More Like this

1. Personalized hypertension treatment recommendations by a data-driven model

   https://doi.org/10.1186/s12911-023-02137-z  

   Hu, Yang; Huerta, Jasmine; Cordella, Nicholas; Mishuris, Rebecca_G; Paschalidis, Ioannis_Ch (March 2023, BMC Medical Informatics and Decision Making)

   Abstract BackgroundHypertension is a prevalent cardiovascular disease with severe longer-term implications. Conventional management based on clinical guidelines does not facilitate personalized treatment that accounts for a richer set of patient characteristics. MethodsRecords from 1/1/2012 to 1/1/2020 at the Boston Medical Center were used, selecting patients with either a hypertension diagnosis or meeting diagnostic criteria (≥ 130 mmHg systolic or ≥ 90 mmHg diastolic, n = 42,752). Models were developed to recommend a class of antihypertensive medications for each patient based on their characteristics. Regression immunized against outliers was combined with a nearest neighbor approach to associate with each patient an affinity group of other patients. This group was then used to make predictions of future Systolic Blood Pressure (SBP) under each prescription type. For each patient, we leveraged these predictions to select the class of medication that minimized their future predicted SBP. ResultsThe proposed model, built with a distributionally robust learning procedure, leads to a reduction of 14.28 mmHg in SBP, on average. This reduction is 70.30% larger than the reduction achieved by the standard-of-care and 7.08% better than the corresponding reduction achieved by the 2nd best model which uses ordinary least squares regression. All derived models outperform following the previous prescription or the current ground truth prescription in the record. We randomly sampled and manually reviewed 350 patient records; 87.71% of these model-generated prescription recommendations passed a sanity check by clinicians. ConclusionOur data-driven approach for personalized hypertension treatment yielded significant improvement compared to the standard-of-care. The model implied potential benefits of computationally deprescribing and can support situations with clinical equipoise. 

   more » « less
2. DeepSOFA: A Continuous Acuity Score for Critically Ill Patients using Clinically Interpretable Deep Learning

   https://doi.org/10.1038/s41598-019-38491-0  

   Shickel, Benjamin; Loftus, Tyler J.; Adhikari, Lasith; Ozrazgat-Baslanti, Tezcan; Bihorac, Azra; Rashidi, Parisa (February 2019, Scientific Reports)

   Abstract Traditional methods for assessing illness severity and predicting in-hospital mortality among critically ill patients require time-consuming, error-prone calculations using static variable thresholds. These methods do not capitalize on the emerging availability of streaming electronic health record data or capture time-sensitive individual physiological patterns, a critical task in the intensive care unit. We propose a novel acuity score framework (DeepSOFA) that leverages temporal measurements and interpretable deep learning models to assess illness severity at any point during an ICU stay. We compare DeepSOFA with SOFA (Sequential Organ Failure Assessment) baseline models using the same model inputs and find that at any point during an ICU admission, DeepSOFA yields significantly more accurate predictions of in-hospital mortality. A DeepSOFA model developed in a public database and validated in a single institutional cohort had a mean AUC for the entire ICU stay of 0.90 (95% CI 0.90–0.91) compared with baseline SOFA models with mean AUC 0.79 (95% CI 0.79–0.80) and 0.85 (95% CI 0.85–0.86). Deep models are well-suited to identify ICU patients in need of life-saving interventions prior to the occurrence of an unexpected adverse event and inform shared decision-making processes among patients, providers, and families regarding goals of care and optimal resource utilization. 

   more » « less
3. eBP: FREQUENT AND COMFORTABLE BLOOD PRESSURE MONITORING FROM INSIDE HUMAN'S EARS

   https://doi.org/10.1145/3400713.3400721  

   Bui, Nam; Pham, Nhat; Truong, Hoang; Nguyen, Phuc; Xiao, Jianliang; Deterding, Robin; Dinh, Thang; Vu, Tam (May 2020, GetMobile: Mobile Computing and Communications)

   Diagnosing hypertension or hemodialysis requires patients to carry a blood pressure (BP) monitoring device for 24 hours. Th erefore, wearing the wrist/arm-based BP monitoring device, in this case, has a signifi cant impact on users' daily activities. To address the problem, we developed eBP, an ear-worn device that measures blood pressure from inside the ear. Th rough the evaluation of 35 subjects, eBP can achieve the average error of 1.8 mmHg for systolic BP and -3.1 mmHg for diastolic BP with the standard deviation error of 7.2 mmHg and 7.9 mmHg, respectively. 

   more » « less
4. Relationship of cardiovascular disease risk and hearing loss in a clinical population

   https://doi.org/10.1038/s41598-023-28599-9  

   Baiduc, Rachael R.; Sun, Joshua W.; Berry, Caitlin M.; Anderson, Melinda; Vance, Eric A. (December 2023, Scientific Reports)

   Abstract Hearing loss has been associated with individual cardiovascular disease (CVD) risk factors and, to a lesser extent, CVD risk metrics. However, these relationships are understudied in clinical populations. We conducted a retrospective study of electronic health records to evaluate the relationship between hearing loss and CVD risk burden. Hearing loss was defined as puretone average (PTA 0.5,1,2,4 ) > 20 dB hearing level (HL). Optimal CVD risk was defined as nondiabetic, nonsmoking, systolic blood pressure (SBP) < 120 and diastolic (D)BP < 80 mm Hg, and total cholesterol < 180 mg/dL. Major CVD risk factors were diabetes, smoking, hypertension, and total cholesterol ≥ 240 mg/dL or statin use. We identified 6332 patients (mean age = 62.96 years; 45.5% male); 64.0% had hearing loss. Sex-stratified logistic regression adjusted for age, noise exposure, hearing aid use, and body mass index examined associations between hearing loss and CVD risk. For males, diabetes, hypertension, smoking, and ≥ 2 major CVD risk factors were associated with hearing loss. For females, diabetes, smoking, and ≥ 2 major CVD risk factors were significant risk factors. Compared to those with no CVD risk factors, there is a higher likelihood of hearing loss in patients with ≥ 2 major CVD risk factors. Future research to better understand sex dependence in the hearing loss-hypertension relationship is indicated. 

   more » « less
5. Effect of Race and Ethnicity on In-Hospital Mortality in Patients with COVID-2019

   https://doi.org/10.18865/ed.31.3.389  

   Qureshi, Adnan I.; Baskett, William I.; Huang, Wei; Shyu, Daniel; Myers, Danny; Lobanova, Iryna; Naqvi, S. Hasan; Thompson, Vetta S.; Shyu, Chi-Ren (July 2021, Ethnicity & Disease)

   null (Ed.)

   Objective: To identify differences in short-term outcomes of patients with coronavirus disease 2019 (COVID-19) according to various racial/ethnic groups.Design: Analysis of Cerner de-identified COVID-19 dataset.Setting: A total of 62 health care facilities.Participants: The cohort included 49,277 adult COVID-19 patients who were hospitalized from December 1, 2019 to November 13, 2020.Methods: We compared patients’ age, gender, individual components of Charl­son and Elixhauser comorbidities, medical complications, use of do-not-resuscitate, use of palliative care, and socioeconomic status between various racial and/or ethnic groups. We further compared the rates of in-hos­pital mortality and non-routine discharges between various racial and/or ethnic groups.Main Outcome Measures: The primary outcome of interest was in-hospital mortali­ty. The secondary outcome was non-routine discharge (discharge to destinations other than home, such as short-term hospitals or other facilities including intermediate care and skilled nursing homes).Results: Compared with White patients, in-hospital mortality was significantly higher among African American (OR 1.5; 95%CI:1.3-1.6, P<.001), Hispanic (OR1.4; 95%CI:1.3-1.6, P<.001), and Asian or Pacific Islander (OR 1.5; 95%CI: 1.1-1.9, P=.002) patients after adjustment for age and gender, Elixhauser comorbidities, do-not-resuscitate status, palliative care use, and socioeconomic status.Conclusions: Our study found that, among hospitalized patients with COVID-2019, African American, Hispanic, and Asian or Pacific Islander patients had increased mortality compared with White patients after adjusting for sociodemographic factors, comorbidities, and do-not-resuscitate/pallia­tive care status. Our findings add additional perspective to other recent studies. Ethn Dis. 2021;31(3):389-398; doi:10.18865/ed.31.3.389 

   more » « less