Dataset Information

Improving palliative care with deep learning.

ABSTRACT: BACKGROUND:Access to palliative care is a key quality metric which most healthcare organizations strive to improve. The primary challenges to increasing palliative care access are a combination of physicians over-estimating patient prognoses, and a shortage of palliative staff in general. This, in combination with treatment inertia can result in a mismatch between patient wishes, and their actual care towards the end of life. METHODS:In this work, we address this problem, with Institutional Review Board approval, using machine learning and Electronic Health Record (EHR) data of patients. We train a Deep Neural Network model on the EHR data of patients from previous years, to predict mortality of patients within the next 3-12 month period. This prediction is used as a proxy decision for identifying patients who could benefit from palliative care. RESULTS:The EHR data of all admitted patients are evaluated every night by this algorithm, and the palliative care team is automatically notified of the list of patients with a positive prediction. In addition, we present a novel technique for decision interpretation, using which we provide explanations for the model's predictions. CONCLUSION:The automatic screening and notification saves the palliative care team the burden of time consuming chart reviews of all patients, and allows them to take a proactive approach in reaching out to such patients rather then relying on referrals from the treating physicians.

SUBMITTER: Avati A

PROVIDER: S-EPMC6290509 | biostudies-literature | 2018 Dec

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Improving palliative care with deep learning.

Avati Anand A Jung Kenneth K Harman Stephanie S Downing Lance L Ng Andrew A Shah Nigam H NH

BMC medical informatics and decision making 20181212 Suppl 4

<h4>Background</h4>Access to palliative care is a key quality metric which most healthcare organizations strive to improve. The primary challenges to increasing palliative care access are a combination of physicians over-estimating patient prognoses, and a shortage of palliative staff in general. This, in combination with treatment inertia can result in a mismatch between patient wishes, and their actual care towards the end of life.<h4>Methods</h4>In this work, we address this problem, with Ins ...[more]

PMID: 30537977

Similar Datasets

Project description:Introduction: Improving end-of-life (EOL) care is a priority worldwide as this population experiences poor outcomes and accounts disproportionately for costs. In clinical practice, physician judgement is the core method of identifying EOL care needs but has important limitations. Machine learning (ML) is a subset of artificial intelligence advancing capacity to identify patterns and make predictions using large datasets. ML approaches have the potential to improve clinical decision-making and policy design, but there has been no systematic assembly of current evidence. Methods: We conducted a rapid review, searching systematically seven databases from inception to December 31st, 2018: EMBASE, MEDLINE, Cochrane Library, PsycINFO, WOS, SCOPUS and ECONLIT. We included peer-reviewed studies that used ML approaches on routine data to improve palliative and EOL care for adults. Our specified outcomes were survival, quality of life (QoL), place of death, costs, and receipt of high-intensity treatment near end of life. We did not search grey literature and excluded material that was not a peer-reviewed article. Results: The database search identified 426 citations. We discarded 162 duplicates and screened 264 unique title/abstracts, of which 22 were forwarded for full text review. Three papers were included, 18 papers were excluded and one full text was sought but unobtainable. One paper predicted six-month mortality, one paper predicted 12-month mortality and one paper cross-referenced predicted 12-month mortality with healthcare spending. ML-informed models outperformed logistic regression in predicting mortality but poor prognosis is a weak driver of costs. Models using only routine administrative data had limited benefit from ML methods. Conclusion: While ML can in principle help to identify those at risk of adverse outcomes and inappropriate treatment near EOL, applications to policy and practice are formative. Future research must not only expand scope to other outcomes and longer timeframes, but also engage with individual preferences and ethical challenges.

Project description:Coordination of services used by palliative care patients across care contexts is essential in providing patient centred care. In Lothian, Edinburgh, a baseline audit in 2008 of patients known to all four specialist palliative care teams revealed only 49% had information available to out of hours (OOH) general practitioners (GPs). This highlighted the poor handover and sharing of information, which are essential for providing quality care for palliative patients in accordance with their wishes, and for reducing inappropriate hospital admissions. A number of quality improvement measures have been introduced, some nationally in Scotland, such as the roll out of Electronic Palliative Care Summaries (ePCS) - an electronic register containing up to date information including patient wishes and latest treatment decisions. In addition there have been changes to the GP Quality Outcomes Framework encouraging the use of electronic records. Locally, at Marie Curie Hospice, drivers were implemented including hosting GP education evenings promoting ePCS use, alteration of hospice discharge letter format to complement ePCS completion, in addition to offering specialist nurse support and presence at GP practice palliative care register meetings. A re-audit in 2012 revealed that 75% of specialist palliative care patients had electronic information available to OOH services, and in 2013, 71% of patients. This represents a significant improvement in electronic information sharing across care contexts. Building on the progress of ePCS, a new Electronic Key Information Summary is currently being rolled out across Scotland. This quality improvement report reflects on the positive measures taken to address the important clinical need of effective electronic handover for specialist palliative care patients in Lothian. Furthermore, it highlights the ongoing requirement to continue to improve the quality and availability of electronically shared information for every patient known to palliative care services across care contexts.

Project description:Background: Demographic change and the medical imperative to accompany patients at all times and also in the case of illness leading to death require good basic knowledge of palliative care in large parts of the medical profession. Palliative care has been introduced into undergraduate medical education as a compulsory subject: "interdisciplinary subject 13 palliative care" (Q13). While course concepts for Q13 have already been positively evaluated, assessment of the consolidation and practical relevance of the knowledge taught is lacking. Methods: Assessment of the consolidation of the learning content from Q13 after the practical year (the "practical year" is the sixth and final year of undergraduate medical education in Germany) by means of a survey with a proven questionnaire and integrated qualitative free-text analysis of a cohort of medical students (n=176) who had already participated in an evaluation before and after Q13. Results: The response rate was 96% after Q13 and 45% after the practical year (PY). Teaching was predominantly perceived as more helpful than the PY (p<0.001). Compared to the status after Q13, students rated themselves as less competent after the PY in all areas surveyed, including drug-based pain therapy (p=0.0386). The certainty in informing patients about the incurability of the disease also decreased significantly after the PY (p=0.0117), although the preparation in Q13 was positively highlighted. Conclusion: The knowledge acquired in Q13 could not be anchored in the PY. On the contrary, after initial practical experiences, the students found it challenging to conduct conversations in cases of serious illness and to deal with their own uncertainty in the care of seriously ill patients. Structural factors regarding palliative care in the PY, as well as intrinsic motives of students, such as prior knowledge or motivation to learn, should be analyzed to identify ways to close the gap between theoretical and practical training in general palliative care. To generate samples that are sufficiently representative, future studies on teaching should be easily accessible to students and consider attractive forms of evaluation including electronic methods and social media.

Project description:MotivationAccurate prediction of residue-residue distances is important for protein structure prediction. We developed several protein distance predictors based on a deep learning distance prediction method and blindly tested them in the 14th Critical Assessment of Protein Structure Prediction (CASP14). The prediction method uses deep residual neural networks with the channel-wise attention mechanism to classify the distance between every two residues into multiple distance intervals. The input features for the deep learning method include co-evolutionary features as well as other sequence-based features derived from multiple sequence alignments (MSAs). Three alignment methods are used with multiple protein sequence/profile databases to generate MSAs for input feature generation. Based on different configurations and training strategies of the deep learning method, five MULTICOM distance predictors were created to participate in the CASP14 experiment.ResultsBenchmarked on 37 hard CASP14 domains, the best performing MULTICOM predictor is ranked 5th out of 30 automated CASP14 distance prediction servers in terms of precision of top L/5 long-range contact predictions (i.e. classifying distances between two residues into two categories: in contact (< 8 Angstrom) and not in contact otherwise) and performs better than the best CASP13 distance prediction method. The best performing MULTICOM predictor is also ranked 6th among automated server predictors in classifying inter-residue distances into 10 distance intervals defined by CASP14 according to the precision of distance classification. The results show that the quality and depth of MSAs depend on alignment methods and sequence databases and have a significant impact on the accuracy of distance prediction. Using larger training datasets and multiple complementary features improves prediction accuracy. However, the number of effective sequences in MSAs is only a weak indicator of the quality of MSAs and the accuracy of predicted distance maps. In contrast, there is a strong correlation between the accuracy of contact/distance predictions and the average probability of the predicted contacts, which can therefore be more effectively used to estimate the confidence of distance predictions and select predicted distance maps.AvailabilityThe software package, source code, and data of DeepDist2 are freely available at https://github.com/multicom-toolbox/deepdist and https://zenodo.org/record/4712084#.YIIM13VKhQM.

Project description:ImportanceEarly palliative care interventions drive high-value care but currently are underused. Health care professionals face challenges in identifying patients who may benefit from palliative care.ObjectiveTo develop a deep learning algorithm using longitudinal electronic health records to predict mortality risk as a proxy indicator for identifying patients with dementia who may benefit from palliative care.Design, setting, and participantsIn this retrospective cohort study, 6-month, 1-year, and 2-year mortality prediction models with recurrent neural networks used patient demographic information and topics generated from clinical notes within Partners HealthCare System, an integrated health care delivery system in Boston, Massachusetts. This study included 26 921 adult patients with dementia who visited the health care system from January 1, 2011, through December 31, 2017. The models were trained using a data set of 24 229 patients and validated using another data set of 2692 patients. Data were analyzed from September 18, 2018, to May 15, 2019.Main outcomes and measuresThe area under the receiver operating characteristic curve (AUC) for 6-month and 1- and 2-year mortality prediction models and the factors contributing to the predictions.ResultsThe study cohort included 26 921 patients (16 263 women [60.4%]; mean [SD] age, 74.6 [13.5] years). For the 24 229 patients in the training data set, mean (SD) age was 74.8 (13.2) years and 14 632 (60.4%) were women. For the 2692 patients in the validation data set, mean (SD) age was 75.0 (12.6) years and 1631 (60.6%) were women. The 6-month model reached an AUC of 0.978 (95% CI, 0.977-0.978); the 1-year model, 0.956 (95% CI, 0.955-0.956); and the 2-year model, 0.943 (95% CI, 0.942-0.944). The top-ranked latent topics associated with 6-month and 1- and 2-year mortality in patients with dementia include palliative and end-of-life care, cognitive function, delirium, testing of cholesterol levels, cancer, pain, use of health care services, arthritis, nutritional status, skin care, family meeting, shock, respiratory failure, and swallowing function.Conclusions and relevanceA deep learning algorithm based on patient demographic information and longitudinal clinical notes appeared to show promising results in predicting mortality among patients with dementia in different time frames. Further research is necessary to determine the feasibility of applying this algorithm in clinical settings for identifying unmet palliative care needs earlier.

Dataset Information

Improving palliative care with deep learning.

Publications

Improving palliative care with deep learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets