OBJECTIVES:The optimal approach for resuscitation in septic shock remains unclear despite multiple randomized controlled trials (RCTs). Our objective was to investigate whether previously uncharacterized variation across individuals in their response to resuscitation strategies may contribute to conflicting average treatment effects in prior RCTs. DESIGN:We randomly split study sites from the Australian Resuscitation of Sepsis Evaluation (ARISE) and Protocolized Care for Early Septic Shock (ProCESS) trials into derivation and validation cohorts. We trained machine learning models to predict individual absolute risk differences (iARDs) in 90-day mortality in derivation cohorts and tested for heterogeneity of treatment effect (HTE) in validation cohorts and swapped these cohorts in sensitivity analyses. We fit the best-performing model in a combined dataset to explore roles of patient characteristics and individual components of early goal-directed therapy (EGDT) to determine treatment responses. SETTING:Eighty-one sites in Australia, New Zealand, Hong Kong, Finland, Republic of Ireland, and the United States. PATIENTS:Adult patients presenting to the emergency department with severe sepsis or septic shock. INTERVENTIONS:EGDT vs. usual care. MEASUREMENTS AND MAIN RESULTS:A local-linear random forest model performed best in predicting iARDs. In the validation cohort, HTE was confirmed, evidenced by an interaction between iARD prediction and treatment (p< 0.001). When patients were grouped based on predicted iARDs, treatment response increased from the lowest to the highest quintiles (absolute risk difference [95% CI], –8% [–19% to 4%] and relative risk reduction, 1.34 [0.89–2.01] in quintile 1 suggesting harm from EGDT, and 12% [1–23%] and 0.64 [0.42–0.96] in quintile 5 suggesting benefit). Sensitivity analyses showed similar findings. Pre-intervention albumin contributed the most to HTE. Analyses of individual EGDT components were inconclusive. CONCLUSIONS:Treatment response to EGDT varied across patients in two multicenter RCTs with large benefits for some patients while others were harmed. Patient characteristics, including albumin, were most important in identifying HTE.
more »
« less
Technical note: Optimal allocation of limited proton therapy resources using model‐based patient selection
Abstract PurposeWe consider the following scenario: A radiotherapy clinic has a limited number of proton therapy slots available each day to treat cancer patients of a given tumor site. The clinic's goal is to minimize the expected number of complications in the cohort of all patients of that tumor site treated at the clinic, and thereby maximize the benefit of its limited proton resources. MethodsTo address this problem, we extend the normal tissue complication probability (NTCP) model–based approach to proton therapy patient selection to the situation of limited resources at a given institution. We assume that, on each day, a newly diagnosed patient is scheduled for treatment at the clinic with some probability and with some benefit from protons over photons, which is drawn from a probability distribution. When a new patient is scheduled for treatment, a decision for protons or photons must be made, and a patient may wait only for a limited amount of time for a proton slot becoming available. The goal is to determine the thresholds for selecting a patient for proton therapy, which optimally balance the competing goals of making use of all available slots while not blocking slots with patients with low benefit. This problem can be formulated as a Markov decision process (MDP) and the optimal thresholds can be determined via a value‐policy iteration method. ResultsThe optimal thresholds depend on the number of available proton slots, the average number of patients under treatment, and the distribution of values. In addition, the optimal thresholds depend on the current utilization of the facility. For example, if one proton slot is available and a second frees up shortly, the optimal threshold is lower compared to a situation where all but one slot remain blocked for longer. ConclusionsMDP methodology can be used to augment current NTCP model–based patient selection methods to the situation that, on any given day, the number of proton slots is limited. The optimal threshold then depends on the current utilization of the proton facility. Although, the optimal policy yields only a small nominal benefit over a constant threshold, it is more robust against variations in patient load.
more »
« less
- Award ID(s):
- 1847865
- PAR ID:
- 10370350
- Publisher / Repository:
- Wiley Blackwell (John Wiley & Sons)
- Date Published:
- Journal Name:
- Medical Physics
- Volume:
- 49
- Issue:
- 8
- ISSN:
- 0094-2405
- Page Range / eLocation ID:
- p. 4980-4987
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Drug-resistant HIV-1 has caused a growing concern in clinic and public health. Although combination antiretroviral therapy can contribute massively to the suppression of viral loads in patients with HIV-1, it cannot lead to viral eradication. Continuing viral replication during sub-optimal therapy (due to poor adherence or other reasons) may lead to the accumulation of drug resistance mutations, resulting in an increased risk of disease progression. Many studies also suggest that events occurring during the early stage of HIV-1 infection (i.e., the first few hours to days following HIV exposure) may determine whether the infection can be successfully established. However, the numbers of infected cells and viruses during the early stage are extremely low and stochasticity may play a critical role in dictating the fate of infection. In this paper, we use stochastic models to investigate viral infection and the emergence of drug resistance of HIV-1. The stochastic model is formulated by a continuous-time Markov chain (CTMC), which is derived based on an ordinary differential equation model proposed by Kitayimbwa et al. that includes both forward and backward mutations. An analytic estimate of the probability of the clearance of HIV infection of the CTMC model near the infection-free equilibrium is obtained by a multitype branching process approximation. The analytical predictions are validated by numerical simulations. Unlike the deterministic dynamics where the basic reproduction number $$ \mathcal{R}_0 $$ serves as a sharp threshold parameter (i.e., the disease dies out if $$ \mathcal{R}_0 < 1 $$ and persists if $$ \mathcal{R}_0 > 1 $$), the stochastic models indicate that there is always a positive probability for HIV infection to be eradicated in patients. In the presence of antiretroviral therapy, our results show that the chance of clearance of the infection tends to increase although drug resistance is likely to emerge.more » « less
-
PURPOSE: Identify Oropharyngeal cancer (OPC) patients at high-risk of developing long-term severe radiation-associated symptoms using dose volume histograms for organs-at-risk, via unsupervised clustering. MATERIAL AND METHODS: All patients were treated using radiation therapy for OPC. Dose-volume histograms of organs-at-risk were extracted from patients’ treatment plans. Symptom ratings were collected via the MD Anderson Symptom Inventory (MDASI) given weekly during, and 6 months post-treatment. Drymouth, trouble swallowing, mucus, and vocal dysfunction were selected for analysis in this study. Patient stratifications were obtained by applying Bayesian Mixture Models with three components to patient’s dose histograms for relevant organs. The clusters with the highest total mean doses were translated into dose thresholds using rule mining. Patient stratifications were compared against Tumor staging information using multivariate likelihood ratio tests. Model performance for prediction of moderate/severe symptoms at 6 months was compared against normal tissue complication probability (NTCP) models using cross-validation. RESULTS: A total of 349 patients were included for long-term symptom prediction. High-risk clusters were significantly correlated with outcomes for severe late drymouth (p <.0001, OR = 2.94), swallow (p = .002, OR = 5.13), mucus (p = .001, OR = 3.18), and voice (p = .009, OR = 8.99). Simplified clusters were also correlated with late severe symptoms for drymouth (p <.001, OR = 2.77), swallow (p = .01, OR = 3.63), mucus (p = .01, OR = 2.37), and voice (p <.001, OR = 19.75). Proposed cluster stratifications show better performance than NTCP models for severe drymouth (AUC.598 vs.559, MCC.143 vs.062), swallow (AUC.631 vs.561, MCC.20 vs -.030), mucus (AUC.596 vs.492, MCC.164 vs -.041), and voice (AUC.681 vs.555, MCC.181 vs -.019). Simplified dose thresholds also show better performance than baseline models for predicting late severe ratings for all symptoms. CONCLUSION: Our results show that leveraging the 3-D dose histograms from radiation therapy plan improves stratification of patients according to their risk of experiencing long-term severe radiation associated symptoms, beyond existing NTPC models. Our rule-based method can approximate our stratifications with minimal loss of accuracy and can proactively identify risk factors for radiation-associated toxicity.more » « less
-
Survival of pediatric AML remains poor despite maximized myelosuppressive therapy. The pneumocystis jiroveci pneumonia (PJP)-treating medication atovaquone (AQ) suppresses oxidative phosphorylation (OXPHOS) and reduces AML burden in patient-derived xenograft (PDX) mouse models, making it an ideal concomitant AML therapy. Poor palatability and limited product formulations have historically limited routine use of AQ in pediatric AML patients. Patients with de novo AML were enrolled at two hospitals. Daily AQ at established PJP dosing was combined with standard AML therapy, based on the Medical Research Council backbone. AQ compliance, adverse events (AEs), ease of administration score (scale: 1 (very difficult)-5 (very easy)) and blood/marrow pharmacokinetics (PK) were collected during Induction 1. Correlative studies assessed AQ-induced apoptosis and effects on OXPHOS. PDX models were treated with AQ. A total of 26 patients enrolled (ages 7.2 months–19.7 years, median 12 years); 24 were evaluable. A total of 14 (58%) and 19 (79%) evaluable patients achieved plasma concentrations above the known anti-leukemia concentration (>10 µM) by day 11 and at the end of Induction, respectively. Seven (29%) patients achieved adequate concentrations for PJP prophylaxis (>40 µM). Mean ease of administration score was 3.8. Correlative studies with AQ in patient samples demonstrated robust apoptosis, OXPHOS suppression, and prolonged survival in PDX models. Combining AQ with chemotherapy for AML appears feasible and safe in pediatric patients during Induction 1 and shows single-agent anti-leukemic effects in PDX models. AQ appears to be an ideal concomitant AML therapeutic but may require intra-patient dose adjustment to achieve concentrations sufficient for PJP prophylaxis.more » « less
-
Abstract ObjectiveEarly identification of chronic diseases is a pillar of precision medicine as it can lead to improved outcomes, reduction of disease burden, and lower healthcare costs. Predictions of a patient’s health trajectory have been improved through the application of machine learning approaches to electronic health records (EHRs). However, these methods have traditionally relied on “black box” algorithms that can process large amounts of data but are unable to incorporate domain knowledge, thus limiting their predictive and explanatory power. Here, we present a method for incorporating domain knowledge into clinical classifications by embedding individual patient data into a biomedical knowledge graph. Materials and MethodsA modified version of the Page rank algorithm was implemented to embed millions of deidentified EHRs into a biomedical knowledge graph (SPOKE). This resulted in high-dimensional, knowledge-guided patient health signatures (ie, SPOKEsigs) that were subsequently used as features in a random forest environment to classify patients at risk of developing a chronic disease. ResultsOur model predicted disease status of 5752 subjects 3 years before being diagnosed with multiple sclerosis (MS) (AUC = 0.83). SPOKEsigs outperformed predictions using EHRs alone, and the biological drivers of the classifiers provided insight into the underpinnings of prodromal MS. ConclusionUsing data from EHR as input, SPOKEsigs describe patients at both the clinical and biological levels. We provide a clinical use case for detecting MS up to 5 years prior to their documented diagnosis in the clinic and illustrate the biological features that distinguish the prodromal MS state.more » « less