Integrating Predictive Analytics Into High-Value Care

Parikh, Ravi B.; Kakad, Meetali; Bates, David W.

doi:10.1001/jama.2015.19417

Cited by 155 publications

(95 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results may not be fully generalisable to health systems not currently utilising such platforms. Although we are utilising a proprietary algorithm for risk prediction in this study, given the increasing trends towards risk prediction in population health management programmes, 36 we anticipate that many health systems will be developing internal capacity or external vendor relationships in the future.…”

Section: Sample Size Considerationsmentioning

confidence: 99%

Targeted Adherence Intervention to Reach Glycemic Control with Insulin Therapy for patients with Diabetes (TARGIT-Diabetes): rationale and design of a pragmatic randomised clinical trial

et al. 2017

View full text Add to dashboard Cite

IntroductionAdherence to and persistence of medications for chronic diseases remains poor and many interventions to improve medication use have only been modestly effective. Targeting interventions to patients who are most likely to benefit should improve their efficiency and clinical impact. This study aims to test the impact of three cost-equivalent pharmacist-led interventions on insulin persistence and glycaemic control among patients with diabetes.Methods and analysisTARGIT-Diabetes (Targeted Adherence Intervention to Reach Glycemic Control with Insulin Therapy for patients with Diabetes) is a randomised controlled trial that will evaluate three different multifaceted pharmacist-outreach strategies for improving long-term insulin use among individuals with diabetes. We will randomise 6000 patients in a large insurer to one of three arms. The arms are designed to deliver an increasingly intensive intervention to a progressively targeted population, identified using predictive analytics. The central component of the intervention in all arms is a tailored telephone consultation with a pharmacist which varies across arms based on the: (A) proportion of patients offered the intervention and (B) intervention intensity, including follow-up frequency and cointerventions such as text reminders and interactions with patients’ providers. The primary outcome is insulin persistence, assessed using pharmacy claims data, and the secondary outcomes are glycaemic control as measured by glycosylated haemoglobin values, healthcare utilisation and healthcare spending.Ethics and disseminationThis protocol has been approved by the Institutional Review Board of Brigham and Women’s Hospital and the Privacy Board of Horizon Blue Cross Blue Shield of New Jersey. We plan to present the results of this trial at national meetings and in manuscripts submitted to peer-reviewed journals.Trial registration numberNCT 02846779.

show abstract

Section: Sample Size Considerationsmentioning

confidence: 99%

Targeted Adherence Intervention to Reach Glycemic Control with Insulin Therapy for patients with Diabetes (TARGIT-Diabetes): rationale and design of a pragmatic randomised clinical trial

et al. 2017

View full text Add to dashboard Cite

show abstract

“…Indeed, it is becoming increasingly clear that traditional risk prediction models (commonly based on a handful of epidemiological factors) fail to capture important information about the individual’s behavior, environment, comorbidities and personal biological makeup. Now, with an influx of detailed patient data residing in large, prospective datasets 3, 4 and the rapid adoption of electronic health records (EHRs), there is an increasing pool of information that can potentially be analyzed to refine our predictive capabilities to deliver better care 30 .…”

Section: Introductionmentioning

confidence: 99%

The use of machine learning for the identification of peripheral artery disease and future mortality risk

Ross

Shah

Dalman

et al. 2016

Journal of Vascular Surgery

113

View full text Add to dashboard Cite

Objective A key aspect of the precision medicine effort is the development of informatics tools that can analyze and interpret ‘big data’ sets in an automated and adaptive fashion, while providing accurate and actionable clinical information. The aims of this study were to develop machine learning algorithms for the identification of disease and the prognostication of mortality risk, and to determine whether such models perform better than classical statistical analyses. Methods Focusing on peripheral artery disease (PAD), patient data were derived from a prospective, observational study of 1,755 patients who presented for elective coronary angiography. We employed multiple supervised machine learning algorithms and utilized diverse clinical, demographic, imaging and genomic information in a hypothesis-free manner to build models that could identify patients with PAD and predict future mortality. Comparison was made to standard stepwise linear regression models. Results Our machine-learned models outperformed stepwise logistic regression models both for the identification of patients with PAD (AUC 0.87 versus 0.76, respectively, P=0.03), and predicting future mortality (AUC 0.76 versus 0.65, respectively, P=0.10). Both machine-learned models were markedly better calibrated than the stepwise logistic regression models, thus providing more accurate disease and mortality risk estimates. Conclusions Machine learning approaches can produce more accurate disease classification and prediction models. These tools may prove clinically useful for the automated identification of patients with highly morbid diseases for which aggressive risk factor management can improve outcomes.

show abstract

“…Based on the paucity of compounds currently in trials, one major hurdle may be planning preclinical studies that consider anti-virulence metrics appropriately, as discussed above. Perhaps, another equally important aspect to consider is the integration of predictive analytics into the clinical trials of anti-virulence drug discovery [68,69 • ] to avoid preemptive trial failure. Finally, moving agents into preclinical and clinical studies is costly, and prohibitively so for academic research laboratories.…”

Section: Clinical Use Of Anti-virulence Drugs Obstacles and Considementioning

confidence: 99%

Considerations and caveats in anti-virulence drug development

Maura

Ballok

Rahme

2016

Current Opinion in Microbiology

128

110

View full text Add to dashboard Cite

As antibiotic resistance remains a major public health threat, anti-virulence therapy research is gaining interest. Hundreds of potential anti-virulence compounds have been examined, but very few have made it to clinical trials and none have been approved. This review surveys the current anti-virulence research field with a focus on the highly resistant and deadly ESKAPE pathogens, especially Pseudomonas aeruginosa. We discuss timely considerations and caveats in anti-virulence drug development, including target identification, administration, preclinical development, and metrics for success in clinical trials. Development of a defined pipeline for anti-virulence agents, which differs in important ways from conventional antibiotics, is imperative for the future success of these critically needed drugs.

show abstract

Integrating Predictive Analytics Into High-Value Care

Cited by 155 publications

References 7 publications

Targeted Adherence Intervention to Reach Glycemic Control with Insulin Therapy for patients with Diabetes (TARGIT-Diabetes): rationale and design of a pragmatic randomised clinical trial

Targeted Adherence Intervention to Reach Glycemic Control with Insulin Therapy for patients with Diabetes (TARGIT-Diabetes): rationale and design of a pragmatic randomised clinical trial

The use of machine learning for the identification of peripheral artery disease and future mortality risk

Considerations and caveats in anti-virulence drug development

Contact Info

Product

Resources

About