1
|
Feld SI, Hippe DS, Miljacic L, Polissar NL, Newman SF, Nair BG, Vavilala MS. A Machine Learning Approach for Predicting Real-time Risk of Intraoperative Hypotension in Traumatic Brain Injury. J Neurosurg Anesthesiol 2023; 35:215-223. [PMID: 34759236 PMCID: PMC9091057 DOI: 10.1097/ana.0000000000000819] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/12/2021] [Accepted: 10/08/2021] [Indexed: 11/25/2022]
Abstract
BACKGROUND Traumatic brain injury (TBI) is a major cause of death and disability. Episodes of hypotension are associated with worse TBI outcomes. Our aim was to model the real-time risk of intraoperative hypotension in TBI patients, compare machine learning and traditional modeling techniques, and identify key contributory features from the patient monitor and medical record for the prediction of intraoperative hypotension. METHODS The data included neurosurgical procedures in 1005 TBI patients at an academic level 1 trauma center. The clinical event was intraoperative hypotension, defined as mean arterial pressure <65 mm Hg for 5 or more consecutive minutes. Two types of models were developed: one based on preoperative patient-level predictors and one based on intraoperative predictors measured per minute. For each of these models, we took 2 approaches to predict the occurrence of a hypotensive event: a logistic regression model and a gradient boosting tree model. RESULTS The area under the receiver operating characteristic curve for the intraoperative logistic regression model was 0.80 (95% confidence interval [CI]: 0.78-0.83), and for the gradient boosting model was 0.83 (95% CI: 0.81-0.85). The area under the precision-recall curve for the intraoperative logistic regression model was 0.16 (95% CI: 0.12-0.20), and for the gradient boosting model was 0.19 (95% CI: 0.14-0.24). Model performance based on preoperative predictors was poor. Features derived from the recent trend of mean arterial pressure emerged as dominantly predictive in both intraoperative models. CONCLUSIONS This study developed a model for real-time prediction of intraoperative hypotension in TBI patients, which can use computationally efficient machine learning techniques and a streamlined feature-set derived from patient monitor data.
Collapse
Affiliation(s)
- Shara I Feld
- Anesthesiology and Pain Medicine, University of Washington
| | - Daniel S Hippe
- The Mountain-Whisper-Light: Statistics & Data Science, Seattle, WA
| | | | - Nayak L Polissar
- The Mountain-Whisper-Light: Statistics & Data Science, Seattle, WA
| | | | - Bala G Nair
- Anesthesiology and Pain Medicine, University of Washington
| | | |
Collapse
|
2
|
Feld SI, Woo KM, Alexandridis R, Wu Y, Liu J, Peissig P, Onitilo AA, Cox J, Page CD, Burnside ES. Improving breast cancer risk prediction by using demographic risk factors, abnormality features on mammograms and genetic variants. AMIA Annu Symp Proc 2018; 2018:1253-1262. [PMID: 30815167 PMCID: PMC6371301] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/09/2023]
Abstract
The predictive capability of combining demographic risk factors, germline genetic variants, and mammogram abnormality features for breast cancer risk prediction is poorly understood. We evaluated the predictive performance of combinations of demographic risk factors, high risk single nucleotide polymorphisms (SNPs), and mammography features for women recommended for breast biopsy in a retrospective case-control study (n = 768) with four logistic regression models. The AUC of the baseline demographic features model was 0.580. Both genetic variants and mammography abnormality features augmented the performance of the baseline model: demographics + SNP (AUC =0.668), demographics + mammography (AUC =0.702). Finally, we found that the demographics + SNP + mammography model (AUC = 0.753) had the greatest predictive power, with a significant performance improvement over the other models. The combination of demographic risk factors, genetic variants and imaging features improves breast cancer risk prediction over prior methods utilizing only a subset of these features.
Collapse
Affiliation(s)
- Shara I Feld
- University of Wisconsin Department of Radiology, Madison, WI
| | - Kaitlin M Woo
- University of Wisconsin Department of Biostatistics and Medical Informatics, Madison, WI
| | - Roxana Alexandridis
- University of Wisconsin Department of Biostatistics and Medical Informatics, Madison, WI
| | - Yirong Wu
- University of Wisconsin Department of Radiology, Madison, WI
| | - Jie Liu
- University of Washington Department of Genome Sciences, Seattle, WA
| | - Peggy Peissig
- Marshfield Clinic Research Institute, Marshfield, WI
| | - Adedayo A Onitilo
- Marshfield Clinic Research Institute, Marshfield, WI
- Marshfield Clinic Weston Center Department of Hematology/Oncology, Weston, WI
| | - Jennifer Cox
- University of Wisconsin Department of Radiology, Madison, WI
- University of Wisconsin Department of Biostatistics and Medical Informatics, Madison, WI
- University of Washington Department of Genome Sciences, Seattle, WA
- Marshfield Clinic Research Institute, Marshfield, WI
- Marshfield Clinic Weston Center Department of Hematology/Oncology, Weston, WI
| | - C David Page
- University of Wisconsin Department of Biostatistics and Medical Informatics, Madison, WI
| | | |
Collapse
|
3
|
Feld SI, Fan J, Yuan M, Wu Y, Woo KM, Alexandridis R, Burnside ES. Utility of Genetic Testing in Addition to Mammography for Determining Risk of Breast Cancer Depends on Patient Age. AMIA Jt Summits Transl Sci Proc 2018; 2017:81-90. [PMID: 29888046 PMCID: PMC5961791] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Figures] [Subscribe] [Scholar Register] [Indexed: 06/08/2023]
Abstract
While screening and treatment have sharply reduced breast cancer mortality in the past 50 years, more targeted diagnostic testing may improve the accuracy and efficiency of care. Our retrospective, age-matched, case-control study evaluated the differential value of mammography and genetic variants to predict breast cancer depending on patient age. We developed predictive models using logistic regression with group lasso comparing (1) diagnostic mammography findings, (2) selected genetic variants, and (3) a combination of both. For women older than 60, mammography features were most predictive of breast cancer risk (imaging AUC = 0.74, genetic variants AUC = 0.54, combined AUC = 0.71). For women younger than 60 there is additional benefit to obtaining genetic testing (imaging AUC = 0.69, genetic variants AUC = 0.70, combined AUC = 0.72). In summary, genetic testing supplements mammography in younger women while mammography appears sufficient in older women for breast cancer risk prediction.
Collapse
Affiliation(s)
- Shara I Feld
- University of Wisconsin Department of Radiology, Madison, WI
| | - Jun Fan
- Hong Kong Baptist University Department of Mathematics, Hong Kong, China
| | - Ming Yuan
- Columbia University Department of Statistics, New York, NY
| | - Yirong Wu
- University of Wisconsin Department of Radiology, Madison, WI
| | - Kaitlin M Woo
- University of Wisconsin Department of Biostatistics and Medical Informatics, Madison, WI
| | - Roxana Alexandridis
- University of Wisconsin Department of Biostatistics and Medical Informatics, Madison, WI
| | | |
Collapse
|
4
|
Feld SI, Cobian AG, Tevis SE, Kennedy GD, Craven MW. Modeling the Temporal Evolution of Postoperative Complications. AMIA Annu Symp Proc 2017; 2016:551-559. [PMID: 28269851 PMCID: PMC5333217] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [MESH Headings] [Grants] [Subscribe] [Scholar Register] [Indexed: 06/06/2023]
Abstract
Post-operative complications have a significant impact on patient morbidity and mortality; these impacts are exacerbated when patients experience multiple complications. However, the task of modeling the temporal sequencing of complications has not been previously addressed. We present an approach based on Markov chain models for characterizing the temporal evolution of post-operative complications represented in the American College of Surgeons National Surgery Quality Improvement Program database. Our work demonstrates that the models have significant predictive value. In particular, an inhomogenous Markov chain model effectively predicts the development of serious complications (coma longer than a day, cardiac arrest, myocardial infarction, septic shock, renal failure, pneumonia) and interventional complications (unplanned re-intubation, longer than 2 days on a ventilator and bleeding transfusion).
Collapse
Affiliation(s)
| | - Alexander G Cobian
- Department of Computer Sciences,; Department of Biostatistics and Medical Informatics University of Wisconsin-Madison
| | | | | | - Mark W Craven
- Department of Biostatistics and Medical Informatics University of Wisconsin-Madison; Department of Computer Sciences
| |
Collapse
|
5
|
Feld SI, Tevis SE, Cobian AG, Craven MW, Kennedy GD. Multiple postoperative complications: Making sense of the trajectories. Surgery 2016; 160:1666-1674. [PMID: 27769659 DOI: 10.1016/j.surg.2016.08.047] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.4] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/01/2016] [Revised: 07/05/2016] [Accepted: 08/16/2016] [Indexed: 12/25/2022]
Abstract
BACKGROUND Many studies have evaluated predictors of postoperative complications, yet little is known about the development of multiple complications. The goal of this study was to assess complication timing in cascades of multiple complications and the risk of future complications given a patient's first complication. METHODS This study includes 30-day, postoperative complications from the American College of Surgeons National Surgical Quality Improvement Program for all patients who underwent major inpatient and outpatient operative procedures from 2005-2013. The timing and sequencing of complications were evaluated using χ2 analysis and pairwise comparisons. RESULTS More severe postoperative complications (cardiac arrest or myocardial infarction, renal insufficiency or failure, stroke, intubation, septic shock, coma) had the greatest impact on the risk for developing further complications, increasing the relative risk of developing future, specific, severe complications by more than 40-fold. These more severe complications occur within a few days of other complications (whether as a preceding factor or an outcome), while less severe complications, such as surgical site infection and urinary tract infection, are linked less tightly to complication cascades. CONCLUSION This analysis highlights both the risk for secondary complications after an initial complication and when those future complications are likely to occur. Physicians can use this information to target interventions to prevent high-risk complications.
Collapse
Affiliation(s)
- Shara I Feld
- Department of Surgery, University of Wisconsin-Madison, Madison, WI
| | - Sarah E Tevis
- Department of Surgery, University of Wisconsin-Madison, Madison, WI
| | - Alexander G Cobian
- Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI; Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI
| | - Mark W Craven
- Department of Computer Sciences, University of Wisconsin-Madison, Madison, WI; Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, Madison, WI
| | - Gregory D Kennedy
- Department of Surgery, University of Alabama at Birmingham, Birmingham, AL.
| |
Collapse
|
6
|
Levy RL, van Tilburg MA, Langer SL, Romano JM, Walker LS, Mancl LA, Murphy TB, Claar RL, Feld SI, Christie DL, Abdullah B, DuPen MM, Swanson KS, Baker MD, Stoner SA, Whitehead WE. Effects of a Cognitive Behavioral Therapy Intervention Trial to Improve Disease Outcomes in Children with Inflammatory Bowel Disease. Inflamm Bowel Dis 2016; 22:2134-48. [PMID: 27542131 PMCID: PMC4995069 DOI: 10.1097/mib.0000000000000881] [Citation(s) in RCA: 33] [Impact Index Per Article: 4.1] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/27/2022]
Abstract
BACKGROUND Studies testing the efficacy of behavioral interventions to modify psychosocial sequelae of inflammatory bowel disease in children are limited. This report presents outcomes through a 6-month follow-up from a large randomized controlled trial testing the efficacy of a cognitive behavioral intervention for children with inflammatory bowel disease and their parents. METHODS One hundred eighty-five children aged 8 to 17 years with a diagnosis of Crohn's disease or ulcerative colitis and their parents were randomized to one of two 3-session conditions: (1) a social learning and cognitive behavioral therapy condition or (2) an education support condition designed to control for time and attention. RESULTS There was a significant overall treatment effect for school absences due to Crohn's disease or ulcerative colitis (P < 0.05) at 6 months after treatment. There was also a significant overall effect after treatment for child-reported quality of life (P < 0.05), parent-reported increases in adaptive child coping (P < 0.001), and reductions in parents' maladaptive responses to children's symptoms (P < 0.05). Finally, exploratory analyses indicated that for children with a higher level of flares (2 or more) prebaseline, those in social learning and cognitive behavioral therapy condition experienced a greater reduction in flares after treatment. CONCLUSIONS This trial suggests that a brief cognitive behavioral intervention for children with inflammatory bowel disease and their parents can result in improved child functioning and quality of life, and for some children may decrease disease activity.
Collapse
Affiliation(s)
| | | | | | - Joan M. Romano
- University of Washington, Psychiatry & Behavioral Sciences
| | | | | | | | - Robyn L. Claar
- University of North Carolina, Division of Gastroenterology and Hepatology
| | - Shara I. Feld
- University of Wisconsin, School of Medicine and Public Health
| | | | | | | | | | | | | | | |
Collapse
|
7
|
Abstract
BACKGROUND & AIMS Heredity has been suggested to explain the finding that irritable bowel syndrome (IBS) tends to run in families. Research in this area has been limited. The aim of the present study was to assess the relative contribution of genetic and environmental (social learning) influences on the development of IBS by comparing concordance rates in monozygotic and dizygotic twins to concordance between mothers and their children. METHODS Questionnaires soliciting information on the occurrence of more than 80 health problems, including IBS, in self and other family members were sent to both members of 11,986 twin pairs. RESULTS Analysis is based on 10,699 respondents representing 6060 twin pairs. Concordance for IBS was significantly greater (P = 0.030) in monozygotic (17.2%) than in dizygotic (8.4%) twins, supporting a genetic contribution to IBS. However, the proportion of dizygotic twins with IBS who have mothers with IBS (15.2%) was greater than the proportion of dizygotic twins with IBS who have co-twins with IBS (6.7%, P < 0.001), and logistic regression analysis showed that having a mother with IBS and having a father with IBS are independent predictors of irritable bowel status (P < 0.001); both are stronger predictors than having a twin with IBS. Addition of information about the other twin accounted for little additional predictive power. CONCLUSIONS Heredity contributes to development of IBS, but social learning (what an individual learns from those in his or her environment) has an equal or greater influence.
Collapse
Affiliation(s)
- R L Levy
- University of Washington, Seattle, Washington 98195, USA.
| | | | | | | | | | | |
Collapse
|