Learning to Personalize from Practice: A Real World Evidence Approach of Care Plan Personalization based on Differential Patient Behavioral Responses in Care Management Records.

Recent studies documented the importance of individuality and heterogeneity in care planning. In practice, varying behavioral responses are revealed in patients' care management (CM) records. However, today's care programs are structured around population-level evidence. What if care managers can take advantage of the revealed behavioral response for personalization? The goal of this study is thus to quantify behavioral response from CM records for informing individual-level intervention decisions. We present a Behavioral Response Inference Framework (BRIeF) for understanding differential behavioral responses that are key to effective care planning. We analyze CM records from a healthcare network over a 14-month period and obtain a set of 2,416 intervention-goal attainment records. Promising results demonstrate that the individual-level care planning strategies that are learned from practice by BRIeF, outperform population-level strategies, yielding significantly more accurate intervention recommendations for goal attainment. To our knowledge, this is the first study of learning practice-based evidence from CM records for care planning, suggesting that increased patient behavioral understanding could potentially benefit augmented intelligence for care management decision support.

Using Semantic Technologies to Extract Highlights from Care Notes.

We propose a cognitive system for patient-centric care that leverages and combines natural language processing, semantics, and learning from users over time to support care professionals working with large volumes of patient notes. The proposed methods highlight the entities embedded in the unstructured data to provide a holistic semantic view of an individual. A user-based evaluation is presented, showing consensus between the users and the system.

International practice survey on palliative lung radiotherapy: third international consensus workshop on palliative radiotherapy and symptom control.

BACKGROUND: The purpose of this work was to disseminate international practice survey results created in conjunction with the Third International Lung Cancer Consensus Workshop. PATIENTS AND METHODS: In conjunction with the American Society for Radiation Oncology (ASTRO) Guideline for Palliative Lung Cancer Care and International Workshop Consensus statements, an online international practice survey was conducted during the summer of 2010. The survey included demographic, educational, and clinical questions as well as 5 cases exploring the role of external beam radiotherapy, endobronchial brachytherapy, and concurrent chemoradiation. RESULTS: A total of 279 individuals responded to the survey over a 3-month period. Most respondents were hospital-based, academic, or government-funded radiation oncologists. Factors that consistently related to use and choice of external beam dose fractionation included estimated treatment benefit to patient, performance status (PS), symptom severity, patient choice, estimated prognosis, and previous radiation to the same site. Factors consistently not related to use and dose fractionation included requirement for future radiation therapy, department policy, and waiting lists. A significant range of dose fractionation schedules existed for external beam (n = 35) and endobronchial brachytherapy treatment (n = 10). The integration of concurrent chemotherapy was recorded by a significant minority of respondents despite lack of level I evidence to support its use. Geographic differences in the use of external beam dose fractionation and of concurrent chemotherapy were seen. CONCLUSIONS: Various patient, tumor, treatment, and logistic factors are associated with the variable use and external beam dose fractionation of palliative lung treatments. The copublication of the ASTRO Guideline for Palliative Lung Cancer Care and International Workshop Consensus statements should assist clinicians by providing evidence-based care.

Consensus statement on palliative lung radiotherapy: third international consensus workshop on palliative radiotherapy and symptom control.

The purpose of this work is to disseminate a consensus statement on palliative radiotherapy (RT) of lung cancer created in conjunction with the Third International Lung Cancer Consensus Workshop. The palliative lung RT workshop committee agreed on 5 questions relating to (1) patient selection, (2) thoracic external-beam radiation therapy (XRT) fractionation, (3) endobronchial brachytherapy (EBB), (4) concurrent chemotherapy (CC), and (5) palliative endpoint definitions. A PubMed search for primary/cross-referenced practice guidelines, consensus statements, meta-analyses, and/or systematic reviews was conducted. Final consensus statements were created after review and discussion of the available evidence. The following summary statements reflect the consensus of the international working group. 1. Key factors involved in the decision to deliver palliative RT include performance status, tumor stage, pulmonary function, XRT volume, symptomatology, weight loss, and patient preference. 2. Palliative thoracic XRT is generally indicated for patients with stage IV disease with current/impending symptoms and for patients with stage III disease treated for palliative intent. 3. There is no evidence to routinely recommend EBB alone or in conjunction with other palliative maneuvers in the initial palliative management of endobronchial obstruction resulting from lung cancer. 4. There is currently no evidence to routinely recommend CC with palliative-intent RT. 5. Standard assessment of symptoms and health-related quality of life (QOL) using validated questionnaires should be carried out in palliative RT lung cancer trials. Despite an expanding literature, continued prospective randomized investigations to better define the role of XRT, EBB, and CC in the context of thoracic palliation of patients with lung cancer is needed.

Risk analysis in radiation treatment: application of a new taxonomic structure.

BACKGROUND AND PURPOSE: Radiation treatment (RT) for cancer is susceptible to clinical incidents resulting from human errors and equipment failures. A systematic approach to collecting and processing incidents is required to manage patient risks. We describe the application of a new taxonomic structure for RT that supports risk analysis and organizational learning. MATERIALS AND METHODS: A systematic analysis of the RT process identified five process domains. Within each domain we defined incident type groups. We then constructed a database reflecting this taxonomic structure and populated it with incidents from publicly available sources. Querying this database provides insights into the nature and relative frequency of incidents in RT. RESULTS: There are relatively few reports of incidents in the Prescription domain compared with the Preparation and Treatment domains. There are also fewer reports of systematic and infrastructure incidents in comparison to sporadic and process incidents. Infrastructure incidents are mainly systematic in nature, while process incidents are more likely to be sporadic. CONCLUSIONS: The lack of a standard, systems-oriented framework for incident reporting makes it difficult to learn from existing incident report sources. A clear understanding of the potential consequences and relationships between different incident types will guide incident reporting, resource allocation, and risk management efforts.

Implications of cancer staging uncertainties in radiation therapy decisions.

INTRODUCTION: Radiation therapy (RT) for cancer is a critical medical procedure that occurs in a complex environment involving numerous health professionals, hardware, software, and equipment. Uncertainties and potential incidents can lead to inappropriate administration of radiation to patients, with sometimes catastrophic consequences such as premature death or appreciably impaired quality of life. The authors evaluate the impact of incorrectly staging (i.e., estimation of extent of cancer) breast cancer patients and resulting inappropriate treatment decisions. METHODS: The authors employ analytic and simulation methods in an influence-diagram framework to estimate the probability of incorrect staging and treatment decisions. As inputs, they use a combination of literature information on the accuracy and precision of pathology and tests as well as expert judgment. Sensitivity and value-of-information analyses are conducted to identify important uncertainties. RESULTS AND CONCLUSIONS: The authors find a small but nontrivial probability that breast cancer patients will be incorrectly staged and thus may be subjected to inappropriate treatment. Results are sensitive to a number of variables, and some routinely used tests for metastasis have very limited information value. This work has implications for the methods used in cancer staging, and the methods are generalizable for quantitative risk assessment of treatment errors.

In pursuit of an artful death: discussion of resuscitation status on an inpatient radiation oncology service.

GOALS OF WORK: Consensus has emerged among health practitioners, legal experts, clinical ethicists and the public that end-of-life decisions should be the shared responsibility of physicians and patients. In discussion of withholding cardiopulmonary resuscitation in cancer patients, however, opinion remains divided. We performed a quality assurance investigation on the use of the 'do-not-resuscitate' (DNR) order on an inpatient radiation oncology service to determine how often DNR orders are accompanied by a description of informed consent. PATIENTS AND METHODS: Records of patients admitted 1 July to 31 December 2002 were identified and reviewed to determine the presence or absence of a DNR order. Circumstances surrounding the order, including evidence of informed consent, were determined. MAIN RESULTS: The study population comprised 96 patients admitted 109 times. The median age was 64 years, and in 56.0% of admissions, the patient was female. In 26.8%, the patient had lung cancer. The intent of admission was curative in 53.2%, and palliative in 44.0%. DNR was recorded for 30.2% of patients, and there was evidence of informed consent in 41.4%. In 89.7% admission was with palliative intent. Nine patients (9.4%) experienced cardiac arrest; all were DNR at the time of their event. CONCLUSIONS: While almost one-third of the patients on this inpatient radiation oncology service had documented DNR status, informed consent appeared to have been obtained in fewer than half. Patient involvement in resuscitative decisions should be an ethical obligation. Performed well, this may also allow for exploration of patients' needs at the end of life, to allow the pursuit of what Nuland terms an 'artful death'.