More Like this

1. Facial Recognition: Understanding Concerns and Privacy Attitudes Across Increasingly Diverse Deployment Scenarios

   Zhang, S. ; Feng, Y. ; Sadeh, N. ( January 2021 , USENIX Symposium on Usable Privacy and Security)

   null (Ed.)

   The rapid growth of facial recognition technology across ever more diverse contexts calls for a better understanding of how people feel about these deployments — whether they see value in them or are concerned about their privacy, and to what extent they have generally grown accustomed to them. We present a qualitative analysis of data gathered as part of a 10-day experience sampling study with 123 participants who were presented with realistic deployment scenarios of facial recognition as they went about their daily lives. Responses capturing their attitudes towards these deployments were collected both in situ and through daily evening surveys, in which participants were asked to reflect on their experiences and reactions. Ten follow-up interviews were conducted to further triangulate the data from the study. Our results highlight both the perceived benefits and concerns people express when faced with different facial recognition deployment scenarios. Participants reported concerns about the accuracy of the technology, including possible bias in its analysis, privacy concerns about the type of information being collected or inferred, and more generally, the dragnet effect resulting from the widespread deployment. Based on our findings, we discuss strategies and guidelines for informing the deployment of facial recognition, particularly focusing on ensuring that people are given adequate levels of transparency and control. 

   more » « less
2. Surveillance imaging for patients with head and neck cancer treated with definitive radiotherapy: A partially observed Markov decision process model

   https://doi.org/10.1002/cncr.32597  

   Ng, Sweet Ping ; Ajayi, Temitayo ; Schaefer, Andrew J. ; Pollard, III, Courtney ; Bahig, Houda ; Garden, Adam S. ; Rosenthal, David I. ; Gunn, G. Brandon ; Frank, Steven J. ; Phan, Jack ; et al ( November 2019 , Cancer)

   A possible surveillance model for patients with head and neck cancer (HNC) who received definitive radiotherapy was created using a partially observed Markov decision process. The goal of this model is to guide surveillance imaging policies after definitive radiotherapy.

   The partially observed Markov decision process model was formulated to determine the optimal times to scan patients. Transition probabilities were computed using a data set of 1508 patients with HNC who received definitive radiotherapy between the years 2000 and 2010. Kernel density estimation was used to smooth the sample distributions. The reward function was derived using cost estimates from the literature. Additional model parameters were estimated using either data from the literature or clinical expertise.

   When considering all forms of relapse, the model showed that the optimal time between scans was longer than the time intervals used in the institutional guidelines. The optimal policy dictates that there should be less time between surveillance scans immediately after treatment compared with years after treatment. Comparable results also held when only locoregional relapses were considered as relapse events in the model. Simulation results for the inclusive relapse cases showed that <15% of patients experienced a relapse over a simulated 36‐month surveillance program.

   This model suggests that less frequent surveillance scan policies can maintain adequate information on relapse status for patients with HNC treated with radiotherapy. This model could potentially translate into a more cost‐effective surveillance program for this group of patients.

    

   more » « less
3. Magnetically-activated, nanostructured cellulose for efficient capture of circulating tumor cells from the blood sample of head and neck cancer patients

   Hazra, R.S. ; Kale, N. ; Boyle, C. ; Molina, K.B. ; D'Souza, A. ; Aland, G. ; Jiang, L. ; Chaturvedi, P. ; Ghosh, S. ; Mallik, S. ; et al ( January 2024 , Carbohydrate polymers)

   In this report, the relative efficiency of cellulose nanocrystals (CNCs) and nanofibers (CNFs) to capture circulating tumor cells (CTCs) from the blood sample of head and neck cancer (HNC) patients was evaluated. Detection and enumeration of CTCs are critical for monitoring cancer progression. Both types of nanostructured cellulose were chemically modified with Epithelial Cell Adhesion Molecule (EpCAM) antibody and iron oxide nanoparticles. The EpCAM antibody facilitated the engagement of CTCs, promoting entrapment within the cellulose cage structure. Iron oxide nanoparticles, on the other hand, rendered the cages activatable via the use of a magnet for the capture and separation of entrapped CTCs. The efficiency of the network structures is shown in head and neck cancer (HNC) patients' blood samples. It was observed that the degree of chemical functionalization of hydroxyl groups located within the CNCs or CNFs with anti-EpCAM determined the efficiency of the system's interaction with CTCs. Further, our result indicated that inflexible scaffolds of nanocrystals interacted more efficiently with CTCs than that of the fibrous CNF scaffolds. Network structures derived from CNCs demonstrated comparable CTC capturing efficiency to commercial standard, OncoDiscover®. The output of the work will provide the chemical design principles of cellulosic materials intended for constructing affordable platforms for monitoring cancer progression in 'real time'. 

   more » « less
4. Depth Videos for the Classification of Micro-Expressions

   https://doi.org/10.1109/ICPR48806.2021.9412976  

   Rakesh Kumar, Ankith Jain ; Bhanu, Bir ; Casey, Christopher ; Cheung, Sierra Grace ; Seitz, Aaron ( January 2021 , 2020 25th International Conference on Pattern Recognition (ICPR))

   null (Ed.)

   Facial micro-expressions are spontaneous, subtle, involuntary muscle movements occurring briefly on the face. The spotting and recognition of these expressions are difficult due to the subtle behavior, and the time duration of these expressions is about half a second, which makes it difficult for humans to identify them. These micro-expressions have many applications in our daily life, such as in the field of online learning, game playing, lie detection, and therapy sessions. Traditionally, researchers use RGB images/videos to spot and classify these micro-expressions, which pose challenging problems, such as illumination, privacy concerns and pose variation. The use of depth videos solves these issues to some extent, as the depth videos are not susceptible to the variation in illumination. This paper describes the collection of a first RGB-D dataset for the classification of facial micro-expressions into 6 universal expressions: Anger, Happy, Sad, Fear, Disgust, and Surprise. This paper shows the comparison between the RGB and Depth videos for the classification of facial micro-expressions. Further, a comparison of results shows that depth videos alone can be used to classify facial micro-expressions correctly in a decision tree structure by using the traditional and deep learning approaches with good classification accuracy. The dataset will be released to the public in the near future. 

   more » « less
5. Savings or Selection? Initial Spending Reductions in the Medicare Shared Savings Program and Considerations for Reform

   https://doi.org/10.1111/1468-0009.12468  

   McWILLIAMS, J. MICHAEL ; HATFIELD, LAURA A. ; LANDON, BRUCE E. ; CHERNEW, MICHAEL E. ( July 2020 , The Milbank Quarterly)

   Concerns have been raised about risk selection in the Medicare Shared Savings Program (MSSP). Specifically, turnover in accountable care organization (ACO) physicians and patient panels has led to concerns that ACOs may be earning shared‐savings bonuses by selecting lower‐risk patients or providers with lower‐risk panels.

   We find no evidence that changes in ACO patient populations explain savings estimates from previous evaluations through 2015. We also find no evidence that ACOs systematically manipulated provider composition or billing to earn bonuses.

   The modest savings and lack of risk selection in the original MSSP design suggest opportunities to build on early progress.

   Recent program changes provide ACOs with more opportunity to select providers with lower‐risk patients. Understanding the effect of these changes will be important for guiding future payment policy.

   The Medicare Shared Savings Program (MSSP) establishes incentives for participating accountable care organizations (ACOs) to lower spending for their attributed fee‐for‐service Medicare patients. Turnover in ACO physicians and patient panels has raised concerns that ACOs may be earning shared‐savings bonuses by selecting lower‐risk patients or providers with lower‐risk panels.

   We conducted three sets of analyses of Medicare claims data. First, we estimated overall MSSP savings through 2015 using a difference‐in‐differences approach and methods that eliminated selection bias from ACO program exit or changes in the practices or physicians included in ACO contracts. We then checked for residual risk selection at the patient level. Second, we reestimated savings with methods that address undetected risk selection but could introduce bias from other sources. These included patient fixed effects, baseline or prospective assignment, and area‐level MSSP exposure to hold patient populations constant. Third, we tested for changes in provider composition or provider billing that may have contributed to bonuses, even if they were eliminated as sources of bias in the evaluation analyses.

   MSSP participation was associated with modest and increasing annual gross savings in the 2012‐2013 entry cohorts of ACOs that reached $139 to $302 per patient by 2015. Savings in the 2014 entry cohort were small and not statistically significant. Robustness checks revealed no evidence of residual risk selection. Alternative methods to address risk selection produced results that were substantively consistent with our primary analysis but varied somewhat and were more sensitive to adjustment for patient characteristics, suggesting the introduction of bias from within‐patient changes in time‐varying characteristics. We found no evidence of ACO manipulation of provider composition or billing to inflate savings. Finally, larger savings for physician group ACOs were robust to consideration of differential changes in organizational structure among non‐ACO providers (eg, from consolidation).

   Participation in the original MSSP program was associated with modest savings and not with favorable risk selection. These findings suggest an opportunity to build on early progress. Understanding the effect of new opportunities and incentives for risk selection in the revamped MSSP will be important for guiding future program reforms.

    

   more » « less