1 Introduction

A vital component of healthcare is medication management, which is crucial for ensuring patient safety and enhancing healthcare outcomes [1]. But medication mistakes seriously jeopardize patient safety and healthcare effectiveness [2]. According to the Institute of Medicine, drug errors cause over 7,000 fatalities and over 1.5 million injuries annually in only the United States [3]. In order to address this issue, innovative and efficient medication management systems that make use of cutting-edge technologies to lower medication errors and enhance patient safety are needed.

Real-time patient monitoring, remote patient care, and better drug administration are all made possible by the Internet of Medical Things (IoMT), a quickly developing field that has the potential to completely change the way healthcare is provided. IoMT refers to a group of gadgets that gather and instantly communicate patient-specific data to healthcare practitioners, such as wearable sensors, mobile apps, and medical devices [4]. By enabling prompt intervention, customized treatment regimens, and improved medication administration, these devices have the potential to boost patient outcomes.

A potential strategy for lowering medication mistakes and increasing patient safety and healthcare effectiveness is personalized medication management [5]. Healthcare practitioners can customize treatment programs for specific patients, lowering the likelihood of adverse drug responses and boosting prescription adherence. This is done by utilizing patient-specific data, such as medical history, genetics, and medication history. Personalized drug management can also increase the effectiveness of healthcare by lowering hospital readmissions and expenditures [6].

It is now possible to apply cutting-edge technologies like IoMT and machine learning to improve drug management as smart hospitals emerge with their sophisticated technologies and integrated systems [7]. Smart hospitals use cutting-edge technology to build a network of interconnected devices and systems that allow for remote patient care, real-time patient monitoring, and improved drug administration.

This study investigates the possibilities of IoMT and machine learning for individualized medication management in smart hospitals. To be more precise, we want to respond to the following study questions:

  1. 1.

    In smart hospitals, how might IoMT be used to enhance individualized medicine management?

  2. 2.

    How do IoMT and machine learning for individualized drug management affect patient safety and healthcare effectiveness?

We predict that individualized medication management via IoMT and machine learning will lead to a substantial decrease in medication mistakes and adverse drug responses as well as an increase in healthcare effectiveness. The results of this study have significant ramifications for the future of medicine administration in modern hospitals and for the incorporation of cutting-edge medical technology.

The structure of this paper is as follows: The problem of medication errors, a thorough assessment of the literature on medication administration in healthcare, and the possible advantages of individualized medication management are covered in the second section. The IoMT and its potential to enhance drug management in smart hospitals are the main topics of the third segment. The impact of individualized medication management utilizing IoMT and machine learning on patient safety and healthcare effectiveness is examined in the fourth section, where we also offer our technique for doing so. The fifth section examines the results of our study and displays our findings. In the final section, we summarize our results, discuss our limitations, and offer suggestions for further research.

2 Literature review

Medication management is a critical component of providing healthcare, and drug errors continue to be a major issue on a global scale. At least one in ten patients worldwide have medication errors, which the World Health Organization claims are a major cause of considerable illness, mortality, and elevated healthcare costs [8]. Any step in the drug process, including prescribing, dispensing, administering, and monitoring, is susceptible to medication errors. Medication errors are caused by a number of variables, including insufficient training, poor communication between healthcare professionals, a lack of information technology, and patient-related issues like non-adherence, polypharmacy, and comorbidities [9].

Healthcare institutions have been investigating the use of individualized medication management systems to address prescription mistakes and enhance patient safety. These systems create prescription regimens that are efficient, effective, and safe for each patient based on information about their medical history, allergies, and genetics. Personalized medication management can enhance patient outcomes, quality of life, and healthcare efficiency while preventing adverse drug reactions, medication interactions, and therapeutic failures [10].

In hospitals, the utilization of cutting-edge technology like the IoMT and machine learning can improve individualized medicine administration. The Internet of Medical Things (IoMT) is the combination of internet-connected platforms that enable real-time data collecting, analysis, and connection with medical devices, sensors, and other healthcare equipment. By providing real-time drug tracking, tracking patient adherence, and warning healthcare professionals of potential medication errors, the IoMT can increase medication safety [4].

Another technology that can be used for individualized drug management is machine learning (ML). In ML, algorithms are used to find patterns in data, forecast the future, and improve decision-making. By evaluating patient-specific data, including medical history, genetics, and real-time sensor data, ML can enhance medication management by making individualized prescription recommendations that are catered to the patient's requirements and preferences [11].

Numerous research have looked into the usage of cutting-edge technologies and individualized drug management in hospitals. For instance, a study by Ge et al. [12] investigated the use of a mobile health platform that combined ML algorithms with electronic medical records to offer tailored drug recommendations for the management of chronic diseases. In comparison to traditional treatment, the platform, according to the study, reduced medication mistakes and improved drug adherence.

Another study by Cocian et al. [13] looked into the application of RFID technology to enhance hospital medication safety. In comparison to manual tracking techniques, the study indicated that RFID tags affixed to pharmaceutical packaging reduced medication errors and enhanced drug tracking.

In conclusion, medication errors continue to be a serious issue in the healthcare industry, and individualized medication management systems have the potential to increase patient safety and healthcare effectiveness. IoMT and machine learning are two examples of cutting-edge technology that can improve individualized medicine administration in hospitals. According to the available research, individualized medication management and cutting-edge technologies have showed promise in enhancing medication safety and adherence. Further study is required to examine the potential advantages and drawbacks of these systems in practical contexts, though.

3 IoMT for medication management in smart hospitals

The IoMT, a rapidly expanding area of healthcare, has the potential to revolutionize medicine administration in modern hospitals. IoMT is a network of sensors and medical devices that can gather and transmit real-time patient data. IoMT devices can track patient vitals, keep tabs on drug use, and warn medical professionals of any medication errors. In this part, we'll look at how IoMT might help smart hospitals manage their medication better [4].

IoMT devices can be used to track and monitor medications in real-time, which can lower the risk of medication errors. Smart medication dispensers, for instance, can be used to track when medication is taken and distribute it at predetermined periods [14]. This can help to make sure that people are taking their prescription as directed and can notify medical professionals if a medication is missed or not taken correctly. IoMT tools can also be used to monitor drug inventories, lowering the possibility of shortages and guaranteeing that drugs are available when needed.

IoMT devices can be used to gather and analyze patient data in addition to doing real-time monitoring [15]. In order to create individualized medication programs, this can assist healthcare professionals in identifying patterns and trends in the medication usage of their patients. Additionally, IoMT devices can be used to warn medical professionals of possible negative drug reactions or interactions, which can assist avoid prescription errors.

IoMT has enormous potential for improving drug management in smart hospitals, but there are also obstacles that need to be overcome. Making sure IoMT devices are safe and secure from online attacks is a challenge. When employing IoMT devices, patient privacy is an issue as well, thus it’s critical to make sure that patient data is managed securely and in accordance with laws [16].

IoMT has a lot of potential to help smart hospitals manage their medications better. IoMT devices can offer tailored medicine planning, real-time monitoring, and drug tracking, which can lower the possibility of medication errors and enhance patient outcomes. It is crucial for healthcare professionals to carefully assess the possible advantages and difficulties of utilizing these technologies for medication management as the field of IoMT continues to expand.

4 Methodology

This section outlines the procedures used to examine the possibilities for employing the IoMT for individualized medication management in smart hospitals. Details on the system architecture, study design, data gathering procedures, and data analysis methodologies are provided.

4.1 System architecture

A variety of technologies and components are used in the system architecture for personalized medicine management utilizing IoMT in smart hospitals to create a seamless and effective healthcare system.

Figure 1 depicts the system’s architecture. Patient data collecting, data processing and analysis, medication management, and communication make up the system’s four key parts.

Fig. 1
figure 1

System Architecture for Personalized Medication Management using IoMT in Smart Hospitals

Full size image

4.1.1 Patient data collection

The patient data collecting component involves a number of data sources, including wearables, other IoMT devices, smart drug dispensers, and electronic health records (EHRs). Information about the patient’s medical history, prescription regimen, allergies, vital signs, and other important clinical characteristics can be gleaned from the data gathered from these sources.

4.1.2 Data processing and analysis

To create individualized medication recommendations for each patient based on their particular needs and health status, the data processing and analysis component processes patient data gathered from numerous sources using machine learning algorithms. The algorithms are capable of finding patterns and trends in the data, which may be utilized to enhance drug management for each patient. They have been trained on enormous datasets of patient data.

4.1.3 Medication management

The implementation of tailored medicine recommendations for each patient is part of the medication management component, as is real-time medication adherence monitoring using IoMT devices like wearables and smart medication dispensers. The patient's medical history, medication regimen, allergies, and other pertinent clinical characteristics are used to develop the individualized medicine recommendations. Real-time medication adherence monitoring enables early detection of prescription errors and can stop unfavorable drug effects.

4.1.4 Communication

The personalized medicine management system's integration with the hospital's current communication infrastructure is part of the communication component. The seamless coordination of healthcare practitioners, patients, and their families is made possible through the use of electronic health records, hospital information systems, and other communication tools.

The IoMT-based individualized medication management system architecture in smart hospitals is created to deliver a complete and effective healthcare system. The system may produce individualized medicine recommendations for each patient, track medication adherence in real-time, and stop adverse drug events by utilizing the capabilities of machine learning algorithms and IoMT devices. The system's seamless integration with the hospital's current communication infrastructure enables efficient coordination between medical staff, patients, and their families, improving patient outcomes and the effectiveness of healthcare delivery.

4.2 Study design

The effectiveness of individualized drug management utilizing IoMT will be examined in a randomized controlled trial (RCT). The study population consists of adult patients admitted to the hospital who require medication management. The dataset for this study will be obtained from the electronic health records (EHRs) of the participating smart hospitals [17].

A sample size of 500 patients will be selected for the study, with 250 patients randomly assigned to the intervention group and 250 patients assigned to the control group. The randomization process will ensure that patients are evenly distributed between the two groups and minimize any potential biases.

The intervention group will receive personalized medication management using IoMT, which includes the use of patient-specific data, advanced technologies, and real-time monitoring of medication adherence. The control group, on the other hand, will receive standard medication management practices typically implemented in the participating hospitals.

Patient data collected for the study will include demographic information, medical history, medication orders, allergies, genetic profiles (if available), and relevant clinical parameters. The data will be securely collected and stored in accordance with privacy regulations and ethical guidelines.

Data analysis will involve statistical methods to compare outcomes between the intervention and control groups. Descriptive statistics will be used to summarize patient demographics and medication-related outcomes. Inferential statistics, such as t-tests and ANOVA [18], will be employed to evaluate the effectiveness of personalized medication management using IoMT in reducing medication errors and improving patient safety and healthcare efficiency.

4.3 Data collection

Patient-specific data will be gathered from various sources in order to ensure a thorough and accurate assessment of the effectiveness of individualized medicine management utilizing IoMT in smart hospitals. This will include electronic health records (EHRs), which will offer useful details on each patient's medical background, allergies, and ongoing drug schedules [17]. In addition, cutting-edge IoMT gadgets like wearables and smart pill dispensers will be used to gather real-time patient data like vital signs and medication adherence. With the aid of these technologies, a more complete and dynamic picture of each patient's health situation and medication requirements will be possible, enabling more precise and individualized medicine prescriptions. The data gathered from these devices will subsequently be analyzed using machine learning algorithms, enabling the creation of individualized medication recommendations for each patient based on their particular requirements and state of health.

4.4 Data analysis

There will be various processes involved in the data analysis for the IoMT-based individualized medication management system. First, patient demographics and medication consumption trends in the intervention and control groups will be examined using descriptive statistics. This will make it easier to spot any major variations between the groups that might have an impact on the study's findings.

Second, to compare the medication mistake rates and patient outcomes between the two groups, hypothesis testing will be done using t-tests and chi-square tests. This will enable us to evaluate the effectiveness of individualized medication management using IoMT to regular medication management in terms of medication adherence and medication mistakes.

Thirdly, the precision of the tailored drug recommendations created for each patient will be assessed using machine learning algorithms. This will entail comparing the algorithm's suggestions to the actual prescriptions prescribed and any adjustments made to the medication schedule over time.

In order to improve medication adherence and decrease medication errors, individualized medication management utilizing IoMT will be evaluated using the data. It will also assist us in determining any places where the algorithm or the drug management procedure needs to be improved.

5 Results

The data analysis techniques we employed to assess the performance of the personalized medication management system were described in the section above. Both the intervention and control groups' patient demographics and medication usage patterns were examined using descriptive statistics. T-tests and chi-square tests were used for hypothesis testing to evaluate the patient outcomes and medication error rates between the two groups. Machine learning techniques were also employed to assess the precision of the unique medicine suggestions created for every patient. The effects of individualized drug management employing IoMT and machine learning on patient safety and healthcare effectiveness are discussed in this section.

5.1 Study results

A sample of 500 patients from a next-generation hospital who had a tailored drug management system employing IoMT and machine learning were included in this study. The study assessed how well the approach reduced prescription errors while enhancing patient safety and healthcare productivity.

The intervention and control groups' demographic details are included in Table 1 for comparison. Age, gender, race, and ethnicity differences between the two groups were comparable, showing that randomization was successful.

Table 1 Demographic characteristics of the intervention and control groups
Full size table

In comparison to the hospital's previous system, the results revealed a 50% decrease in medication errors, which was a considerable reduction in medication errors. The rates of medication errors in the intervention and control groups are shown in Fig. 2.

Fig. 2
figure 2

Comparison of Medication Error Rates between Intervention and Control Groups

Full size image

Based on patient-specific data and cutting-edge technology like IoMT and machine learning, the personalized medication management system was able to identify and avoid medication errors in real-time. Reduced risk of medication-related injury was made possible by the system's capacity to make individualized medicine recommendations based on patient-specific information, such as medical history, allergies, and genetic profile. The patterns of medication use in the intervention and control groups are displayed in Table 2.

Table 2 Medication usage patterns in the intervention and control groups
Full size table

The approach was proven to be very successful in preventing negative drug reactions and medication-related problems, which is important for patient safety. Figure 3 displays the prevalence rates of medication-related problems and adverse drug responses in the intervention and control groups.

Fig. 3
figure 3

Incidence Rates of Adverse Drug Reactions (ADR) and Medication-Related Complications (MRC) in the Intervention and Control Groups

Full size image

The individualized drug management system significantly increased healthcare productivity in addition to patient safety. Healthcare workers spent less time on chores connected to administering medication thanks to the technology, which freed them up to concentrate on other crucial patient care duties. The technology also assisted in reducing duration of stay and readmissions to hospitals, which saved the hospital money.

Overall, this study provides compelling evidence that using IoMT and machine learning for individualized drug management can considerably increase patient safety and healthcare effectiveness.

5.2 Implications of study results

The implications of the study's findings show how individualized drug management systems might boost patient outcomes and cut expenses. Healthcare providers can create personalized prescription programs for individuals based on their unique medical histories, allergies, and genetic profiles by using IoMT and machine learning technology in drug management. The risk of medication-related harm can be reduced and patient outcomes can be improved with this tailored approach to medication management.

Additionally, by incorporating predictive analytics models, healthcare providers can foresee probable medication-related issues and take preventative action to avoid negative outcomes. This proactive method of managing medications can increase patient safety and lower healthcare expenditures.

According to the study's findings, hospitals aiming to boost medication efficiency and safety should think about putting in place customized medication management systems that make use of IoMT and machine learning. By drastically reducing prescription errors, adverse drug responses, hospital readmissions, and length of stay, such systems could save hospitals money while also improving patient outcomes.

The study's findings show the possibility for using IoMT and machine learning for individualized drug management in the healthcare industry. To fully investigate these technologies' potential for enhancing patient outcomes and lowering costs, more study is required.

6 Discussion

This section discusses the potential implications of the study findings for clinical practice and healthcare policy, examines the advantages and disadvantages of the study design and methodology, and makes suggestions for future studies in the area of personalized medication management using IoMT and machine learning.

The study’s findings demonstrated that integrating IoMT and machine learning for tailored medication management can considerably lower medication mistakes while also enhancing patient safety and healthcare effectiveness. This result is in line with earlier studies that showed the potential of cutting-edge technologies to enhance medication management in healthcare.

These findings have important consequences for clinical practice and healthcare policy. Healthcare professionals may make better judgments about medicine prescribing, dose, and administration with the use of IoMT and machine learning, which will improve patient outcomes and save healthcare costs.

The study’s ability to deliver individualized drug recommendations by using patient-specific data and cutting-edge technology is one of its strengths. The sample size, however, placed restrictions on the study design, and future studies should seek to reproduce these results in larger, more diverse populations.

Personalized medication management with IoMT and machine learning has the potential to increase patient safety and healthcare effectiveness in smart hospitals, according to the study's findings. To fully exploit the promise of these technologies and to assure their successful incorporation into clinical practice, more research in this area is required.

7 Conclusion and future directions

In smart hospitals, individualized medication management has the potential to greatly increase patient safety and healthcare productivity. This study illustrates this potential. Healthcare practitioners can decrease medication errors, improve drug adherence, and ultimately improve patient outcomes by utilizing patient-specific data and cutting-edge technologies. To achieve personalized medication management and improve patient care, clinical practice must include cutting-edge technology like IoMT and machine learning.

However, it is crucial to advance research in the area of individualized medicine management in order to fully exploit the potential advantages of these technologies. Future research should concentrate on fixing shortcomings and broadening the current study's scope to include a larger sample size and a more varied patient group. In order to employ IoMT and machine learning in clinical practice safely and effectively, detailed guidelines and procedures must be developed.

Additionally, this study’s future directions could involve investigating the application of additional cutting-edge technologies, such blockchain, to enhance the security and privacy of patient data. Further research is required to ascertain the cost-effectiveness of individualized drug management utilizing IoMT and machine learning, as well as its potential impact on lowering healthcare inequities.

In summary, personalized medication management using IoMT and machine learning has the potential to revolutionize medication management in smart hospitals and significantly improve patient outcomes. By adopting advanced technologies and leveraging patient-specific data, healthcare providers can enhance medication safety and efficacy, leading to better patient outcomes and reduced healthcare costs. Future research and implementation of personalized medication management in smart hospitals hold great promise in improving the quality of patient care.