateral TKAs in patients 85 years and older was seen between the second and third study periods. The prevalence of coronary artery disease and pulmonary disease increased from the first to the second study periods but decreased from the second to the third. The changes in the variables studied may reflect a recently acquired reluctance to perform bilateral TKAs in elderly patients with cardiopulmonary comorbidities. Additional studies are necessary to identify other causal relationships and define the impact of these changes on various aspects of the healthcare system. LEVEL OF EVIDENCE: Level II, prognostic study. See the Guidelines for Authors for a complete description of levels of evidence.