A computer model for the study of breast cancer.
*Computer Simulation; Breast Neoplasms/epidemiology/mortality/*pathology; Female; Humans; Incidence; Life Expectancy; Lymphatic Metastasis; Neoplasm Metastasis; SEER Program; Software; United States/epidemiology
A computer model was designed as a relational database to assess breast cancer screening in a cohort of women where the growth and development of breast cancer originates with the first malignant cell. The concepts of thresholds for growth, axillary spread, and distant sites are integrated. With tumor diagnosis, staging was performed that includes clinical and sub-clinical states. The model was parameterized to have staging characteristics similar to data published by the Surveillance, Epidemiology, and End-Results (SEER) Program. Validation was accomplished by comparing simulated staging results with non-SEER sources, and simulated survival with independent clinical survival data.
Carter Kimbroe J; Castro Frank; Kessler Edward; Erickson Barbara
Computers in biology and medicine
2003
2003-07
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
<a href="http://doi.org/10.1016/s0010-4825(03)00003-9" target="_blank" rel="noreferrer noopener">10.1016/s0010-4825(03)00003-9</a>
A gradient boosting algorithm for survival analysis via direct optimization of concordance index.
*Survival Analysis; Algorithms; Artificial Intelligence; Breast Neoplasms/*epidemiology/*mortality; Clinical; Databases; Decision Support Systems; Factual; Female; Humans; Internet; Models; Prognosis; Proportional Hazards Models; Software; Theoretical
Survival analysis focuses on modeling and predicting the time to an event of interest. Many statistical models have been proposed for survival analysis. They often impose strong assumptions on hazard functions, which describe how the risk of an event changes over time depending on covariates associated with each individual. In particular, the prevalent proportional hazards model assumes that covariates are multiplicatively related to the hazard. Here we propose a nonparametric model for survival analysis that does not explicitly assume particular forms of hazard functions. Our nonparametric model utilizes an ensemble of regression trees to determine how the hazard function varies according to the associated covariates. The ensemble model is trained using a gradient boosting method to optimize a smoothed approximation of the concordance index, which is one of the most widely used metrics in survival model performance evaluation. We implemented our model in a software package called GBMCI (gradient boosting machine for concordance index) and benchmarked the performance of our model against other popular survival models with a large-scale breast cancer prognosis dataset. Our experiment shows that GBMCI consistently outperforms other methods based on a number of covariate settings. GBMCI is implemented in R and is freely available online.
Chen Yifei; Jia Zhenyu; Mercola Dan; Xie Xiaohui
Computational and mathematical methods in medicine
2013
1905-07
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
<a href="http://doi.org/10.1155/2013/873595" target="_blank" rel="noreferrer noopener">10.1155/2013/873595</a>
An integrated multielectrode electrophysiology system.
Animals; Rats; Software; Data Display; Computer Graphics; *Electrodes; Electrophysiology/*instrumentation; Microcomputers; Visual Cortex/physiology; Amplifiers; Electronic
An integrated system for recording and analyzing electrophysiological data from multiple channels is described. The system uses an MS-DOS microcomputer, a
Borroni A; Chen F M; LeCursi N; Grover L M; Teyler T J
Journal of neuroscience methods
1991
1991-02
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
<a href="http://doi.org/10.1016/0165-0270(91)90043-y" target="_blank" rel="noreferrer noopener">10.1016/0165-0270(91)90043-y</a>
Handheld computer use in a family medicine clerkship.
*Clinical Clerkship; Adult; Computers; Family Practice/*education; Female; Handheld/*statistics & numerical data; Humans; Male; Medical; Ohio; Schools; Software
PURPOSE: The objectives of this study were to track students' use of medical and nonmedical personal digital assistant (PDA) software and to obtain students' ratings of the usefulness of PDAs in a family medicine clerkship. METHOD: During the academic year 2001-02, third-year clerkship students at the Northeastern Ohio Universities College of Medicine were loaned PDAs equipped with company-installed software, such as a date book and address book. Additional software was installed (Griffith's 5 Minute Clinical Consult, ePocrates qRx, ePocrates qID, iSilo, HanDBase, MedCalc, and Application Usage). Pre- and post-orientation questionnaires and a post-rotation evaluation measured students' comfort level, the perceived usefulness, and ratings of programs on their PDA. Application Usage tracked the number of minutes and times students used each software program. RESULTS: Eighty-five students completed the study. They rated ePocrates qRx and Griffith's 5 Minute Clinical Consult the most useful medical software programs. PDAs were rated as "almost always" enhancing the clerkship experience. Students reported the PDA altered the way they accessed clinical information and that every few days it helped them understand a clinical discussion. Experience with computer technology was correlated with PDA use. CONCLUSIONS: This study objectively demonstrates clerkship students' use of PDA resources. Students' use mirrors their assessment of the value of the software. Although PDAs and software programs can be an expense, it is a worthwhile educational resource as evaluated by the medical student.
Sutton John; Stockton LuAnne; McCord Gary; Gilchrist Valerie J; Fedyna Dinah
Academic medicine : journal of the Association of American Medical Colleges
2004
2004-11
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
<a href="http://doi.org/10.1097/00001888-200411000-00024" target="_blank" rel="noreferrer noopener">10.1097/00001888-200411000-00024</a>
Hyperacute T-wave criteria using computer ECG analysis.
Female; Humans; Male; Middle Aged; Predictive Value of Tests; *Electrocardiography; Software; Myocardial Infarction/*diagnosis; Computer-Assisted; *Signal Processing
Hyperacute T waves (HATWs) have been described as tall-amplitude, primary T-wave abnormalities sometimes seen in the early phases of transmural myocardial infarction. Despite numerous human and animal studies addressing the presence and significance of HATWs, there are no widely held, reliable ECG criteria for their accurate identification. Using a specially designed computer program on a Hewlett-Packard Realm ECG analysis system, we screened 13,393 adult ECGs to identify those having T-wave amplitudes greater than accepted standards (limb leads, greater than 0.5 mV; precordial leads, greater than 1.0 mV). Patients with other known causes of primary and secondary tall T waves were excluded from the study sample. Patients with tall-amplitude T-waves who then developed clinically verifiable myocardial infarction were labeled the HATW group. The HATW group (21) represented 4.1% of the tall T wave group (513) and 0.16% of the entire sample. The remaining patients, who did not meet HATW criteria, were called the early repolarization variant (ERV) group (51). Both groups underwent comparative computer morphology analysis. Nine parameters were statistically significant in discriminating HATWs from early repolarization variants. A combination of J-point position/T-wave amplitude of more than 25%, T-wave amplitude/QRS amplitude of more than 75%, J-point position of more than 0.30 mV, and age of more than 45 years predicted HATWs from a control group with a specificity of 98.0% and a sensitivity of 61.9% and with positive and negative predictive values of 92.9% and 86.2%, respectively. We conclude that HATWs have characterizable discriminating ECG morphology as determined by computer ECG analysis compared with a control group.
Collins M S; Carter J E; Dougherty J M; Majercik S M; Hodsden J E; Logue EE
Annals of emergency medicine
1990
1990-02
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
<a href="http://doi.org/10.1016/s0196-0644(05)81792-5" target="_blank" rel="noreferrer noopener">10.1016/s0196-0644(05)81792-5</a>
Is middleware the right medicine?
Access to Information; Software; Equipment and Supplies; Electronic Data Interchange; Clinical Information Systems; Health Level 7; Hospital Information Systems; Organizational Structure; Systems Integration
Voltz Donald; Thanh Tran
Health Management Technology
2015
2015-05
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).
The cost of interoperability.
Software; International Classification of Diseases; Death Certificates; Cause of Death; Electronic Data Interchange; Health Care Errors; Health Facility Administration; Patient Record Systems
The article looks at an interoperability report by the U.S. Government Accountability Office (GAO) on the status of efforts to develop infrastructure that could lead to nationwide interoperability of health information. Topics covered include five barriers to interoperability according to the GAO, plug-and-play interoperability tools being pushed by the U.S. Centers for Medicare & Medicaid Services that already exist, and medical error as the third leading cause of death in the U.S.
Voltz Donald
Health Management Technology
2017
2017-01
Article information provided for research and reference use only. All rights are retained by the journal listed under publisher and/or the creator(s).