A predictive decision support system for coronavirus disease 2019 response management and medical logistic planning

Objective

Coronavirus disease 2019 demonstrated the inconsistencies in adequately responding to biological threats on a global scale due to a lack of powerful tools for assessing various factors in the formation of the epidemic situation and its forecasting. Decision support systems have a role in overcoming the challenges in health monitoring systems in light of current or future epidemic outbreaks. This paper focuses on some applied examples of logistic planning, a key service of the Earth Cognitive System for Coronavirus Disease 2019 project, here presented, evidencing the added value of artificial intelligence algorithms towards predictive hypotheses in tackling health emergencies.

Methods

Earth Cognitive System for Coronavirus Disease 2019 is a decision support system designed to support healthcare institutions in monitoring, management and forecasting activities through artificial intelligence, social media analytics, geospatial analysis and satellite imaging. The monitoring, management and prediction of medical equipment logistic needs rely on machine learning to predict the regional risk classification colour codes, the emergency rooms attendances, and the forecast of regional medical supplies, synergically enhancing geospatial and temporal dimensions.

Results

The overall performance of the regional risk colour code classifier yielded a high value of the macro-average F1-score (0.82) and an accuracy of 85%. The prediction of the emergency rooms attendances for the Lazio region yielded a very low root mean square error (<11 patients) and a high positive correlation with the actual values for the major hospitals of the Lazio region which admit about 90% of the region's patients. The prediction of the medicinal purchases for the regions of Lazio and Piemonte has yielded a low root mean squared percentage error of 16%.

Conclusions

Accurate forecasting of the evolution of new cases and drug utilisation enables the resulting excess demand throughout the supply chain to be managed more effectively. Forecasting during a pandemic becomes essential for effective government decision-making, managing supply chain resources, and for informing tough policy decisions.

A Geospatial Artificial Intelligence and satellite-based earth observation cognitive system in response to COVID-19

The pandemic emergency caused by the spread of COVID-19 has stressed the importance of promptly identifying new epidemic clusters and patterns, to ensure the implementation of local risk containment measures and provide the needed healthcare to the population. In this framework, artificial intelligence, GIS, geospatial analysis and space assets can play a crucial role. Social media analytics can be used to trigger Earth Observation (EO) satellite acquisitions over potential new areas of human aggregation. Similarly, EO satellites can be used jointly with social media analytics to systematically monitor well-known areas of aggregation (green urban areas, public markets, etc.). The information that can be obtained from the Earth Cognitive System 4 COVID-19 (ECO4CO) are both predictive, aiming to identify possible new clusters of outbreaks, and at the same time supervisorial, by monitoring infrastructures (i.e. traffic jams, parking lots) or specific categories (i.e. teenagers, doctors, teachers, etc.). In this perspective, the technologies described in this paper will allow us to detect critical areas where individuals can be involved in risky aggregation clusters. The ECO4CO data lake will be integrated with ad hoc data obtained by health care structures to understand trends and dynamics, to assess criticalities with respect to medical response and supplies, and to test possibilities useful to tackle potential future emergencies. The System will also provide geographical information on the spread of the infection which will allow an appropriate context-specific public health response to the epidemic. This project has been co-funded by the European Space Agency under its Business Applications programme.

Preliminary results of a phase I clinical trial of CYT-6091: A pegylated colloidal gold-TNF nanomedicine

3603

Background: CYT-6091, a nanotherapeutic manufactured by covalently linking tumor necrosis factor-a (TNF) onto the surface of 30 nm particles of pegylated colloidal gold, avoids uptake by the reticuloendothelial system (RES) and distributes primarily to solid tumors. In tumor bearing mice, CYT-6091 shows little to no uptake by the RES and increases intra-tumor TNF levels 10-fold. Electron micrographs show the accumulation of gold nanoparticles in tumors, with few particles in healthy tissue. In dogs with naturally occurring cancers and healthy rabbits, CYT-6091 caused fever but no hypotension, the known DLT for TNF. Methods: CYT-6091 is being tested in a phase I open label trial in solid tumor, advanced stage disease patients. Patients (n=3/dose), admitted to the NIH Clinical Center ICU, receive two IV injections of CYT-6091 on day 0 and 14. Doses start at 50 μg/m2 of TNF and increase by 50 μg/m2 increments to 300 μg/m2. Vital signs are monitored and blood samples are drawn over 48 hours. The primary endpoint of the study is to determine the MTD for CYT-6091. Secondary endpoints include PK, disease response (staged 45 days post treatment), and the detection of gold nanoparticles in tumors and in adjacent healthy tissue. Results: Seven patients have been treated to date. The three treated with the lowest dose (50 μg/m2) exhibited a febrile response, which was mitigated by acetaminophen and indomethacin pretreatment. None of the seven patients treated with 50, 100 or 150 μg/m2 showed a DLT hypotensive response, and blood chemistries and urinalysis were not significantly different following treatment. PK estimates for the TNF T1/2, administered as CYT-6091, are 117, 145 and 127 minutes for 50, 100 and 150 μg/m2, respectively. Electron micrographs of tumor biopsies and adjacent healthy tissue show as much as a 10-fold increase in the number of gold nanoparticles in tumors from 5 of 6 patients compared to adjacent healthy tissue. Conclusion: These observations are the first definitive demonstration in man of the tumor targeting of a systemically administered, colloidal gold-based nanomedicine.

No significant financial relationships to disclose.

Phase I dose escalation and PK study of thermally sensitive liposomes containing doxorubicin given during radiofrequency ablation (RFA) in patients with non-resectable primary and metastatic liver cancer

15010

Purpose: This phase I dose escalation and pharmacokinetic (PK) study in patients with non-resectable primary or metastatic hepatic tumors undergoing radiofrequency ablation (RFA) uses a 30-minute IV infusion of ThermoDox (TDox) starting 15 minutes prior to RFA treatment. TDox liposomes are engineered to release doxorubicin (Dox) locally at temperatures greater than 39.5 °C. High local concentrations of Dox could allow for increased drug concentration targeted at the tumor margins in an effort to achieve improved local recurrence and tumor control near these RFA-induced thermal lesions. The phase I study goals are to determine the maximum tolerated dose and dose-limiting toxicity of TDox. Patients and Methods: Patients (pts) must be eligible for RFA for primary (HCC) or metastatic liver cancer (MLC). Main inclusion criteria are = 4 lesions and = 7 cm in greatest diameter. Dose escalation is: cohorts of 3–6 pts treated with a single dose of 20, 30, 40, 50, 60 or 70 mg/m2. RFA is administered via percutaneous or surgical approach. RFA treatment without TDox can be repeated for recurrent hepatic (distant or local) tumors. Patients requiring systemic chemotherapy following RFA are removed from the study. MRI, PET and contrast enhanced CT (CE-CT) scans are done pre-, one and three months post-treatment (q3 months thereafter for patients on trial). CE-CT scans are also performed immediately following RFAs. Patients are assessed for safety, PK, and lesion diameters on CT. RFA+TDox lesion diameters will be compared to patients treated by RFA alone (control) at the same institution. Results: A total of 22 pts have been treated as of January 2007 submission date (3, 6, 6, 6, 1 patients at 20, 30, 40, 50, and 60 mg/m2, respectively). This population includes 8 pts with HCC and 14 pts with MLC. Grade 3/4 toxicity (reversible neutropenia) has been observed to be dose dependent. 1 patient at 50 mg/m2 has met DLT criteria. Conclusions: TDox has been safely administered in combination with percutaneous or surgical RFA procedures in 22 patients with liver tumors. There has been limited, manageable toxicity thus far. Enrollment continues as the MTD and DLT have yet to be defined.

[Table: see text]

A pilot study of local injection of TNFerade biologic in addition to neo-adjuvant chemoradiation for the treatment of primary and recurrent rectal cancer

14585

Background: Rectal cancer presents unique therapeutic considerations due to competing concerns regarding sphincter preservation and local recurrence. Treatments using pre-operative chemoradiation are employed to decrease local recurrence and improve the probability of sphincter preservation. Agents, which improve the pathologic response rate may be of further benefit. Methods: TNFerade biologic is a replication deficient adenovirus expressing human TNF-alpha driven by a radiation inducible promoter. TNFerade biologic (4X10e10 pfu) is injected locally into rectal tumors once a week for 5 weeks. Patients receive concurrent chemoradiation utilizing oral capecitabene (937.50 mg/m2 BID, Monday-Friday) and external beam radiotherapy (1.8 Gy/day, 5 days per week to a total dose of 45 Gy). A boost dose of 5.4–9 Gy is delivered to sites of gross disease. After treatment, patients recover for 6–9 weeks before surgery. Patients are scored prior to the start of neo-adjuvant therapy for the feasibility of a sphincter preserving operation versus an abdominal perineal resection (APR). Following surgery the specimen (entire area submitted for processing) is examined for the percent of viable tumor remaining. The goal of the study is to show a target pathologic response rate of <10% viable tumor in more than 30% of patients treated. Results: Six patients have been treated (4M, 2F). There has been no toxicity attributable to the TNFerade biologic, and the chemoradiation has been well tolerated with only mild, expected toxicities. Five of the six patients have undergone surgery (one is awaiting surgery). Three of these five patients were thought to require an APR prior to treatment due to the size and location of their tumor. All five patients have successfully undergone sphincter- preserving operations. On examination of the five specimens, 3 had less than 5% viable tumor while 2 had greater than 50% viable tumor. All resections were margin negative. The target pathologic response rate of <10% viable tumor was achieved in 60% of the patients evaluated. Conclusion: The addition of TNFerade biologic to pre-operative chemoradiation was well tolerated and a prospective randomized trial comparing the addition of this agent to chemoradiation is warranted.

No significant financial relationships to disclose.