The index below is a live metric of “Hospital Stress” that represents: “how much hospitalization numbers are growing daily in percentage”. By hospitalization number i mean, hospitalized_symptomatic_cases and intensive_care_cases (see section below for explanation) Equally important, this index is ALSO a decent(*) indicator, but lagged(5to8days), of the real hidden recent growth of the ACTUAL contagion.

UPDATE: 07/08-April Data, and COMMENTS:

Longer Summary

Macro Regions: North_ish, Center_ish, South_ish.

The epidemic started in the Lombardia region, so the grouping below is both geographical as well as approximately represents the epidemic at different stages (even if in Piedmont or Liguria there was approx a week delay of the onset). In terms of policy the starting times for social distancing were similar (8th / 9th Mar). This region definitions maybe overlapping. Here in Fig2, I am plotting the actual real dates with no sinthetic lags.

The data in the south_ish area is more noisy and sparse, the growing rate smoothed value recently does appear to start slowing down more significantly. I also Put the indicator for All_wihtout_Lombardia and Lombardia-alone. In Lombardia some province ( Bergamo, Brescia, some part of Milano) have had frequent saturations based on other info. However the informativeness of the index as a whole at the Italian Level stll holds, as it is seen from the center and south trends or Italy without Lombardia. It basically starts at around 30/35 % and ends aroudn 2 % between the beginnnig and the end of March. Approx 1% per day average deceleration of percentage growth. This should hold for the contagion itself.

(If you know the Italian data already you can skip the next section. You can click on the little arrows to expand certain sections)

Data Sources

Click for Expanding The Data Source Section

Raw Data from “Protezione Civile Italiana” (better sources are welcome if you have them)

https://raw.githubusercontent.com/pcm-dpc/COVID-19/master/dati-regioni/dpc-covid19-ita-regioni.csv

Here there is a list of daily pdf reports.

https://github.com/pcm-dpc/COVID-19/tree/master/schede-riepilogative/regioni

The time series with daily frequenceies are : “hospitalized_symptomatic”,“intensive_care”,“tot_hospitalized”,“home_isolation”,“tot_positive”,“recovered”,“dead”,“tot_cases”,"“tested”

in Italian (“ricoverati_con_sintomi”,“terapia_intensiva”,“totale_ospedalizzati”,“isolamento_domiciliare”,
“totale_attualmente_positivi”,“dimessi_guariti”,“deceduti”,“totale_casi”
“tamponi”)

Italy Total, last 3 days
hospitalized_symptomatic intensive_care tot_hospitalized home_isolation tot_positive_now new_positive recovered dead tot_cases
2020-04-17 25786 2812 28598 78364 106962 3493 42727 22745 172434
2020-04-18 25007 2733 27740 80031 107771 3491 44927 23227 175925
2020-04-19 25033 2635 27668 80589 108257 3047 47055 23660 178972

Raw Data in Log Scale

Click for Expanding this Section

There are various models for epidemic data (the SIR with its varations being the most used, see all the references in [1], [16]) here we just want to build a live indicator (Blue line in Fig1 or Fig2) to monitor the current state of the epidemic without assuming any model or stationarity in the time series dynamic, or for their relationship and parameters.

The Figure3 below is just the raw data, and shows visually that in the logarithmic space there is an “approximately” linear growth of the time series. It also appears the linear growths, the tangent lines of this plots, tends to flattens out with time. Independently from stationarity assumptions, one can measure the daily percentage growth of the time series, such as an “instantaneous” growth rate that (hopefully) decreases with time, due to all sorts of effects, both intrinsic of the epidemic and exogenous such as government policies, as well as other noisy contributions.

NOTE: The raw numbers in Figure 3 represent the current number of people/cases in a specific “state” (e.g. a “state” is “being hospitalized”). In Figure 4 the daily-differences of the Log(Series) of Figure 3. It would be better to have daily number of people entering each state, such as daily number of new_hospitalized, or daily number of new_intensive_care. One person/case can, in principle, move from hospitalized to intensive_care and back, between hospitalized and non-hospitalized, as well as from intensive care to dead (usually 50% of the cases according to some research [see summary reference [1]]). Also, some recovered from icu and clinically recovered are still contagious as well and is not so clear where they have been classified. The number of New tested positive and new death cases are in principle computable, since those are “one-way” state, however they are: 1)total positive cases: have upper bounds dependent on will/ability of large scale testing. 2)dead: very slow and small proportion, with a large dispersion of lag: death has a big lag-uncertainty in the from symptoms (median 20 +/- 10 days ). Also some cases may go straight to the dead state never being recorded as hospitalized or in intensive care. New Intensive care could be partially deduced from the change in total current intensive care numbers adding the new_dead (I may do this later), but other uncertainties holds and this flows between states have different timescales (icu to dead seems to be median of 5 days, while recovering from icu may take weeks).

All data dynamics, in general, can be influenced by “border effects” like saturation of available space/resources to deal with fast local growth of the cases. Moreover there are occasional and regional dependent delays in noting the data points and the inability to even record/attribute the cases for death/hospitalization etc. With anecdotal knowledge some data points maybe cleaned ad-hoc (not yet done here). A lot of issues may be present in the data, such as large underestimation for positive cases and even related deaths (see [17])

We can estimate the time-trend of growth doing the 1-day differences of the numbers of each Series above : 100*(Log(Series(t))-Log(Series(t-1))) . this is simple the 1-day percent Change. Plotted in the next figure Figure4. There are two evident reasons to use percentage change: 1) this series tend to grow exponentially, at least locally, that is new daily cases are proportional to number of cases from the previous day; 2) secondly this hospitalizations are in general a percentage of the actual unknown total infected cases (appearing in the data, with a lag after incubation and worsening conditions). It is difficult to backtrack the number of daily contagion (even if it could be done with better data see comment sections).
However even without knowing the real number of contagion we can estimate its daily percentage change, using as a proxy the percentage change of the various hospitalizations.

See also the Global Trend Line that highlight the tendency of all series. Indeed percentage changes allows to put all Series in teh same natural scale. They could be compared/averaged.

The “Hospital Stress” was growing unitil the end of March, BUT the growth-rate wasdecelerating. This is informative of Contagion Growth rate and its deceleration, and actual hidden number.

…………………………………………………………………………………………..

Comments on data collection strategies.

  • This data collected by the Italian “Protezione Civile” is useful, but far from ideal. Hospitals are overwhelmed with work and sometimes they lag with the publications of data. Would be useful to have hospitalization data from other countries, and for comparisons, and at that stage it would be important to have harmonization of definitions between countries, for all type of cases. Definitely at least for the definition of death associated to Covid-19. Currently Germany death numbers are defined with different criteria that in Italy. Transparent Numbers and criteria for all testing including tested negative, types of intensive care (invasive, non invasive), etc.

  • One of the most important live analysis for decision making would be to build backward the time series of daily New-Infected cases. This is currently not-explicitly observable, but with better data can be reconstructed with a certain lag (incubation period to symptoms is 6 +/- 3 days)[3] [7]. Using all the measured series Positive cases, …until dead Again as mentioned above, also for that type of backtracking it would significantly help if all hospitals keep/disclose not only the current total numbers of cases in a specific “state”, but more importantly the new-arrival for each state. For obvious reasons this is computable for death, and tests cases, but its unclear for different level of hospitalization. Hospitals/Government should ask to patients, collect and release :

  • When was each case having the first symptoms ? [7].

  • New entry in each level of hospitalization ( And possibly increase the details of the level of hospitalization: early-pneumonia, non-invasive int-care, invasive-int-care, etc.).

  • In general record any New entry in any “state” that may be two-way state.

  • In addition for any good analysis on positive cases, countries need to do more testing (as in South Korea) and in particuar randomized population testing, To assess any risk factor, for infectivness, temperature, humuidity, social context, as well as Health- Risk-factors. This is a key part of the Test-Trace-Contain procedure that has been successful to contain the growth of the infection in many Asian countries.

Next, going forward, Exit Strategy?

  • Non-Asian governments have been generally too slow to react (see [10] [14]). While globally there is an on-going research for therapeutics and vaccines, up to few dozens drugs according to the NewYork Times [15], the ability to denoise, measure and predicts “Hospital Stress” is valuable for monitoring as well as making well-informed-quick-decision making. Many ot similar indicators like the simple plotted here will continue to be useful also in the near future during any hypothetical exit strategies. It seems we will have to deal with infection-waves possibly moving bouncing around globally. We would need a global orchestrated response. We may be reducing the amplitude an/or just postponing locally infection-wave now, just to get another one coming back later. Some dynamic public-policy strategies are needed to overcome and gradually reduce the amplitude of each wave(s) of epidemic and carefully try to reopen the social and economic life; Including long distance connections between geographical areas.

  • The next phase of the crisis is to define a strategy, see for example [4],[13]. From this strategy point of view we need to collect and share medical/clinical data on a global scale. The identification of risk factors to define different clusters/groups, set of groups, of the population that can start to go out, possibly in order of their risk of needing hospitalization. As an example we need to be more confident on the estimates that: Younger citizens ( <30 yo, or < 40yo), Healthy with no pre-existing conditions ( no-cardiovascular, high-SOFA score, no-diabetes, non-smokers see reference [5]) have a very low risk of severe COVID-19. These groups may slowly start to “go out” and possibly get infected/immune, while restarting social and economic life. This can only be done when hospitals will start to have some free space for the small proportion of their new controlled cases. (prob of hospitalization < 1% , prob of ICU < 0.1% ).

  • There is of course another challenge for governments, with organizing the bureaucracy, regulations and practical logistic that make sure that the higher risk cluster/s must stay isolated from the lower risk part of the population (e.g. new extended childcare instead of grandparents taking care of children, unemployment benefits for high-risk workers in working age, while having those jobs redistributed to younger low-risk groups).

  • These exits strategies involves monitoring, freedom of traveling, and movements, etc., all these the technical aspects are deeply connected with very important key choices that society will have to make , apparently i an Emergency state. As very well highlighted by Harari, we are likely to face choices between a) totalitarian surveillance and citizen empowerment , b) nationalist isolation and global solidarity, see [22] .

Some Selected References

[1] Great Overview and Summary Presentation (London Business. Sc.) both on Epidemic and Economic aspects https://www.youtube.com/watch?time_continue=5&v=Zu3EF5d_KYM&feature=emb_logo

[2] Official WHO-China report https://www.who.int/docs/default-source/coronaviruse/who-china-joint-mission-on-covid-19-final-report.pdf?fbclid=IwAR3uKKbOcHHh87LVQQAn5FuCC4tTEmsBz7Cu1lUkM06YkAw7jAtcBjyrTD8

[3] Incubation Period and Other Epidemiological Characteristics https://www.mdpi.com/2077-0383/9/2/538?fbclid=IwAR0MZTGj0QtsYSC3fGIj_ByTPGwwg9R9_JWTREScz9wBLzo5CzCpC6V81xk

[4] Epidemic Modelling for UK urging BOJO to change policy. And suggesting and exit yo-yo strategy https://www.imperial.ac.uk/media/imperial-college/medicine/sph/ide/gida-fellowships/Imperial-College-COVID19-NPI-modelling-16-03-2020.pdf?fbclid=IwAR3kXntjIAEBXKisA68dEakB2Ef_Fgl1qs4wWZkqecQcigNnhpGFsSTPTUY

[5] Risk factors for mortality in Wuhan hospitals (190 cases): AGE, Cardiovasc, SOFA score, d-dimer, Diabetes, Chronic Resp, etc. https://www.thelancet.com/action/showPdf?pii=S0140-6736%2820%2930566-3

[6] Data, clinical Lags between on Italian cases https://www.epicentro.iss.it/coronavirus/bollettino/Report-COVID-2019_17_marzo-v2.pdf?fbclid=IwAR22cSPdt5Uqzho9U0n9xLGZL-7iJNli3C9Wjvmx7aZUCLlTdLKbt13hdb4

[7] Ma quanti sono gli ammalati di Covid-19 in Italia? https://www.scienzainrete.it/articolo/ma-quanti-sono-gli-ammalati-di-covid-19-italia/simone-franchini-enzo-marinari-giorgio?fbclid=IwAR1YwMPe0UBU8mGPTt7uqaXZmO4xaNnm826GE39AHlCSUkeRFK2mLWNIaeI

[8] Ralph Baric Coronavirus Expert Talk http://www.microbe.tv/twiv/twiv-591/

[9] Potential false-positive rate https://archive.st/archive/2020/3/www.ncbi.nlm.nih.gov/i8vf/www.ncbi.nlm.nih.gov/pubmed/32133832.html?fbclid=IwAR3UUnyqf7syZHesrfd1Xg1quBbDm6fb8uTt-Pp2R8SMkOnwq27UcF0C7R4

[10] The early phase of the COVID-19 outbreak in Lombardy, Italy https://arxiv.org/abs/2003.09320?fbclid=IwAR1kepPhH-7u1_435pc4gAm7LoHLFMUdJ84cJTz0BVs5I5gm5zaT7qYoRmE

[11] About The Virus Origins, Proximal Origins of SARS (No conspiracy) https://www.nature.com/articles/s41591-020-0820-9 https://www.nature.com/news/engineered-bat-virus-stirs-debate-over-risky-research-1.18787?fbclid=IwAR0SaV035DEKLYOmGBsCm1j9IgnQehOlKPULUO1RKCDrDbdJBeIe_8MShYo

[12] Monitoring Tracing Infection at the individual level https://www.covid-watch.org/article#heatmapImplementation

[13] The Hammer and the Dance. Backtraking. https://medium.com/@tomaspueyo/coronavirus-the-hammer-and-the-dance-be9337092b56

[14] Lock-down-your-Country.Now https://medium.com/ask-your-government-to-lock-down-your-country/look-at-italy-case-and-lock-down-your-country-now-933062f67f51

[15] Drugs Under Testing Globally https://www.nytimes.com/2020/03/22/science/coronavirus-drugs-chloroquine.html

[16] SIR modeling explained https://triplebyte.com/blog/modeling-infectious-diseases

[16b] SIR modeling explained video https://www.youtube.com/watch?v=gxAaO2rsdIs

[17] Scale of missing/ data http://tiny.cc/1e5ylz

[21] The global hunt for a coronavirus drug https://www.ft.com/content/91bd081e-6e7b-11ea-9bca-bf503995cd6f?fbclid=IwAR16XYjsG5xjJTVe7UjJVGrAGvhhjWD5GO2614PhZi2RZ6Csc_N_8pTQSKQ

[22] Key choices (Totalitarian surveillance VS citizen empowerment) and ( nationalist isolation VS global solidarity ) https://www.ft.com/content/19d90308-6858-11ea-a3c9-1fe6fedcca75?fbclid=IwAR1yJlpKICCN-SAtuu5XipsV661qzGzRCE2-HmgyxvJADuKKXVYStgRWsdU

Good Divulgative Videos

[18] Coronavirus General Scientific-Info Video (by those amazing guys at Kurzgesagt) https://www.youtube.com/watch?v=BtN-goy9VOY

[19] Exponential growth of epidemics https://www.youtube.com/watch?v=Kas0tIxDvrg

[20] Bill Gates Ted Talk (2015) https://www.youtube.com/watch?v=6Af6b_wyiwI&t=200s

[16b] SIR modeling explained video https://www.youtube.com/watch?v=gxAaO2rsdIs

[23] Anslysis of data from Protezione civile. In Italian https://www.facebook.com/zanzo.azonzo/videos/1576575472495848

…………………………………………………………………………………………….

Author: Riccardo Senatore

Senior Quant Trader/Strategist Cross-Asset high/mid-frequency, at a major global trading company

Background in Theoretical Physics/Statistical Field Theory (MRes), Computational Neuroscience/Information Theory (PhD)