Improving hospital layout planning through clinical pathway mining

Abstract

Clinical pathways (CPs) are standardized, typically evidence-based health care processes. They define the set and sequence of procedures such as diagnostics, surgical and therapy activities applied to patients. This study examines the value of data-driven CP mining for strategic healthcare management. When assigning specialties to locations within hospitals-for new hospital buildings or reconstruction works-the future CPs should be known to effectively minimize distances traveled by patients. The challenge is to dovetail the prediction of uncertain CPs with hospital layout planning. We approach this problem in three stages: In the first stage, we extend a machine learning algorithm based on probabilistic finite state automata (PFSA) to learn significant CPs from data captured in hospital information systems. In that stage, each significant CP is associated with a transition probability. A unique feature of our approach is that we can generalize the data and include those CPs which have not been observed in the data but which are likely to be followed by future patients according to the pathway probabilities obtained from the PFSA. At the same time, rare and non-significant CPs are filtered out. In the second stage, we present a mathematical model that allows us to perform hospital layout planning decisions based on the CPs, their probabilities and expert knowledge. In the third stage, we evaluate our approach based on different performance measures. Our case study results based on real-world hospital data reveal that using our CP mining approach, distances traveled by patients can be reduced substantially as compared to using a baseline method. In a second case study, when using our approach for reconstructing a hospital and incorporating expert knowledge into the planning, existing layouts can be improved. B Daniel Gartner

Improving patient timeliness of care through efficient outpatient clinic layout design using data-driven simulation and optimisation

“…Research on layout problems originally focused on organising manufacturing units to improve performance of workers by reducing walking distances. However, in the last two decades, research on layout problems has been extended to include the design of spaces in service sectors such as airport terminals (Edwards, 2004;Manataki & Zografos, 2009), train and railway stations (Li, 2000), shipyards and ports (Bruzzone & Signorile, 1998), retail stores (Levy, Weitz, & Grewal, 2012), online web services (Wu, Lee, Fu, & Wang, 2013), and healthcare facilities (Arnolds & Gartner, 2018;Chraibi, Osman, & Kharraja, 2018). In general, layout design in healthcare has been characterised by the scale of the design problem, either "macro-level design" or "micro-level design" (Arnolds & Nickel, 2015).…”

Clinical pathway modelling: a literature review

“…They also state that 'Although we will not explicitly model it, patient need not be present for each of the activities (consider e.g. lab tests).. • Arnolds and Gartner [8] is categorised as 'Hospital', as they focus on improving hospital layout planning by using clinical pathway mining. Figure 9 displays the frequency of papers in each scope category.…”

“…JCR Category MI [3, 11, 13, 14, 16, 17, 19, 32, 37, 42, 45-47, 52, 54, 56, 57, 66, 72, 73, 1-93, 95-97, 99-101, 108, 122, 124, 131, 140, 144, 149, 150, 157, 160, 164, 170, 178, 187, 196, 197, 206, 211] OR/MS [7,8,12,18,22,23,27,30,31,43,50,51,64,75,79,90,113,114,134,151,158,165,169,190,203,212] HPS [9, 10, 21, 33, 39, 40, 80, 102-104, 110, 116, 141, 143, 153, 163, 166, 209] IE [34,120] AN [53,133] No ISSN [15,24,36,60,70,71,82,127,138,139,142,161,183,[198][199][200] Table A4. Way in which information about the pathway was obtained.…”

“…Multiple Methods Two [8,11,12,18,54,74,76,99,108,140,151,162,167,179,190,203] Three [7,211] Table A11. Investigating type.…”

“…Investigating Type Mapping (Ma) [1, 4, 5, 7, 22, 29, 33, 37, 42, 47, 48, 54, 56, 57, 70, 71, 81, 83, 87, 88, 90, 91, 94-99, 104, 112, 121, 126, 127, 131, 136, 138, 139, 144, 149, 154, 157, 161, 162, 164, 170, 172, 177-179, 183-185, 192, 195, 197-203, 206, 209-211] Modelling (Mo) [15, 19-21, 23, 24, 30, 31, 36, 39, 43, 50, 55, 58, 64, 67, 76, 79, 82, 86, 89, 102, 103, 115, 117-119, 122, 129, 145-147, 150, 151, 160, 169, 171, 187, 188, 190, 191, 196, 212] Improving (I) [13,46] Ma & Mo [3, 9, 11, 17, 18, 40, 60, 62, 66, 72-74, 80, 85, 90, 93, 101, 107, 108, 114, 120, 124, 125, 128, 133, 134, 140, 143, 158, 205] Mo & I [8,16,25,32,34,41,45,52,53,68,75,110,111,113,116,141,148,165,182] All Types [10,12,14,27,35,49,51,100,142,152,153,163,166,167,186,204] Table A12. Outcome focus of the pathway.…”