Ed Corbett, MD

Machine learning (ML) can deliver critical insight to clinicians at the point of decision making and replace manual processes, such as reviewing a patient’s lab history. However, many clinicians don’t reap these ML benefits due to a lack of understanding and data infrastructure. To maximize the many advantages ML can bring to the bedside, organizations need to educate team members about ML and then invest in data infrastructure that supports ML capabilities. A transparent explanation of benefits can garner support and understanding that ML augments—not replaces—clinicians. With this increased understanding, leaders see the value of data integration infrastructure. A robust data platform allows organizations to aggregate data from multiple sources, ensuring ML algorithms deliver accurate insight based on comprehensive patient data.

Over the last decade, many health systems have found that augmented intelligence (AI) technologies have overpromised and underdelivered. The promises of AI in clinical care were grand—to ease physicians’ burdens and deliver the most relevant information at the point of decision making. However, more technology has increased the demand on providers along with clinicians’ doubt of AI’s capabilities.

Organizations can still deliver valuable AI-derived patient insight to providers at the front lines of care by taking a collaborative approach to AI that enlists clinicians in three key areas:

1. Development.
2. Implementation.
3. Results.

With an ever-changing understanding of COVID-19 and a continually fluctuating disease impact, health systems can’t rely on a single, rigid plan to guide their response and recovery efforts. An effective solution is likely a flexible framework that steers hospitals and other providers through four critical phases of a communitywide healthcare emergency:
1. Prepare for an outbreak.
2. Prevent transmission.
3. Recover from an outbreak.
4. Plan for the future.

The framework must include data-supported surveillance and containment strategies to enhance detection, reduce transmission, and manage capacity and supplies, providing a roadmap to respond to immediate demands and also support a sustainable long-term pandemic response.

With an ever-changing understanding of COVID-19 and a continually fluctuating disease impact, health systems can’t rely on a single, rigid plan to guide their response and recovery efforts. An effective solution is likely a flexible framework that steers hospitals and other providers through four critical phases of a communitywide healthcare emergency:

1. Prepare for an outbreak.
2. Prevent transmission.
3. Recover from an outbreak.
4. Plan for the future.

The framework must include data-supported surveillance and containment strategies to enhance detection, reduce transmission, and manage capacity and supplies, providing a roadmap to respond to immediate demands and also support a sustainable long-term pandemic response.

COVID-19 is now a commanding force in healthcare, and outbreak-driven trends will continue to influence the industry and impact patients for the foreseeable future. Understanding and preparing for activity in five critical categories will help health systems navigate the next phases of the COVID-19 era:

1. A potential vaccine—confronting availability and distribution challenges.
2. Virtual care—managing the best interests of patients and providers.
3. Models of care—accommodating changing delivery and long-term needs of COVID-19 patients.
4. Healthcare resource management—planning for and recovering from financial and capacity strain.
5. Data—improving accuracy, availability, and timeliness for pandemic management.

由于新型冠状病毒，卫生系统面临着常规非急诊患者护理的下降，它们必须灵活并找到新的护理提供方法，以确保患者获得服务。
Telehealth—using a digital platform to conduct are remotely—benefits both patients and health systems. Although laying the groundwork for telehealth and then scaling telehealth solutions is challenging, virtual care leads to increased patient access, better patient retention, and overall reduced costs for health systems, employers, and patients.
With the right tools to build a reliable framework, organizations can effectively deliver quality care to patient populations, no matter where they live.

到目前为止，电子病历并没有达到其最初的目的，即以更高效、更个性化和更低的成本来改善患者护理。Instead, physician users blame the systems for worsening their experience and the quality of their care in significant ways:

1. Less time for patient interaction and worsened quality of interaction.
2. An extended workday.
3. Poor design (difficult to use).
4. Demands of quality measures.
5. Cost and maintenance.

Despite these challenges, the EHR is likely here to stay. Health systems have invested heavily in their electronic reporting systems and are now focused on making these technologies and processes work for the benefit of patients and providers. CIOs are working towards better aligning digital health goals with physician experience for an environment where EHRs enable smarter, not harder, work.

将高质量的数据与改善患者体验联系起来可能有点飞跃。但是，当你考虑到医生需要数据来跟踪患者的诊断、治疗、进展和结果时，这种路径是显而易见的。
数据必须是高质量的(容易获取、标准化、全面)，这样才能简化而不是复杂化医生的工作。这在追求人口健康方面变得更加重要，因为护理团队需要容易地确定需要预防性或后续护理的高危患者。
Patients engaged in their own care via portals and personal peripherals contribute to the volume and quality of data and feel empowered in the process. This physician and patient engagement leads to improved care and outcomes, and, ultimately, an improved patient experience.