Illuminating the dark spaces of healthcare with ambient intelligence.

Advances in machine learning and contactless sensors have given rise to ambient intelligence-physical spaces that are sensitive and responsive to the presence of humans. Here we review how this technology could improve our understanding of the metaphorically dark, unobserved spaces of healthcare. In hospital spaces, early applications could soon enable more efficient clinical workflows and improved patient safety in intensive care units and operating rooms. In daily living spaces, ambient intelligence could prolong the independence of older individuals and improve the management of individuals with a chronic disease by understanding everyday behaviour. Similar to other technologies, transformation into clinical applications at scale must overcome challenges such as rigorous clinical validation, appropriate data privacy and model transparency. Thoughtful use of this technology would enable us to understand the complex interplay between the physical environment and health-critical human behaviours.

Association between maternal employment status and presence of children with major congenital anomalies in Denmark.

IMPORTANCE: The burden of caring for children with complex medical problems such as major congenital anomalies falls principally on mothers, who in turn suffer a variety of potentially severe economic consequences. As well, health consequences of caregiving often further impact the social and economic prospects of mothers of children with major congenital anomalies (MCMCAs). Evaluating the long-term economic consequences of extensive in-home caregiving among MCMCAs can inform strategies to mitigate these effects. OBJECTIVE: To assess whether MCMCAs face reduced employment and increased need for disability benefits over a 20-year period. DESIGN: A population-based matched cohort study. SETTING: Denmark. PARTICIPANTS: All women who gave birth to a singleton child with a major congenital anomaly in Denmark between January 1, 1997 and December 31, 2017 (n = 23,637) and a comparison cohort of mothers matched by maternal age, parity, and infant's year of birth (n = 234,586). EXPOSURES: Liveborn infant with a major congenital anomaly. MAIN OUTCOMES AND MEASURES: The primary outcome was mothers' employment status, stratified by their child's age. Employment status was categorized as employed, outside the workforce (on temporary leave, holding a flexible job, or pursuing education), or unemployed; the number of weeks in each category was measured over time. The secondary outcome was time to receipt of a disability pension, which in Denmark implies permanent exit from the labor market. We used a negative binomial regression model to estimate the number of weeks in each employment category, stratified by the child's age (i.e., 0-1 year, > 1-6 years, 7-13 years, 14-18 years). A Cox proportional hazards regression model was used to compute hazard ratios as a measure of the relative risk of receiving a disability pension. Rate ratios and hazard ratios were adjusted for maternal demographics, pregnancy history, health, and infant's year of birth. RESULTS: During 1-6 years after delivery, MCMCAs were outside the workforce for a median of 50 weeks (IQR, 6-107 weeks), while members of the comparison cohort were outside the workforce for a median of 48 weeks (IQR, 4-98 weeks), corresponding to an adjusted rate ratio [ARR] of 1.05 (95% confidence interval [CI], 1.04-1.07). During the first year after delivery, MCMCAs were more likely to be employed than mothers in the comparison cohort (ARR, 1.08; 95% CI, 1.06-1.10). At all timepoints thereafter, MCMCAs had a lower rate of workforce participation. The rate of being outside the workforce was 5% higher than mothers in the comparison cohort during 1-6 years after delivery (ARR, 1.05; 95% CI, 1.04-1.07), 9% higher during 7-13 years after delivery (ARR, 1.09; 95% CI, 1.06-1.12), and 12% higher during 14-18 years after delivery (ARR, 1.12; 95% CI, 1.07-1.18). Overall, MCMCAs had a 20% increased risk of receiving a disability pension during follow-up than mothers in the matched comparison cohort [incidence rates 3.10 per 1000 person-years (95% CI, 2.89-3.32) vs. 2.34 per 1000 person-years (95% CI, 2.29-2.40), adjusted hazard ratio, 1.20; 95% CI, 1.11-1.29]. CONCLUSION AND RELEVANCE: MCMCAs were less likely to participate in the Danish workforce, less likely to be employed, and more likely to receive disability pensions than mothers of unaffected children. The rate of leaving the workforce intensified as their affected children grew older. The high demands of caregiving among MCMCAs may have long-term employment consequences even in nations with comprehensive and heavily tax-supported childcare systems, such as Denmark.

Influence of a COVID-19 vaccine's effectiveness and safety profile on vaccination acceptance.

Although a safe and effective vaccine holds the greatest promise for resolving the COVID-19 pandemic, hesitancy to accept vaccines remains common. To explore vaccine acceptance decisions, we conducted a national survey of 1,000 people from all US states in August of 2020 and a replication in December of 2020. Using a 3 × 3 × 3 factorial experimental design, we estimated the impact of three factors: probability of 1) protection against COVID-19, 2) minor side effects, and 3) a serious adverse reactions. The outcome was respondents' reported likelihood of receiving a vaccine for the coronavirus. Probability of vaccine efficacy (50%, 70%, or 90%) had the largest effect among the three factors. The probability of minor side effects (50%, 75%, 90%) including fever and sore arm, did not significantly influence likelihood of receiving the vaccine. The chances of a serious adverse reaction, such as temporary or permanent paralysis, had a small but significant effect. A serious adverse reaction rate of 1/100,000 was more likely to discourage vaccine use in comparison to rates of 1/million or 1/100 million. All interactions between the factors were nonsignificant. A replication following the announcement that vaccines were 95% effective showed small, but significant increases in the likelihood of taking a vaccine. The main effects and interactions in the model remained unchanged. Expected benefit was more influential in respondents' decision making than expected side effects. The absence of interaction effects suggests that respondents consider the side effects and benefits independently.

Caring for People With Depression: Costs Among 43 Million Commercially Insured Patients With or Without Comorbid Illnesses.

BACKGROUND: Depression is a common comorbidity for patients with chronic medical conditions. Although the costs of treating chronic medical illness in combination with depression are believed to be significantly higher than the costs of treating each condition independently, few studies have formally modeled the cost consequences of mental health comorbidity. PURPOSE: To estimate the relative magnitude of the independent and synergistic contributions to health care costs from depression diagnosis and other chronic physical health conditions. METHODS: Cross-sectional, observational study using all individuals >18 years of age in the national Blue Cross Blue Shield (BCBS) Axis claims database (N = 43,872,144) from calendar year 2018. General linear models with and without interaction terms were used to assess the relative magnitude of independent and synergistic contributions to total annual health care costs of depression alone and in combination with coronary heart disease, chronic kidney disease, chronic obstructive pulmonary disease, diabetes (both types 1 and 2), hypertension, and arthritis. RESULTS: The incremental annual cost associated with having a diagnosis of depression was $2,951 compared to $1,986-$6,251 for the other chronic physical conditions. The interaction between depression and chronic conditions accounted for less than one-hundredth of the amount of variation in costs explained by the main effects of depression and each chronic physical condition. CONCLUSIONS: The independent increase in total annual health care costs associated with a depression diagnosis was comparable to that of many common physical chronic conditions. This finding underscores the importance of health care service and payment models that acknowledge depression as an equal contributor to overall health care costs. The combination of depression and another chronic condition did not synergistically increase total annual health care costs beyond the increases in costs associated with each condition independently. This finding has implications for simplifying risk adjustment models.

It is widely believed that depression, when combined with other chronic physical conditions, systematically inflates health care costs. For example, it is assumed that the costs of caring for a patient with both depression and heart disease are higher than the costs of caring for each condition independently. Using a database that included 43 million commercially insured people in the United States, we found that the costs of care for patients with depression were comparable to the costs for patients with other chronic medical conditions. This result supports the need for mental health parity and for trained mental health care providers in medical settings. We then considered the costs of caring for people with depression with or with or without one of seven common chronic physical condition. Contrary to expectation, the combination of depression and any of the diagnoses appeared to have largely independent relationships with health care costs. The results contradict the suggestion that depression and chronic condition diagnoses act synergistically to inflate health care expenditures.

Identifying solutions to meet unmet needs of family caregivers using human-centered design.

BACKGROUND: Given the rapidly aging society, shrinking workforce, and reducing dependency ratio, there is an increasing challenge for family members to provide care for older adults. While a broad understanding of caregiver burden and its consequences have been studied across various contexts, there is a need to better understand this challenge among family caregivers in Asian societies. METHODS: This study is a cross-sectional observational study. A total of 20 dyads of community-based older adults, who required assistance with at least one activities of daily living, and family caregivers in Thailand participated in the study. We used the first three stages out of five stages of human-centered design: empathize, define, and ideate. RESULTS: On average caregivers were 59.2 years old, with 43% still employed. Of the older adult participants, 10 were interviewed, the others had moderate-to-severe cognitive impairment. Based on the analysis, six caregiver personas (i.e. semi-fictional characters) are identified. Caregiver personas of "The 2-Jober" and "My Life Purpose" has the highest caregiver burden score whereas "The Spouse" has the lowest. Based on the specific needs of the caregiver persona "My Life Purpose", the team brainstormed more than 80 potential solutions which were classified into three categories of solutions that satisfied the metrics of desirability, feasibility and viability: distributed medical care system, technology-charged care network, and community gathering for rest and recuperation. CONCLUSIONS: These solutions are culturally sensitive given that they are built around established behavioral patterns. This is an illustration of a method of innovation that can be applied to bring a culturally specific understanding, and to develop products and services to enable further independent aging.

Effect of a Biopsychosocial Intervention or Postural Therapy on Disability and Health Care Spending Among Patients With Acute and Subacute Spine Pain: The SPINE CARE Randomized Clinical Trial.

Importance: Low back and neck pain are often self-limited, but health care spending remains high. Objective: To evaluate the effects of 2 interventions that emphasize noninvasive care for spine pain. Design, Setting, and Participants: Pragmatic, cluster, randomized clinical trial conducted at 33 centers in the US that enrolled 2971 participants with neck or back pain of 3 months' duration or less (enrollment, June 2017 to March 2020; final follow-up, March 2021). Interventions: Participants were randomized at the clinic-level to (1) usual care (n = 992); (2) a risk-stratified, multidisciplinary intervention (the identify, coordinate, and enhance [ICE] care model that combines physical therapy, health coach counseling, and consultation from a specialist in pain medicine or rehabilitation) (n = 829); or (3) individualized postural therapy (IPT), a postural therapy approach that combines physical therapy with building self-efficacy and self-management (n = 1150). Main Outcomes and Measures: The primary outcomes were change in Oswestry Disability Index (ODI) score at 3 months (range, 0 [best] to 100 [worst]; minimal clinically important difference, 6) and spine-related health care spending at 1 year. A 2-sided significance threshold of .025 was used to define statistical significance. Results: Among 2971 participants randomized (mean age, 51.7 years; 1792 women [60.3%]), 2733 (92%) finished the trial. Between baseline and 3-month follow-up, mean ODI scores changed from 31.2 to 15.4 for ICE, from 29.3 to 15.4 for IPT, and from 28.9 to 19.5 for usual care. At 3-month follow-up, absolute differences compared with usual care were -5.8 (95% CI, -7.7 to -3.9; P < .001) for ICE and -4.3 (95% CI, -5.9 to -2.6; P < .001) for IPT. Mean 12-month spending was $1448, $2528, and $1587 in the ICE, IPT, and usual care groups, respectively. Differences in spending compared with usual care were -$139 (risk ratio, 0.93 [95% CI, 0.87 to 0.997]; P = .04) for ICE and $941 (risk ratio, 1.40 [95% CI, 1.35 to 1.45]; P < .001) for IPT. Conclusions and Relevance: Among patients with acute or subacute spine pain, a multidisciplinary biopsychosocial intervention or an individualized postural therapy intervention, each compared with usual care, resulted in small but statistically significant reductions in pain-related disability at 3 months. However, compared with usual care, the biopsychosocial intervention resulted in no significant difference in spine-related health care spending and the postural therapy intervention resulted in significantly greater spine-related health care spending at 1 year. Trial Registration: ClinicalTrials.gov Identifier: NCT03083886.

Parents' Perspectives on Using Artificial Intelligence to Reduce Technology Interference During Early Childhood: Cross-sectional Online Survey.

BACKGROUND: Parents' use of mobile technologies may interfere with important parent-child interactions that are critical to healthy child development. This phenomenon is known as technoference. However, little is known about the population-wide awareness of this problem and the acceptability of artificial intelligence (AI)-based tools that help with mitigating technoference. OBJECTIVE: This study aims to assess parents' awareness of technoference and its harms, the acceptability of AI tools for mitigating technoference, and how each of these constructs vary across sociodemographic factors. METHODS: We administered a web-based survey to a nationally representative sample of parents of children aged ≤5 years. Parents' perceptions that their own technology use had risen to potentially problematic levels in general, their perceptions of their own parenting technoference, and the degree to which they found AI tools for mitigating technoference acceptable were assessed by using adaptations of previously validated scales. Multiple regression and mediation analyses were used to assess the relationships between these scales and each of the 6 sociodemographic factors (parent age, sex, language, ethnicity, educational attainment, and family income). RESULTS: Of the 305 respondents, 280 provided data that met the established standards for analysis. Parents reported that a mean of 3.03 devices (SD 2.07) interfered daily in their interactions with their child. Almost two-thirds of the parents agreed with the statements "I am worried about the impact of my mobile electronic device use on my child" and "Using a computer-assisted coach while caring for my child would help me notice more quickly when my device use is interfering with my caregiving" (187/281, 66.5% and 184/282, 65.1%, respectively). Younger age, Hispanic ethnicity, and Spanish language spoken at home were associated with increased technoference awareness. Compared to parents' perceived technoference and sociodemographic factors, parents' perceptions of their own problematic technology use was the factor that was most associated with the acceptance of AI tools. CONCLUSIONS: Parents reported high levels of mobile device use and technoference around their youngest children. Most parents across a wide sociodemographic spectrum, especially younger parents, found the use of AI tools to help mitigate technoference during parent-child daily interaction acceptable and useful.

Association Between HEDIS Performance and Primary Care Physician Age, Group Affiliation, Training, and Participation in ACA Exchanges.

BACKGROUND: There are a limited number of studies investigating the relationship between primary care physician (PCP) characteristics and the quality of care they deliver. OBJECTIVE: To examine the association between PCP performance and physician age, solo versus group affiliation, training, and participation in California's Affordable Care Act (ACA) exchange. DESIGN: Observational study of 2013-2014 data from Healthcare Effectiveness Data and Information Set (HEDIS) measures and select physician characteristics. PARTICIPANTS: PCPs in California HMO and PPO practices (n = 5053) with part of their patient panel covered by a large commercial health insurance company. MAIN MEASURES: Hemoglobin A1c testing; medical attention nephropathy; appropriate treatment hypertension (ACE/ARB); breast cancer screening; proportion days covered by statins; monitoring ACE/ARBs; monitoring diuretics. A composite performance measure also was constructed. KEY RESULTS: For the average 35- versus 75-year-old PCP, regression-adjusted mean composite relative performance scores were at the 60th versus 47th percentile (89% vs. 86% composite absolute HEDIS scores; p < .001). For group versus solo PCPs, scores were at the 55th versus 50th percentiles (88% vs. 87% composite absolute HEDIS scores; p < .001). The effect of age on performance was greater for group versus solo PCPs. There was no association between scores and participation in ACA exchanges. CONCLUSIONS: The associations between population-based care performance measures and PCP age, solo versus group affiliation, training, and participation in ACA exchanges, while statistically significant in some cases, were small. Understanding how to help older PCPs excel equally well in group practice compared with younger PCPs may be a fruitful avenue of future research.

Exploring Care Attributes of Nephrologists Ranking Favorably on Measures of Value.

BACKGROUND: Despite growth in value-based payment, attributes of nephrology care associated with payer-defined value remains unexplored. METHODS: Using national health insurance claims data from private preferred provider organization plans, we ranked nephrology practices using total cost of care and a composite of common quality metrics. Blinded to practice rankings, we conducted site visits at four highly ranked and three average ranked practices to identify care attributes more frequently present in highly ranked practices. A panel of nephrologists used a modified Delphi method to score each distinguishing attribute on its potential to affect quality and cost of care and ease of transfer to other nephrology practices. RESULTS: Compared with average-value peers, high-value practices were located in areas with a relatively higher proportion of black and Hispanic patients and a lower proportion of patients aged >65 years. Mean risk-adjusted per capita monthly total spending was 24% lower for high-value practices. Twelve attributes comprising five general themes were observed more frequently in high-value nephrology practices: preventing near-term costly health crises, supporting patient self-care, maximizing effectiveness of office visits, selecting cost-effective diagnostic and treatment options, and developing infrastructure to support high-value care. The Delphi panel rated four attributes highly on effect and transferability: rapidly adjustable office visit frequency for unstable patients, close monitoring and management to preserve kidney function, early planning for vascular access, and education to support self-management at every contact. CONCLUSIONS: Findings from this small-scale exploratory study may serve as a starting point for nephrologists seeking to improve on payer-specified value measures.

Stress Disorders and Dementia in the Danish Population.

There is an association between stress and dementia. However, less is known about dementia among persons with varied stress responses and sex differences in these associations. We used this population-based cohort study to examine dementia among persons with a range of clinician-diagnosed stress disorders, as well as the interaction between stress disorders and sex in predicting dementia, in Denmark from 1995 to 2011. This study included Danes aged 40 years or older with a stress disorder diagnosis (n = 47,047) and a matched comparison cohort (n = 232,141) without a stress disorder diagnosis with data from 1995 through 2011. Diagnoses were culled from national registries. We used Cox proportional hazards regression to estimate associations between stress disorders and dementia. Risk of dementia was higher for persons with stress disorders than for persons without such diagnosis; adjusted hazard ratios ranged from 1.6 to 2.8. There was evidence of an interaction between sex and stress disorders in predicting dementia, with a higher rate of dementia among men with stress disorders except posttraumatic stress disorder, for which women had a higher rate. Results support existing evidence of an association between stress and dementia. This study contributes novel information regarding dementia risk across a range of stress responses, and interactions between stress disorders and sex.

Economic Benefit of "Modern" Nonemergency Medical Transportation That Utilizes Digital Transportation Networks.

OBJECTIVES: To determine the economic benefit of "modern" nonemergency medical transportation (NEMT) that utilizes digital transportation networks compared with traditional NEMT in the United States. METHODS: We used the National Academies' NEMT cost-effectiveness model to perform a baseline cost savings analysis for provision of NEMT for transportation-disadvantaged Medicaid beneficiaries. On the basis of a review of the literature, commercial information, and structured expert interviews, we performed a sensitivity analysis to determine the incremental economic benefit of using modern NEMT. We estimated confidence intervals (CIs) by using Monte Carlo simulation. RESULTS: Total annual net savings for traditional NEMT in Medicaid was approximately $4 billion. For modern NEMT, estimated savings on ride costs varied from 30% to 70%. In comparison with traditional, modern NEMT was estimated to save $268 per expected user (95% CI = $248, $288 per member per year) and $537 million annually (95% CI = $496 million, $577 million) when scaled nationally. CONCLUSIONS: Modern NEMT has the potential to yield greater cost savings than traditional NEMT while also improving patient experience. Public Health Implications: Barriers to NEMT are a health risk affecting high-need, economically disadvantaged patients. Economic arguments supporting modern NEMT are important given decreased support for human services spending.

Systems Delivery Innovation for Alzheimer Disease.

OBJECTIVE: The authors describe a comprehensive care model for Alzheimer disease (AD) that improves value within 1-3 years after implementation by leveraging targeted outpatient chronic care management, cognitively protective acute care, and timely caregiver support. METHODS: Using current best evidence, expert opinion, and macroeconomic modeling, the authors designed a comprehensive care model for AD that improves the quality of care while reducing total per capita healthcare spending by more than 15%. Cost savings were measured as reduced spending by payers. Cost estimates were derived from medical literature and national databases, including both public and private U.S. payers. All estimates reflect the value in 2015 dollars using a consumer price index inflation calculator. Outcome estimates were determined at year 2, accounting for implementation and steady-state intervention costs. RESULTS: After accounting for implementation and recurring operating costs of approximately $9.5 billion, estimated net cost savings of between $13 and $41 billion can be accomplished concurrently with improvements in quality and experience of coordinated chronic care ($0.01-$6.8 billion), cognitively protective acute care ($8.7-$26.6 billion), timely caregiver support ($4.3-$7.5 billion), and caregiver efficiency ($4.1-$7.2 billion). CONCLUSION: A high-value care model for AD may improve the experience of patients with AD while significantly lowering costs.

Contributions of Health Care to Longevity: A Review of 4 Estimation Methods.

PURPOSE: Health care expenditures and biomedical research funding are often justified by the belief that modern health care powerfully improves life expectancy in wealthy countries. We examined 4 different methods of estimating the effect of health care on health outcomes. METHODS: We reviewed the contributions of medical care to health outcomes using 4 methods: (1) analyses by McGinnis and Schroeder, (2) Wennberg and colleagues' studies of small area variation, (3) Park and colleagues' analysis of County Health Rankings and Roadmaps, and (4) the RAND Health Insurance Experiment. RESULTS: The 4 methods, using different data sets, produced estimates ranging from 0% to 17% of premature mortality attributable to deficiencies in health care access or delivery. Estimates of the effect of behavioral factors ranged from 16% to 65%. CONCLUSIONS: The results converge to suggest that restricted access to medical care accounts for about 10% of premature death or other undesirable health outcomes. Health care has modest effects on the extension of US life expectancy, while behavioral and social determinants may have larger effects.

The Association of ICU Acuity With Outcomes of Patients at Low Risk of Dying.

OBJECTIVE: Many ICU patients do not require critical care interventions. Whether aggressive care environments increase risks to low-acuity patients is unknown. We evaluated whether ICU acuity was associated with outcomes of low mortality-risk patients. We hypothesized that admission to high-acuity ICUs would be associated with worse outcomes. This hypothesis was based on two possibilities: 1) high-acuity ICUs may have a culture of aggressive therapy that could lead to potentially avoidable complications and 2) high-acuity ICUs may focus attention toward the many sicker patients and away from the fewer low-risk patients. DESIGN: Retrospective cohort study. SETTING: Three hundred twenty-two ICUs in 199 hospitals in the Philips eICU database between 2010 and 2015. PATIENTS: Adult ICU patients at low risk of dying, defined as an Acute Physiology and Chronic Health Evaluation-IVa-predicted mortality of 3% or less. EXPOSURE: ICU acuity, defined as the mean Acute Physiology and Chronic Health Evaluation IVa score of all admitted patients in a calendar year, stratified into quartiles. MEASUREMENTS AND MAIN RESULTS: We used generalized estimating equations to test whether ICU acuity is independently associated with a primary outcome of ICU length of stay and secondary outcomes of hospital length of stay, hospital mortality, and discharge destination. The study included 381,997 low-risk patients. Mean ICU and hospital length of stay were 1.8 ± 2.1 and 5.2 ± 5.0 days, respectively. Mean Acute Physiology and Chronic Health Evaluation IVa-predicted hospital mortality was 1.6% ± 0.8%; actual hospital mortality was 0.7%. In adjusted analyses, admission to low-acuity ICUs was associated with worse outcomes compared with higher-acuity ICUs. Specifically, compared with the highest-acuity quartile, ICU length of stay in low-acuity ICUs was increased by 0.24 days; in medium-acuity ICUs by 0.16 days; and in high-acuity ICUs by 0.09 days (all p < 0.001). Similar patterns existed for hospital length of stay. Patients in lower-acuity ICUs had significantly higher hospital mortality (odds ratio, 1.28 [95% CI, 1.10-1.49] for low-; 1.24 [95% CI, 1.07-1.42] for medium-, and 1.14 [95% CI, 0.99-1.31] for high-acuity ICUs) and lower likelihood of discharge home (odds ratio, 0.86 [95% CI, 0.82-0.90] for low-, 0.88 [95% CI, 0.85-0.92] for medium-, and 0.95 [95% CI, 0.92-0.99] for high-acuity ICUs). CONCLUSIONS: Admission to high-acuity ICUs is associated with better outcomes among low mortality-risk patients. Future research should aim to understand factors that confer benefit to patients with different risk profiles.

Identifying Distinct Subgroups of ICU Patients: A Machine Learning Approach.

OBJECTIVES: Identifying subgroups of ICU patients with similar clinical needs and trajectories may provide a framework for more efficient ICU care through the design of care platforms tailored around patients' shared needs. However, objective methods for identifying these ICU patient subgroups are lacking. We used a machine learning approach to empirically identify ICU patient subgroups through clustering analysis and evaluate whether these groups might represent appropriate targets for care redesign efforts. DESIGN: We performed clustering analysis using data from patients' hospital stays to retrospectively identify patient subgroups from a large, heterogeneous ICU population. SETTING: Kaiser Permanente Northern California, a healthcare delivery system serving 3.9 million members. PATIENTS: ICU patients 18 years old or older with an ICU admission between January 1, 2012, and December 31, 2012, at one of 21 Kaiser Permanente Northern California hospitals. INTERVENTIONS: None. MEASUREMENTS AND MAIN RESULTS: We used clustering analysis to identify putative clusters among 5,000 patients randomly selected from 24,884 ICU patients. To assess cluster validity, we evaluated the distribution and frequency of patient characteristics and the need for invasive therapies. We then applied a classifier built from the sample cohort to the remaining 19,884 patients to compare the derivation and validation clusters. Clustering analysis successfully identified six clinically recognizable subgroups that differed significantly in all baseline characteristics and clinical trajectories, despite sharing common diagnoses. In the validation cohort, the proportion of patients assigned to each cluster was similar and demonstrated significant differences across clusters for all variables. CONCLUSIONS: A machine learning approach revealed important differences between empirically derived subgroups of ICU patients that are not typically revealed by admitting diagnosis or severity of illness alone. Similar data-driven approaches may provide a framework for future organizational innovations in ICU care tailored around patients' shared needs.

Achieving higher-value obstetrical care.

Obstetrical care in the United States is unnecessarily costly. Birth is 1 of the most common reasons for healthcare use in the United States and 1 of the top expenditures for payers every year. However, compared with other Organization for Economic Cooperation and Development countries, the United States spends substantially more money per birth without better outcomes. Our team at the Clinical Excellence Research Center, a center that is focused on improving value in healthcare, spent a year studying ways in which obstetrical care in the United States can deliver better outcomes at a lower cost. After a thoughtful discovery process, we identified ways that obstetrical care could be delivered with higher value. In this article, we recommend 3 redesign steps that foster the delivery of higher-value maternity care: (1) to provide long-acting reversible contraception immediately after birth, (2) to tailor prenatal care according to women's unique medical and psychosocial needs by offering more efficient models such as fewer in-person visits or group care, and (3) to create hospital-affiliated integrated outpatient birth centers as the planned place of birth for low-risk women. For each step, we discuss the redesign concept, current barriers and implementation solutions, and our estimation of potential cost-savings to the United States at scale. We estimate that, if this model were adopted nationally, annual US healthcare spending on obstetrical care would decline by as much as 28%.

Exploring Attributes of High-Value Primary Care.

PURPOSE: Medicare's merit-based incentive payment system and narrowing of physician networks by health insurers will stoke clinicians' and policy makers' interest in care delivery attributes associated with value as defined by payers. METHODS: To help define these attributes, we analyzed 2009 to 2011 commercial health insurance claims data for more than 40 million preferred provider organization patients attributed to over 53,000 primary care practice sites. We identified sites ranking favorably on both quality and low total annual per capita health care spending ("high-value") and sites ranking near the median ("average-value"). Sites were selected for qualitative assessment from 64 high-value sites and 102 average-value sites with more than 1 primary care physician who delivered adult primary care and provided services to enough enrollees to permit meaningful spending and quality ranking. Purposeful sampling ensured regional diversity. Physicians experienced in primary care assessment and blinded to site rankings visited 12 high-value sites and 4 average-value sites to identify tangible attributes of care delivery that could plausibly explain a high ranking on value. RESULTS: Thirteen attributes of care delivery distinguished sites in the high-value cohort. Six attributes attained statistical significance: decision support for evidence-based medicine, risk-stratified care management, careful selection of specialists, coordination of care, standing orders and protocols, and balanced physician compensation. CONCLUSIONS: Awareness of care delivery attributes that distinguish their high-value peers may help physicians respond successfully to incentives from Medicare and private payers to lower annual health care spending and improve quality of care.