Dataset Information

A Clinical Prediction Model to Predict Heparin Treatment Outcomes and Provide Dosage Recommendations: Development and Validation Study.

ABSTRACT:

Background

Unfractionated heparin is widely used in the intensive care unit as an anticoagulant. However, weight-based heparin dosing has been shown to be suboptimal and may place patients at unnecessary risk during their intensive care unit stay.

Objective

In this study, we intended to develop and validate a machine learning-based model to predict heparin treatment outcomes and to provide dosage recommendations to clinicians.

Methods

A shallow neural network model was adopted in a retrospective cohort of patients from the Multiparameter Intelligent Monitoring in Intensive Care III (MIMIC III) database and patients admitted to the Peking Union Medical College Hospital (PUMCH). We modeled the subtherapeutic, normal, and supratherapeutic activated partial thromboplastin time (aPTT) as the outcomes of heparin treatment and used a group of clinical features for modeling. Our model classifies patients into 3 different therapeutic states. We tested the prediction ability of our model and evaluated its performance by using accuracy, the kappa coefficient, precision, recall, and the F1 score. Furthermore, a dosage recommendation module was designed and evaluated for clinical decision support.

Results

A total of 3607 patients selected from MIMIC III and 1549 patients admitted to the PUMCH who met our criteria were included in this study. The shallow neural network model showed results of F1 scores 0.887 (MIMIC III) and 0.925 (PUMCH). When compared with the actual dosage prescribed, our model recommended increasing the dosage for 72.2% (MIMIC III, 1240/1718) and 64.7% (PUMCH, 281/434) of the subtherapeutic patients and decreasing the dosage for 80.9% (MIMIC III, 504/623) and 76.7% (PUMCH, 277/361) of the supratherapeutic patients, suggesting that the recommendations can contribute to clinical improvements and that they may effectively reduce the time to optimal dosage in the clinical setting.

Conclusions

The evaluation of our model for predicting heparin treatment outcomes demonstrated that the developed model is potentially applicable for reducing the misdosage of heparin and for providing appropriate decision recommendations to clinicians.

SUBMITTER: Li D

PROVIDER: S-EPMC8176336 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:ImportanceFunctional impairment and pain are common indications for the initiation of lumbar spine surgery, but information about expected improvement in these patient-reported outcome (PRO) domains is not readily available to most patients and clinicians considering this type of surgery.ObjectiveTo assess population-level PRO response after lumbar spine surgery, and develop/validate a prediction tool for PRO improvement.Design, setting, and participantsThis statewide multicenter cohort was based at 15 Washington state hospitals representing approximately 75% of the state's spine fusion procedures. The Spine Surgical Care and Outcomes Assessment Program and the survey center at the Comparative Effectiveness Translational Network prospectively collected clinical and PRO data from adult candidates for lumbar surgery, preoperatively and postoperatively, between 2012 and 2016. Prediction models were derived for PRO improvement 1 year after lumbar fusion surgeries on a random sample of 85% of the data and were validated in the remaining 15%. Surgical candidates from 2012 through 2015 were included; follow-up surveying continued until December 31, 2016, and data analysis was completed from July 2016 to April 2017.Main outcomes and measuresFunctional improvement, defined as a reduction in Oswestry Disability Index score of 15 points or more; and back pain and leg pain improvement, defined a reduction in Numeric Rating Scale score of 2 points or more.ResultsA total of 1965 adult lumbar surgical candidates (mean [SD] age, 61.3 [12.5] years; 944 [59.6%] female) completed baseline surveys before surgery and at least 1 postoperative follow-up survey within 3 years. Of these, 1583 (80.6%) underwent elective lumbar fusion procedures; 1223 (77.3%) had stenosis, and 1033 (65.3%) had spondylolisthesis. Twelve-month follow-up participation rates for each outcome were between 66% and 70%. Improvements were reported in function, back pain, and leg pain at 12 months by 306 of 528 surgical patients (58.0%), 616 of 899 patients (68.5%), and 355 of 464 patients (76.5%), respectively, whose baseline scores indicated moderate to severe symptoms. Among nonoperative patients, 35 (43.8%), 47 (53.4%), and 53 (63.9%) reported improvements in function, back pain, and leg pain, respectively. Demographic and clinical characteristics included in the final prediction models were age, sex, race, insurance status, American Society of Anesthesiologists score, smoking status, diagnoses, prior surgery, prescription opioid use, asthma, and baseline PRO scores. The models had good predictive performance in the validation cohort (concordance statistic, 0.66-0.79) and were incorporated into a patient-facing, web-based interactive tool (https://becertain.shinyapps.io/lumbar_fusion_calculator).Conclusions and relevanceThe PRO response prediction tool, informed by population-level data, explained most of the variability in pain reduction and functional improvement after surgery. Giving patients accurate information about their likelihood of outcomes may be a helpful component in surgery decision making.

Project description:Because existing risk prediction models for lung cancer were developed in white populations, they may not be appropriate for predicting risk among African-Americans. Therefore, a need exists to construct and validate a risk prediction model for lung cancer that is specific to African-Americans. We analyzed data from 491 African-Americans with lung cancer and 497 matched African-American controls to identify specific risks and incorporate them into a multivariable risk model for lung cancer and estimate the 5-year absolute risk of lung cancer. We performed internal and external validations of the risk model using data on additional cases and controls from the same ongoing multiracial/ethnic lung cancer case-control study from which the model-building data were obtained as well as data from two different lung cancer studies in metropolitan Detroit, respectively. We also compared our African-American model with our previously developed risk prediction model for whites. The final risk model included smoking-related variables [smoking status, pack-years smoked, age at smoking cessation (former smokers), and number of years since smoking cessation (former smokers)], self-reported physician diagnoses of chronic obstructive pulmonary disease or hay fever, and exposures to asbestos or wood dusts. Our risk prediction model for African-Americans exhibited good discrimination [75% (95% confidence interval, 0.67-0.82)] for our internal data and moderate discrimination [63% (95% confidence interval, 0.57-0.69)] for the external data group, which is an improvement over the Spitz model for white subjects. Existing lung cancer prediction models may not be appropriate for predicting risk for African-Americans because (a) they were developed using white populations, (b) level of risk is different for risk factors that African-American share with whites, and (c) unique group-specific risk factors exist for African-Americans. This study developed and validated a risk prediction model for lung cancer that is specific to African-Americans and thus more precise in predicting their risks. These findings highlight the importance of conducting further ethnic-specific analyses of disease risk.