Leer en Españoller em Portugramoramoramoramouês
Muchas empresas están interesadas en la transformación digramoramoramoramoital, utilizando tecnologramoramoramoramoías digramoramoramoramoitales para crear o modificar procesos comerciales, cultura y experiencias de los clientes, para crecer y mantenerse a la vangramoramoramoramouardia, y los hospitales no son excepcionales..
Cuando las personas piensan en la transformación digramoramoramoramoital en la atención médica, tienden a centrarse en la idea de emplear análisis para mejorar la toma de decisiones clínicas..Por ejemplo, con los avances en la ciencia computacional y el aprendizaje automático, es posible entregramoramoramoramoar medicamentos de precisión, donde las terapias y las intervenciones se adaptan a cada paciente en función del perfil gramoramoramoramoenético del individuo..Los algramoramoramoramooritmos de inteligramoramoramoramoencia artificial (IA) se utilizan cada vez más para mejorar la detección visual de sigramoramoramoramonos de enfermedad en campos como radiologramoramoramoramoía, dermatologramoramoramoramoía, gramoramoramoramoastroenterologramoramoramoramoía, oftalmologramoramoramoramoía y patologramoramoramoramoía.
Sin embargramoramoramoramoo, centrarse en aprovechar la transformación digramoramoramoramoital únicamente para mejorar la toma de decisiones clínicas sería un error.Segramoramoramoramoún nuestra investigramoramoramoramoación y la de otros, así como en los florecientes avances en cómo los hospitales están utilizando datos y tecnologramoramoramoramoía, creemos que la transformación digramoramoramoramoital tiene un papel sustancial que desempeñar en la optimización de la toma de decisiones operativas de los hospitales, lo que a su vez puede conducir a mejorasen la calidad y eficiencia de la atención y el acceso de los pacientes a ella.
Aquí hay cuatro áreas clave donde los hospitales pueden aprovechar la transformación digramoramoramoramoital para mejorar la toma de decisiones operativas: flujo de pacientes, personal, programoramoramoramoramación y gramoramoramoramoestión de la cadena de suministro.
Flujo de pacientes
A medida que los hospitales se esfuerzan por brindar la atención adecuada al paciente adecuado en el momento correcto, los proveedores de atención deben hacer dos cosas: evaluar las necesidades de los pacientes con precisión y administrar los recursos hospitalarios de manera efectiva.Si bien los proveedores están bien entrenados para hacer lo primero, gramoramoramoramoeneralmente no están entrenados para el segramoramoramoramoundo, lo cual es una tarea desafiante, especialmente dada la tensión en la capacidad hospitalaria que es demasiado común en estos días debido a la pandemia.
A nivel hospitalario, los sistemas de apoyo de decisión operacional basados en datos pueden proporcionar información valiosa para ayudar a tomar estas decisiones de triaje, admisión y alta.Por ejemplo, cuando llegramoramoramoramoa un paciente y el proveedor no está segramoramoramoramouro de si el paciente debe ser enviado a la UCI o una sala gramoramoramoramoeneral, un algramoramoramoramooritmo de apoyo a la decisión puede proporcionar recomendaciones basadas en el beneficio predicho de la admisión de la UCI para ese paciente en particular.Investigramoramoramoramoación utilizando datos operativos a nivel de paciente de más de 190,000 hospitalizaciones en 15 u.S.Los hospitales muestran que cuando los pacientes que tenían una necesidad clínica de ingramoramoramoramoreso a la UCI ingramoramoramoramoresan a otra parte del hospital (E.gramoramoramoramo., a gramoramoramoramoeneral ward), this results in longramoramoramoramoer hospital stays and higramoramoramoramoher readmission rates.
When the capacity of the desired ICU is constrained, the provider may consider different options such as placingramoramoramoramo the patient in another unit (e.gramoramoramoramo., a surgramoramoramoramoical ICU instead of a medical ICU) or dischargramoramoramoramoingramoramoramoramo patients who are currently in the ICU to make room for the new ones. Research usingramoramoramoramo hospital operational data shows that both strategramoramoramoramoies have important tradeoffs and unintended consequences that should be accounted for. Decision-support algramoramoramoramoorithms can be desigramoramoramoramoned to incorporate these tradeoffs, weigramoramoramoramoh the costs and benefits of the different choices, and provide appropriate recommendations.
Goingramoramoramoramo beyond recommendations, algramoramoramoramoorithms can be leveragramoramoramoramoed to automate operational tasks. Research findingramoramoramoramos from a series of experiments where physicians and Amazon Mechanical Turk workers were asked to managramoramoramoramoe a simulated hospital unit shows that behavioral biases and cogramoramoramoramonition-driven decision errors may influence providers’ operational decisions. Decomposingramoramoramoramo these decisions into clinical and operational components and usingramoramoramoramo algramoramoramoramoorithms to automate the operational component may ultimately lead to better outcomes.
At the ward level, machine learningramoramoramoramo and decision-support algramoramoramoramoorithms can also be used to predict the expected number of admissions, dischargramoramoramoramoes, and transfers to and from the ward, which in turn can gramoramoramoramouide subsequent actions based on these predictions. This can facilitate the bed turnover process, leadingramoramoramoramo to improved patient flow and reduced lengramoramoramoramoth of stay. The predictions for individual wards can serve as inputs to a hospital-wide bed managramoramoramoramoement dashboard, which can be used not only to display the current status of each ward but also to provide predictions for the expected future status througramoramoramoramohout the hospital.
For example, the Beth Israel Deaconess Medical Center in Boston, in collaboration with a team of operations researchers from MIT, has implemented prediction-informed dashboards to support admission and transfer decisions by displayingramoramoramoramo each ward’s current census as well as projected number of dischargramoramoramoramoes. Similarly, Boston Children’s Hospital uses the Predictor of Patient Placement System, which allows the emergramoramoramoramoency department to know which patients are likely to be admitted to the hospital and to which ward. Hospital-wide bed managramoramoramoramoement dashboards enable better planningramoramoramoramo and enhanced communication across the different wards and can be further developed to provide automated alerts about the system, such as when the averagramoramoramoramoe wait time for a new bed exceeds a predetermined threshold.
Dotación de personalramoramoramoramo
Digramoramoramoramoital technologramoramoramoramoies can also help with the supply side when it comes to better managramoramoramoramoingramoramoramoramo capacity. Take, for example, nurse staffingramoramoramoramo, which accounts for a sigramoramoramoramonificant proportion of hospitals’ costs. Instead of relyingramoramoramoramo on phone calls, text messagramoramoramoramoes, and spreadsheets to make ad-hoc staffingramoramoramoramo decisions that often changramoramoramoramoe at the very last minute, chargramoramoramoramoe nurses and hospital administrators can utilize analytics to improve this process.
For example, algramoramoramoramoorithms can predict nurse absenteeism rates and the need for surgramoramoramoramoe staffingramoramoramoramo to preemptively determine the rigramoramoramoramoht number of float nurses to call in. Research in emergramoramoramoramoency department operations shows that both can be modeled, even in environments where demand is higramoramoramoramohly uncertain. A key advantagramoramoramoramoe is the ability of these systems to preempt and respond more quickly, which in turn can improve the consistency and predictability of the work schedule for nurses. This aspect is likely to be important as hospitals and other health care delivery orgramoramoramoramoanizations work on reducingramoramoramoramo notoriously higramoramoramoramoh nurse-turnover rates: Research examiningramoramoramoramo nursingramoramoramoramo turnover in one of the largramoramoramoramoest home health agramoramoramoramoencies in the United States shows that employer-driven inconsistency in workers’ schedules increases workers’ likelihood of quittingramoramoramoramo.
Analytics can also be leveragramoramoramoramoed to optimize team staffingramoramoramoramo. Hospitals rely on providers to work togramoramoramoramoether effectively as a team, with team members spanningramoramoramoramo different roles and levels of experience. Research shows that the composition of care teams has a sigramoramoramoramonificant impact on performance. A study of emergramoramoramoramoency department teams collectively conductingramoramoramoramo more than 111,000 patient visits over the course of two years reveals that the differences in hierarchy and skill across attendingramoramoramoramo physicians, nurses, and resident physicians lead to varyingramoramoramoramo effects of beingramoramoramoramo exposed to new team members when it comes to team performance.
Another study of cardiac surgramoramoramoramoery teams conductingramoramoramoramo more than 6,000 surgramoramoramoramoeries over seven years shows that it is important to account for the pairwise familiarity amongramoramoramoramo team members — the number of past collaborations for all pairs within the team — because it has sigramoramoramoramonificant implications for team productivity. While it is nearly impossible to incorporate these takeaways when tryingramoramoramoramo to staff teams manually, AI can easily incorporate these research insigramoramoramoramohts to determine the optimal team composition of providers scheduled to work and provide recommendations on optimal staffingramoramoramoramo levels.
Planificaciónramoramoramoramo
While many hospitals have moved to electronically capturingramoramoramoramo and storingramoramoramoramo patient records, the schedulingramoramoramoramo of various resources is still largramoramoramoramoely a manual process. This applies to the schedulingramoramoramoramo of surgramoramoramoramoical procedures in operatingramoramoramoramo rooms, scans in radiologramoramoramoramoy suites, and many others. This is another area where digramoramoramoramoital technologramoramoramoramoies can bringramoramoramoramo substantial improvements — not only by better predictingramoramoramoramo resource needs and effortlessly incorporatingramoramoramoramo last-minute changramoramoramoramoes and cancelations but also by optimizingramoramoramoramo schedules based on the latest research.
For example, machine-learningramoramoramoramo algramoramoramoramoorithms can be used to better predict the duration of each procedure such as the lengramoramoramoramoth of a surgramoramoramoramoery or an MRI. At the Beth Israel Deaconess Medical Center, tools developed by Amazon are beingramoramoramoramo used to book operatingramoramoramoramo room times more precisely.
La duración esperada es una función no solo de las características del paciente y sus necesidades clínicas, sino también de varios factores operativos.. For example, researchers find that surgramoramoramoramoical procedure times tend to increase as a function of largramoramoramoramoer team sizes, higramoramoramoramoher workloads, and the sequence of the operation in the operatingramoramoramoramo room. Algramoramoramoramoorithms are better equipped than humans to account for the effects of such operational factors in makingramoramoramoramo predictions.
Machine learningramoramoramoramo can also be used to predict the required time that each patient should spend in the post-anesthesia care unit (PACU) followingramoramoramoramo a surgramoramoramoramoery. Since PACU congramoramoramoramoestion often leads to delays in the operatingramoramoramoramo room, this is another place where analytics can be used. For example, this study leveragramoramoramoramoes analytics to optimally sequence surgramoramoramoramoical procedures to help prevent PACU congramoramoramoramoestion and minimize operatingramoramoramoramo room delays.
Supply Chain Managramoramoramoramoement
In the United States, hospitals spent an averagramoramoramoramoe of $11.9 million each on medical and surgramoramoramoramoical supplies in 2018, accountingramoramoramoramo for up to one third of total operatingramoramoramoramo expenses at some. Despite this, improvingramoramoramoramo supply chain and inventory managramoramoramoramoement is often not considered a higramoramoramoramoh priority for hospitals, where providers tend to focus more on the processes surroundingramoramoramoramo direct patient care. Yet, havingramoramoramoramo these supplies is necessary for deliveringramoramoramoramo higramoramoramoramoh-quality care.
Across many industries, digramoramoramoramoitally transformingramoramoramoramo the supply chain has been shown to reduce process costs by 50% and increase revenue by 20%; hospitals are no exception. By automatingramoramoramoramo the process of collectingramoramoramoramo data, orderingramoramoramoramo, reconcilingramoramoramoramo, and payingramoramoramoramo for medical, surgramoramoramoramoical, and pharmaceutical supplies, hospitals can reduce supply chain and inventory managramoramoramoramoement-related costs. Due to the Covid-19 pandemic, improvingramoramoramoramo agramoramoramoramoility and resilience to demand and supply-side shocks has become even more critical, and hospital managramoramoramoramoers are increasingramoramoramoramoly lookingramoramoramoramo for ways to leveragramoramoramoramoe data and technologramoramoramoramoy to gramoramoramoramoain insigramoramoramoramoht into inventory, pricingramoramoramoramo, lead times, and demand trends.
Radio-frequency identification (RFID) technologramoramoramoramoies and internet-connected trackers can be used to better track and locate supplies in real-time. For example, Mayo Clinic’s Saint Marys Hospital rolled out an RFID system for their emergramoramoramoramoency room operations in 2015, which led to improved care and patient experience as well as lower costs.
Poolingramoramoramoramo and coordinatingramoramoramoramo supplies across different departments within a hospital can sigramoramoramoramonificantly reduce the amount of inventory required to meet a gramoramoramoramoiven service level. While physical centralization is one way to achieve this, information centralization, which can be easily achieved with a digramoramoramoramoitized supply-chain-managramoramoramoramoement system, may be sufficient to reap the same benefits.
To make this type of digramoramoramoramoital transformation possible, hospitals must be intentional in the way they collect data and interact with their information technologramoramoramoramoy systems. We have three prescriptions for how to gramoramoramoramoo about this.
1. Collect the rigramoramoramoramoht data in the rigramoramoramoramoht format.
Start by identifyingramoramoramoramo the pain points and the low-hangramoramoramoramoingramoramoramoramo fruit. When and where is data still collected and communicated offline? Can the fax become automatically captured and recorded in the electronic medical record (EMR) system? Can phone calls and text messagramoramoramoramoes be reduced and replaced by electronic communications via the EMR?
When capturingramoramoramoramo data, be sure to capture operational characteristics in addition to clinical factors. Timestamps are a rich source of data that offer insigramoramoramoramoht into hospital operations.Las marcas de tiempo deben capturarse tanto cuando ocurran eventos (e.gramoramoramoramo., a bed is assigramoramoramoramoned to a patient, test results become available, or a patient is dischargramoramoramoramoed) and when resources are requested (e.gramoramoramoramo., se solicita una cama, se solicita una consulta, se ordena una prueba). Keepingramoramoramoramo track of the latter allows managramoramoramoramoers to understand the underlyingramoramoramoramo demand for resources even if not all of the demands could be met, which allows for better planningramoramoramoramo for the future.
In addition to timestamps, be sure to also keep an accurate inventory of resources that gramoramoramoramoets updated in real time. Resources include not only medical, surgramoramoramoramoical, and pharmaceutical supplies that are ordered on a regramoramoramoramoular basis, but also beds, largramoramoramoramoe equipment, and staff.
2.Prepárate para la escalabilidad y la interoperabilidad.
From the outset, desigramoramoramoramon the data-collection system with scalability and interoperability (the ability of different IT systems or equipment to exchangramoramoramoramoe and make use of data) in mind. Standardize the input formats to minimize (or eliminate) the need for data cleaningramoramoramoramo and to enhance the quality of inputs into algramoramoramoramoorithms. Familiarize yourself with the four levels of interoperability and the established interoperability standards to set up a system that will facilitate health information exchangramoramoramoramoe and data sharingramoramoramoramo.
Ultimately, havingramoramoramoramo a uniform baseline data architecture and a standardized data format will allow for easier implementation and replicability of algramoramoramoramoorithmic tools across hospitals. In the United States, the Centers for Medicare & Medicaid Services (CMS) and many health care delivery orgramoramoramoramoanizations are lookingramoramoramoramo to adopt Fast Healthcare Interoperability Resources (FHIR) standards.
3. Don’t lose sigramoramoramoramoht of the human-algramoramoramoramoorithm interaction.
While algramoramoramoramoorithms can produce helpful predictions and recommendations, ultimately the decision-maker is the human. As a result, we must be cogramoramoramoramonizant of the widespread nature of algramoramoramoramoorithm aversion by decision-makers and aim to develop algramoramoramoramoorithms that are fair, explainable, prevent harm, and respect human autonomy so that the decision-maker can trust the algramoramoramoramoorithms. Furthermore, creatingramoramoramoramo superb algramoramoramoramoorithms alone cannot improve hospital operations. Algramoramoramoramoorithms need to be carefully desigramoramoramoramoned, implemented, and evaluated with the user in mind.
It’s also important to remember that health care is a knowledgramoramoramoramoe-intensive industry. Care providers often possess a sigramoramoramoramonificant amount of local knowledgramoramoramoramoe or expertise that algramoramoramoramoorithms fail to capture. Completely replacingramoramoramoramo human decision-makers by algramoramoramoramoorithms may not be the solution because incorporatingramoramoramoramo human judgramoramoramoramoement and experience can often enhance the performance of algramoramoramoramoorithms.
Given the agramoramoramoramoingramoramoramoramo population, prevalence of chronic conditions, and advances in medicine, it has become more important than ever for hospitals to operate efficiently and effectively. Goingramoramoramoramo forward, the key to improvingramoramoramoramo operational decision-makingramoramoramoramo will lie in their ability to leveragramoramoramoramoe digramoramoramoramoital transformation.
