Automated Identification of Patients with Advanced Illness.

Early identification of advanced illness patients within an inpatient population is essential in order to establish the patient's goals of care. Having goals of care conversations enables hospital patients to dictate a plan for care in concordance with their values and wishes. These conversations allow a patient to maintain some control, rather than be subjected to a default care process that may not be desired and may not provide benefit. In this study the performance of two approaches which identify advanced illness patients within an inpatient population were evaluated: LACE (a rule-based approach that uses L - Length of stay, A- Acuity of Admission, C- Co-morbidities, E- Emergency room visits), and a novel approach: Hospital Impairment Score (HIS). The Hospital impairment score is derived by leveraging both rule-based insights and a novel machine learning algorithm. It was identified that HIS significantly outperformed the LACE score, the current model being used in production at Northwell Health. Furthermore, we describe how the HIS model was piloted at a single hospital, was launched into production, and is being successfully used by clinicians at that hospital.

Let Sleeping Patients Lie, avoiding unnecessary overnight vitals monitoring using a clinically based deep-learning model.

Impaired sleep for hospital patients is an all too common reality. Sleep disruptions due to unnecessary overnight vital sign monitoring are associated with delirium, cognitive impairment, weakened immunity, hypertension, increased stress, and mortality. It is also one of the most common complaints of hospital patients while imposing additional burdens on healthcare providers. Previous efforts to forgo overnight vital sign measurements and improve patient sleep used providers' subjective stability assessment or utilized an expanded, thus harder to retrieve, set of vitals and laboratory results to predict overnight clinical risk. Here, we present a model that incorporates past values of a small set of vital signs and predicts overnight stability for any given patient-night. Using data obtained from a multi-hospital health system between 2012 and 2019, a recurrent deep neural network was trained and evaluated using ~2.3 million admissions and 26 million vital sign assessments. The algorithm is agnostic to patient location, condition, and demographics, and relies only on sequences of five vital sign measurements, a calculated Modified Early Warning Score, and patient age. We achieved an area under the receiver operating characteristic curve of 0.966 (95% confidence interval [CI] 0.956-0.967) on the retrospective testing set, and 0.971 (95% CI 0.965-0.974) on the prospective set to predict overnight patient stability. The model enables safe avoidance of overnight monitoring for ~50% of patient-nights, while only misclassifying 2 out of 10,000 patient-nights as stable. Our approach is straightforward to deploy, only requires regularly obtained vital signs, and delivers easily actionable clinical predictions for a peaceful sleep in hospitals.

An approach to predicting patient experience through machine learning and social network analysis.

OBJECTIVE: Improving the patient experience has become an essential component of any healthcare system's performance metrics portfolio. In this study, we developed a machine learning model to predict a patient's response to the Hospital Consumer Assessment of Healthcare Providers and Systems survey's "Doctor Communications" domain questions while simultaneously identifying most impactful providers in a network. MATERIALS AND METHODS: This is an observational study of patients admitted to a single tertiary care hospital between 2016 and 2020. Using machine learning algorithms, electronic health record data were used to predict patient responses to Hospital Consumer Assessment of Healthcare Providers and Systems survey questions in the doctor domain, and patients who are at risk for responding negatively were identified. Model performance was assessed by area under receiver-operating characteristic curve. Social network analysis metrics were also used to identify providers most impactful to patient experience. RESULTS: Using a random forest algorithm, patients' responses to the following 3 questions were predicted: "During this hospital stay how often did doctors. 1) treat you with courtesy and respect? 2) explain things in a way that you could understand? 3) listen carefully to you?" with areas under the receiver-operating characteristic curve of 0.876, 0.819, and 0.819, respectively. Social network analysis found that doctors with higher centrality appear to have an outsized influence on patient experience, as measured by rank in the random forest model in the doctor domain. CONCLUSIONS: A machine learning algorithm identified patients at risk of a negative experience. Furthermore, a doctor social network framework provides metrics for identifying those providers that are most influential on the patient experience.

Determining the role of correlated firing in large populations of neurons using white noise and natural scene stimuli.

The role of correlated firing in representing information has been a subject of much discussion. Several studies in retina, visual cortex, somatosensory cortex, and motor cortex, have suggested that it plays only a minor role, carrying <10% of the total information carried by the neurons (Gawne & Richmond, 1993; Nirenberg et al., 2001; Oram et al., 2001; Petersen, Panzeri, & Diamond, 2001; Rolls et al., 2003). A limiting factor of these studies, however, is that they were carried out using pairs of neurons; how the results extend to large populations was not clear. Recently, new methods for modeling network firing patterns have been developed (Nirenberg & Pandarinath, 2012; Pillow et al., 2008), opening the door to answering this question for more complete populations. One study, Pillow et al. (2008), showed that including correlations increased information by a modest amount, ~20%; however, this work used only a single retina (primate) and a white noise stimulus. Here we performed the analysis using several retinas (mouse) and both white noise and natural scene stimuli. The results showed that correlations added little information when white noise stimuli were used (~13%), similar to Pillow et al.'s findings, and essentially no information when natural scene stimuli were used. Further, the results showed that ignoring correlations did not change the quality of the information carried by the population (as measured by comparing the full pattern of decoding errors). These results suggest generalization: the pairwise analysis in several species show that correlations account for very little of the total information. Now, the analysis with large populations in two species show a similar result, that correlations still account for only a small fraction of the total information, and, most significantly, the amount is not statistically significant when natural stimuli are used, making rapid advances in the study of population coding possible.

Symmetry, probability, and recognition in face space.

The essential midline symmetry of human faces is shown to play a key role in facial coding and recognition. This also has deep and important connections with recent explorations of the organization of primate cortex, as well as human psychophysical experiments. Evidence is presented that the dimension of face recognition space for human faces is dramatically lower than previous estimates. One result of the present development is the construction of a probability distribution in face space that produces an interesting and realistic range of (synthetic) faces. Another is a recognition algorithm that by reasonable criteria is nearly 100% accurate.

On the dimensionality of face space.

The dimensionality of face space is measured objectively in a psychophysical study. Within this framework, we obtain a measurement of the dimension for the human visual system. Using an eigenface basis, evidence is presented that talented human observers are able to identify familiar faces that lie in a space of roughly 100 dimensions and the average observer requires a space of between 100 and 200 dimensions. This is below most current estimates. It is further argued that these estimates give an upper bound for face space dimension and this might be lowered by better constructed "eigenfaces" and by talented observers.