Hand Hygiene Compliance Sensor

Michael T. Lash∗Ms, Jason Slater† Bs,

Philip M. Polgreen‡ MD MPH, and Alberto Maria Segre∗PhD Abstract—This large-scale study, consisting of 24.5 million hand hygiene opportunities spanning 19 distinct facilities in 10 different states, uses linear predictive models to expose factors that may affect hand hygiene compliance. We examine the use of features such as temperature, relative humidity, influenza severity, day/night shift, federal holidays and the presence of new residents in predicting daily hand hygiene compliance. The results suggest that colder temperatures and federal holidays have an adverse effect on hand hygiene compliance rates, and that individual cultures and attitudes regarding hand hygiene exist among facilities.

Index Terms—Public healthcare, Hand hygiene, Supervised

I. Introduction

Healthcare associated infections represent a major cause of morbidity and mortality in the United States and other countries . Although many can be treated, these infections add greatly to healthcare costs . Furthermore, the emer- gence of multidrug resistant bacteria have greatly complicated treatment of healthcare associated infections , making the prevention of these infections even more important. One of the most effective interventions for preventing healthcare associ- ated infections is hand hygiene . Yet, despite international programs aimed at increasing hand hygiene , , , rates remain low, less than 50% in most cases , , .

Because of the importance of hand hygiene in preventing healthcare associated infections, infection control programs are encouraged to monitor rates to encourage process im-

Provement , , . In Most Cases, Hand Hygiene Mon-

itoring is done exclusively by human observers, which are still considered the gold standard for monitoring . Yet, human observations are subject to a number of limitations.

For example, human observers incur high costs and there are difficulties in standardizing the elicited observations. Also, the timing and location of observers can greatly affect the diversity and the quantity of observations , . Furthermore, the distance of observers to healthcare workers under observation and the relative busyness of clinical units can adversely affect the accuracy of human observers . The presence of human observers may artificially increase hand hygiene rates tem- porarily as the presence of other healthcare workers can induce peer effects to increase rates , . Finally, the number of human observations possible is quite small in comparison to the number of opportunities , . Several automated

Approaches To Monitoring Have Been Proposed , , ,

. Many of these measure hand hygiene upon entering and leaving a patient’s room. The subsequent activation of a nearby hand hygiene dispenser is recorded as a hand hygiene opportunity fulfilled whereas, if no such activation is observed, the opportunity is not satisfied. Such approaches, while not capturing all five moments of hand hygiene, do provide an easy and convenient measure of hand hygiene compliance.

With automated approaches becoming more common, a more comprehensive picture of hand hygiene adherence should emerge, providing new insights into why healthcare workers abstain from practicing hand hygiene.

A. Hand Hygiene Event Data

Our hand hygiene event data is a proprietary dataset pro- vided by Gojo Industries. The data were obtained from a number of installations consisting of door counter sensors, which increment a counter anytime an individual goes in or out of a room, and hand hygiene sensors, which increment a counter when soap or alcohol rub are dispensed. Additional supporting technology was also installed to collect and record timestamped sensor-reported counts. In this paper, we will use the term dispenser event to designate triggering and use of an instrumented hand hygiene dispenser and door event to designate the triggering of a counter sensor located on one of the instrumented doors.

A total of 19 facilities in 10 states were outfitted with sensors; because of privacy concerns, we provide only the state and CDC Division for each. The facilities comprise a wide range of geographies, spanning both coasts, the midwest, and the south. A total of 1851 door sensors and 639 dispenser sen- sors reported a total of 24,525,806 door events and 6,140,067

Arxiv:1705.03540V2 [Cs.Cy] 7 Jul 2017

dispenser events, beginning on October 21, 2013 and ending on July 7, 2014. Each facility contributed an average of 172.3 reporting days, making this study the largest investigation of hand hygiene compliance to date (i.e., larger than the 13.1 million opportunities reported in ). Assuming each door event corresponds to a hand hygiene opportunity, we compute an estimated intra-facility compliance rate of 25.03%, in line with if not just below the reported low-end rate found in .

The original data, consisting of timestamped counts reported from individual sensors over short intervals, were re-factored to support our analysis. First, data from each sensor were binned by timestamp, t, into 12 hour intervals, corresponding to traditional day and night shifts, as indicated by an additional

T Ε [7Am, 6:59Pm]

Second, door and dispenser counts were aggregated based on day and night shift so as to produce a series of records. For each such record we compute hand hygiene compliance, or just compliance, by dividing the number of reported dispensed

# Door

Such a definition of compliance assumes that each door event corresponds to a single hand-hygiene opportunity and each dispenser event corresponds to a single hand-hygiene event whereas, in reality, a health care worker might well be expected to perform hand hygiene more than once per entry, resulting in rates that exceed one, if only slightly. This estimator also ignores the placement of doors with respect to dispensers: multiple dispensers may well be associated with a single doorway, and some dispensers may be in rooms having multiple doors. Adding new dispensers will raise apparent compliance rates, while adding new door sensors will appear to reduce compliance. Even so, when applied consistently and if system layouts are fixed, this estimator is a reasonable approximation of true hand hygiene compliance, and supports sound comparisons within a facility (but not across facilities).

Because malfunctioning sensors or dead batteries can pro- duce outliers (i.e., very low or very high values), records with fewer than 10 door or dispenser events reported per day (possibly indicating an installation undergoing maintenance), zero compliance, or compliance values greater than 1 were removed prior to analysis (at the cost of possibly excluding some legal records). The remaining data consists of 5308 shifts from the original 5647 records, having 21,273,980 hand hygiene opportunities and 5,296,749 hand hygiene events (see Table I).

B. Feature Definitions

In this subsection we define the features (factors) that will be examined, and how each is derived.

3274

TABLE I: Descriptive statistics for all reporting facilities in terms of state, CDC division, hand hygiene events, people events, and reporting days.

1) Local Weather Data: Because health care workers fre- quently cite skin dryness and irritation as a factor in decreased compliance (particularly in cold weather months where en- vironmental humidity is reduced), we associate daily air temperature and relative humidity to each timestamped record based on each facility’s reported zip code. Spatially assimilated weather values (σ = 0.995) for the entire globe were obtained from the National Oceanic and Atmospheric Administration (NOAA) . Given in terms of grid elements (a tessilation

◦Longitude),

the world is thus defined as a 144 by 73 grid having 10512 distinct grid elements. Weather data are available at a fine level Fig. 1: Assigning (red box) NOAA weather data, reported in terms of a geographic grid, to health care facilities (red dots), where the blue color gradient might represent temperature.

of temporal granularity (on the order of 4 times daily for each grid unit) for the entire period of interest. The geographical assignment of weather data was obtained by first mapping each facility’s numerical zipcode to the zipcode’s centroid (2010 US Census data), given by (latitude,longitude), which was subsequently mapped to the matching NOAA grid element.

An example of this assignment can be observed in Figure 1. We associate weather information from the 6am reporting hour with records corresponding to traditional day shifts (7am- 6:59pm) and use the 6pm reporting hour for traditional night shifts (7pm-6:59am).

2) Influenza Severity: We conjecture that the local severity of common seasonal diseases, such as influenza, may also affect hand hygiene compliance rates. We define influenza severity as the number of influenza-related deaths relative to all deaths over a specified time interval.

Influenza severity data were obtained from the CDC’s Morbidity and Mortality Weekly Report (MMWR), which also reports data at weekly temporal granularity. Rather than reporting data by CDC region, however, data are provided by reporting city (one of 122 participating cities, mostly large metropolitan areas). We map each facility in our dataset to the closest reporting city in order to associate the appropriate

Severity Value To Each Record. In Other Words

repCity = argmin{dist(facility, cityi) : i = 1, . . . , 122} where dist(fac, city) ≜∥(faclat, faclon), (citylat, citylon)∥2, the Euclidean distance between two entities given in terms of (lat, lon) coordinates. Eight of 19 facilities were located in a reporting city (i.e., dist= 0). The remaining 11 facilities were mapped to a reporting city that was, on average, 66.2 miles away (only 3 of 19 facilities were mapped to a reporting city further than this average, with the largest distance being 142 miles).

3) Temporal Factors: We also conjecture that external factors associated with specific holidays or events may affect hand hygiene compliance rates. Holidays may change staffing rates or affect healthcare worker behaviors in various ways.

The number of visitors (affecting door counter rates) may also be greater than during regular weekdays. Holidays such as the 4th of July are often associated with alcohol-related accidents, and may increase health care facility workloads. Such factors may also be observable during weekends.

We define a new variable holiday that reflects whether a given shift occurs on one of the 10 federal holidays (New Year’s Eve, Martin Luther King Day, President’s Day, Memo- rial Day, the 4th of July, Labor Day, Columbus Day, Veteran’s

T ∈{Holidays}

Similarly, in order to ascertain the impact of weekends on compliance, we define a new variable weekday as follows:

T ∈{Mon, Tues, Weds, Thurs, Fri}

A related concept is the presence of new resident physicians, who traditionally start work the first of July. We define a new variable that corresponds with this time period in order to see

C. Exploring Factors Affecting Hand Hygiene

1) M5 Ridge Regression for Feature Examination: With covariates defined and associated with the collected sensor data, we wish to build a linear hypothesis h that (a) accurately estimates hand hygiene and (b) reports the direction and degree of effect of our defined features.

In Accomplishing (B) We Bear In Mind Two Things:

(1) There may be multi-collinearity among features, which may adversely affect the output. (2) That (a) and (b) may be at odds with one another; i.e., obtaining good predictions may entail discarding some prediction-inhibiting features for which we would like to obtain effect estimates (in practice, we find that this is not actually the case).

Therefore, we propose an M5 Ridge Regression for Feature Examination method designed to accomplish (a) and (b), while bearing (1) and (2) in mind. This method is given by

2

s.t.

(1)

where X ∈Rn×p is a design matrix, h is the hypothesis, y is the target vector consisting of compliance rates in which a particular yi ∈[0, 1], λ is a regularization term, ∥·∥2 is the ℓ2-norm, and ρ(·) is a function that reports the p- value of a hypothesis term (this constraint is ensured via sequential backwards elimination ). The function Λ(X)

(2)

where t is hypothesis selected from a tree of hypotheses constructed using the M5 method . Effectively, (2) only reduces the p dimension, acting as a feature selection method, and having no bearing on the n dimension.

There are a few benefits of the above method worth pointing out. First, the hypothesis class Hl is linear and common to both (1) and (2). Two-stage optimization approaches, where the first objective is optimized, taking into account the hypothesis class, before the hypothesis itself is optimized for predictive accuracy (or some other such measure), have been shown to work well . Secondly, such a method is specifically geared toward producing a hypothesis that makes use of features that have an immediate bearing upon the problem, while eliminating interpretability obscuring effects, such as multi- collinearity. Moreover, these desirables are obtained while attempting to produce the most accurate hypothesis: an h that elicits feature indicativeness, produces accurate results, and controls for confounding effects is the goal of this two-step optimization procedure.

Ultimately, we conduct our analysis by observing the sign and magnitude of the values in the hypothesis vector in order to determine the factors that influence hand hygiene compli- ance, and whether such factors affect compliance in a positive or negative manner. We also observe correlation and RMSE values to determine how well our predictive model works, and whether the corresponding results can be trusted. All results and are obtained via k-fold cross-validation (k = 10).

We Also Use Two Estab-

lished/standard techniques – RReliefF feature ranking and marginal effects modeling – that will serve as a point of comparison between our method, and also help inform the discussion of the obtained results1.

Feature ranking: First, we propose the use of the RReliefF algorithm , a modification of the original Relief algorithm of Kira and Rendell . RReliefF finds a feature j’s weight by randomly selecting a seed instance xi from design matrix X and then using that instance’s k nearest neighbors to update the attribute. This description consists of three terms: the probability of observing a different rate of hand hygiene compliance than that of the current value given that of the

(3)

the probability of observing the current attribute value given

(4)

and the probability of observing a different hand hygiene rate than the current value given a different feature value v and the

Nearest Neighbors, Given By

C = p(rate̸ = ratexi,j|kNN(xi,j) ∧j = v).

(5)

Attribute distance weighting is used in order to place greater emphasis on instances that are closer to the seed instance when updating each term; final weights are obtained by applying Bayes’ rule to the three terms maintained for each attribute,

1 −A

.

(6)

By using this method we could then rank attributes in terms of their importance. We again report rankings using k-fold (k = 10) cross validation.

Marginal Effects Modeling: To provide additional insight into the features that are relevant to hand hygiene we analyzed 1Note that both the LASSO and Elastic Net would have also made appropriate supporting methods.

their marginal effects . Marginal effects, also referred to as instantaneous rates of change, are computed by first training a hypothesis h, then, using the testing data, the effect of each covariate can be estimated by holding all others constant and observing the predictions. Such a method can be expressed by

(7)

where, with a slight abuse of notation, xi,j, the value of instance i’s jth feature, is added to the vector ¯x̸=j, which consists of the average of each non-j feature, at the appropriate location (namely, the jth position). Here, the notation̸ = j is used to reinforce the fact that the vector of averages ¯x has it’s jth element replaced by xi,j. Other non-j entries are given by ¯xk = µ(Xk), for an arbitrary index position k.

A. Predictive Power: M5 Ridge Regression

We learned a hypothesis using all available features, in- cluding a nominalized facility identifier. Our predictive results can be observed in Table II. We note that the RMSE is not large and the correlation is moderate, implying relatively good predictive performance.

0.1702

TABLE II: Correlation coefficient and RMSE of cross- validated model predictions.

B. Examining Hypothesis H∗

We next examine the terms of the learned hypothesis h∗ (see Table III). The model includes all 19 facilities, 12 of which had positive values, indicating relatively higher rates of compliance. The size remaining facility’s h∗terms had relatively small negative values, indicating lower rates of com- pliance. Among other features, holidays are associated with lower compliance rates, while influenza severity has higher compliance. Weekdays are associated with higher compliance rates, as are higher temperatures and humidity. Interestingly, the M5 Ridge Regression model appears to have eliminated

−0.0106

TABLE III: Feature specific hj terms, where red highlights features with a negative association and blue highlights those with a positive association.

Related Journal Articles & DOI Links

Selected peer-reviewed publications relevant to 12 Lead ECG Acquisition. Click the DOI to access the full paper (may require institutional access).

Why Choose Us?

Bangalore guidance for robotics, Spectre and autonomous systems projects.