- Browse by Subject
Browsing by Subject "Predictions"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item A note on the multiplicative fairness score in the NIJ recidivism forecasting challenge(Springer Nature, 2021) Mohler, George; Porter, Michael D.; Computer Science, Luddy School of Informatics, Computing, and EngineeringBackground: The 2021 NIJ recidivism forecasting challenge asks participants to construct predictive models of recidivism while balancing false positive rates across groups of Black and white individuals through a multiplicative fairness score. We investigate the performance of several models for forecasting 1-year recidivism and optimizing the NIJ multiplicative fairness metric. Methods: We consider standard linear and logistic regression, a penalized regression that optimizes a convex surrogate loss (that we show has an analytical solution), two post-processing techniques, linear regression with re-balanced data, a black-box general purpose optimizer applied directly to the NIJ metric and a gradient boosting machine learning approach. Results: For the set of models investigated, we find that a simple heuristic of truncating scores at the decision threshold (thus predicting no recidivism across the data) yields as good or better NIJ fairness scores on held out data compared to other, more sophisticated approaches. We also find that when the cutoff is further away from the base rate of recidivism, as is the case in the competition where the base rate is 0.29 and the cutoff is 0.5, then simply optimizing the mean square error gives nearly optimal NIJ fairness metric solutions. Conclusions: The multiplicative metric in the 2021 NIJ recidivism forecasting competition encourages solutions that simply optimize MSE and/or use truncation, therefore yielding trivial solutions that forecast no one will recidivate.Item Accuracy of Orthodontic Soft Tissue Prediction Software between Different Ethnicities(2019) Stewart, Kelton; Patel, Pranali; Eckert, George; Rigsbee III, OH; Hughes, Jay; Utreja, AchintObjective: The objective of this study was to assess the accuracy of the soft tissue prediction module of Dolphin Imaging Software (DIS) in patients requiring extractions as part of the orthodontic treatment plan and compare its accuracy between different ethnicities. Materials and Methods: Initial and final records of 57 patients from three ethnic groups (African Americans, Caucasians, and Hispanics) who completed orthodontic treatment were included for assessment. The identified cases were managed non-surgically with dental extractions. A predictive profile was generated using DIS and compared to post-treatment lateral photographs. Actual and predictive profile photographs were compared using five designated parameters. The assessment parameters were evaluated using a manual protractor. ANOVA was used to compare differences between actual and predicted parameters between the specified groups and ICC was used to assess correlations between the data. Results: Neither ethnicity nor gender had a significant effect on the difference between predicted and final values. No significant difference was noted between the predicted and final images for the nasolabial angle. Significant differences were observed for the mentolabial fold, upper lip to E-line, and lower lip to E-line between predicted and actual images. Additionally, soft tissue convexity was significantly different (p=0.019). Additionally, a clinically significant difference was found for the mentolabial fold. Conclusion: Ethnicity and gender had no impact on the accuracy of predicted and actual image parameters. Overall, DIS demonstrated acceptable accuracy when simulating soft tissue changes after extraction therapy. Additional research on the accuracy of the software is warranted.Item A Comprehensive Survey and Deep Learning-Based Prediction on G-quadruplex Formation and Biological Functions(2022-09) Fang, Shuyi; Wan, Jun; Liu, Yunlong; Yan, Jingwen; Zhang, JieThe G-quadruplexes (G4s) are guanine-rich four-stranded DNA/RNA structures, which have been found throughout the human genome. G4s have been reported to affect chromatin structure and are involved in important biological processes at transcriptional and epigenetic levels. However, the underlying molecular mechanisms and locating of G4 still remain elusive due to the complexity of G4s. Taking advantage of the development of high-throughput sequencing technologies and machine learning approaches, we constructed this comprehensive investigation on G4 structures, including discovery of a novel marker for functional human hematopoietic stem cells and gained interest in G4 structure, exploring association between G4 and genomic factors by incorporating multi-omics data, and development of a deep-learningbased G4 prediction tool with G4 motif. First, we discovered ADGRG1 as a novel marker for functional human hematopoietic stem cells and its regulation through transcription activities. Our interest in G4s was stimulated while the transcription-related investigations. Next, we analyzed the genome-wide distribution properties of G4s and uncovered the associations of G4 with other epigenetic and transcriptional mechanisms to coordinate gene transcription. We explored that different-confidence G4 groups correlated differently with epigenetic regulatory elements and revealed that G4 structures could correlate with gene expression in two opposite ways depending on their locations and forming strands. Some transcription factors were identified to be over-represented with G4 emergence. We found distinct consensus sequences enriched in the G4 feet, with a high GC content in the feet of high-confidence G4s and a high TA content in solely predicted G4 feet. As for the last part, we developed a novel deep-learning-based prediction tool for DNA G4s with G4 motifs. Considering the classical G4 motif, we applied bi-directional LSTM model with attention method, which captures sequential information, and showed good performance in whole-genome level prediction of DNA G4s with the certified G4 pattern. Our comprehensive work investigated G4 with its functions and predictions and provided a better understanding of G4s on multi-omics level and computational information capture riding the wave of deep learning.Item Middle East respiratory syndrome coronavirus – The need for global proactive surveillance, sequencing and modeling(Elsevier, 2021) Al-Tawfiq, Jaffar A.; Petersen, Eskild; Memish, Ziad A.; Perlman, Stanley; Zumla, Alimuddin; Medicine, School of Medicine